Application of Non-destructive and Chemical-free Short-Wave Infrared Hyperspectral Imaging (SWIR-HSI) coupled with Machine Learning Regression for Rapid Quantification of Deoxynivalenol (DON) in Individual Corn Kernels

Application of Non-destructive and Chemical-free Short-Wave Infrared Hyperspectral Imaging (SWIR-HSI) coupled with Machine Learning Regression for Rapid Quantification of Deoxynivalenol (DON) in Individual Corn Kernels | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Application of Non-destructive and Chemical-free Short-Wave Infrared Hyperspectral Imaging (SWIR-HSI) coupled with Machine Learning Regression for Rapid Quantification of Deoxynivalenol (DON) in Individual Corn Kernels Rathna Priya Thangaraj Sundaramurthy, Thiruppathi Senthilkumar, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6465545/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Deoxynivalenol (DON), found in corn, is a serious food safety issue. This study utilized a hyperspectral imaging system (HSI) in the shortwave infrared region (Reflectance, 900 – 2500 nm) to quantify the Deoxynivalenol (DON) content in corn kernels. The corn kernels pericarp layers were cracked and spiked with laboratory DON at five concentration levels – 0, 1, 2, 5 and 10 µg/g to mimic the natural distribution of DON. The HSI images were acquired at two different orientations of corn grain – germ-side and endosperm-side. The acquired images were subjected to 15 different preprocessing and feature selection methods. Partial least square regression (PLSR) and support vector machine regression (SVMR) models were developed to correlate the processed spectra with the DON content measured by ELISA. The spectral data from the full spectrum and the spectral data from significant wavelengths obtained using feature selection methods were used to build regression models. The SVMR model developed from the germ-side full spectrum with SNV preprocessing provided the best R 2 prediction of 0.9855 and RMSE prediction of 0.2953. The SVMR model developed using germ-side significant wavelengths with Orthogonal Spectral Correction (OSC) + Standard Normal Variate (SNV)preprocessing provided the best R 2 prediction of 0.9847 and RMSE prediction of 0.3010. Deoxynivalenol near-infrared HSI CARS IRIV preprocessing Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Figure 13 Figure 14 1. Introduction Corn is the largest grain crop in the world, with a global production amounting to 1241 million tonnes in 2023 (FAOSTAT 2023 ). Corn is essential in the human diet because of its 72–73 % carbohydrat content. Corn grain finds various applications as food, feed, and raw material for ethanol production, and the global demand for corn continuously increases yearly. Mycotoxins, the secondary metabolites in food and feed products, are predominantly produced by the pre-harvest Fusarium, post-harvest Aspergillus , and Penicillium species. (Senthilkumar et al. 2016 ). Fusarium infection in field corn before harvest and subsequent mycotoxin contamination of corn grains has affected the yield and quality of corn grains. Deoxynivalenol (DON) (3,7,15-trihydroxy,12,13-epoxy-tricothec-9-en-8-one) predominantly present in corn, is a trichothecene secondary metabolite produced mainly by Fusarium graminearum and Fusarium culmorum. The DON is a very stable compound and can’t be removed from the food supply chain even at higher processing temperatures between 170 and 350℃. The DON content in corn kernels is a serious quality and safety issue, resulting in reduced yield, poor grade, and eventually reduced profit for the producers and processors. Corn remains the economical source of food for consumers around the world, and the presence of DON can severely affect consumers. Several incidents of DON have been reported in the past in cattle feed and processed foods (pasta, bread, flour, extruded foods) (Brumley et al. 1985 ; Schollenberger et al. 1999 ; Castillo et al. 2008 ; EFSA 2013 ; Wu et al. 2017 ). A study on Swine Feed intake found reduced feed intake with 1 µg/g DON. The reduction rate increased proportionally, and complete feed refusal has been observed at concentrations greater than 10 µg/g DON in feed (Munkvold et al. 2018 ). Consumption of DON-contaminated feed has triggered vomiting, nausea and adverse effects in cattle and swine. DON inhibits the cell signalling process in eukaryotic cells. Its compounds have been reported to cause throat irritation, esophageal cancer, diarrhea, dizziness, fever, headache, and other adverse effects when consumed. (Prieto-Simón et al. 2007 ). The DON, due to its thermal stability and the potential health risk, is regulated by most countries with maximum allowable limits (MAL) for baby food products, adult foods, and animal feed. The DON MAL for infant and baby foods is in the range of 200 µg/kg to 600 µg/kg, direct adult human consumption is in the range of 750 µg/kg to 1200 µg/kg, and animal feed in the range of 1000 to 5000 µg/kg (EFSA 2013 ; Food and Agriculture Organization of the United Nations (FAO) 2015 ; Regulatory Guidance (RG-8). Government of Canada. 2017). Current analytical methods to detect mycotoxins (DON and a combination of different mycotoxins) include immunochemical and analytical methods like liquid and gas chromatography (LC, GC) and assay-based. These methods are expensive, time-consuming, require professional knowledge, and cannot be applied directly in the field (McMullin et al. 2015 ). Several non-destructive methods have been recently studied for their potential to detect mycotoxin contamination and fungal infections in cereals and cereal products, such as IR spectroscopic methods (Near-infrared (NIR), Shortwave infrared (SWIR), Visible NIR).Shi et al. 2022 demonstrated using NIR spectroscopy to rapidly investigate different quality parameters associated with soybeans.Rathna Priya and Manickavasagan 2021 used NIR spectroscopy for corn grain characterization, including seed viability, kernel hardness, haploid kernel identification, moisture, oil, and starch content. Several studies utilized NIR spectroscopy between the 1000 and 2500 nm spectral range for rapid fusarium -damaged wheat kernel (FDK) identification and DON contamination (Peiris et al. 2009 ; Peiris et al. 2010 ; Kautzman et al. 2015 ). In maize, fusarium infection detection, aflatoxin and mycotoxin contamination detection, and quantification of AFB1 toxin and fumonisins have been widely studied. In addition, IR spectroscopic methods can only detect spectral characteristics and chemical changes at a single spot on the grain and do not reflect the true contamination levels of the individual grain. Hyperspectral imaging systems (HSI) can overcome this disadvantage of NIR spectroscopic techniques. In recent years, studies on the quality and safety aspects of food using hyperspectral imaging (HSI) have gained popularity. HSI acquires information in a wide range of the electromagnetic spectrum (250–2500 nm), and depending upon the application, the HSI system could collect information from specific spectral ranges in the Ultraviolet-visible (UV-VIS) regions (250–500 nm), visible and near-infrared (VIS-NIR) regions (400–1000 nm), near-infrared (NIR) regions (900–1700 nm), and short wave infrared (SWIR) regions (900–2500 nm). HSI studies utilizing the UV-VIS range predominantly focus on visible changes, defects, and other physical features. In contrast, the NIR and SWIR ranges can detect physicochemical components and contaminants (Femenias et al.2022). Unlike conventional spectroscopic techniques, HSI is a hypercube comprising spectral and spatial information. The hypercube is a 3-D data cube with spatial axes (X, Y) and spectral axes (λ), enabling specific regions to be extracted and analyzed. (Jiang et al. 2010 ). HSI has the potential to screen single grain and acquire individual kernel data for numerous grains simultaneously. The HSI allows the selection of X and Y axes of each individual kernel. Thus, the acquired HSI or hypercube contains spectral data from n x n pixels of every kernel. The background could be removed either manually or automatically. Thus, HSI is a potential tool for analyzing the chemical profile of a single kernel at the n x n pixel level acquired at different wavelengths. In combination with chemometric techniques, HSI has been successfully utilized to determine different quality characteristics in foods, including fruits, vegetables, cereals, pulses, oilseeds, fish, and meat, by extracting and analyzing relevant information from the hypercube. Regression and classification methods such as principal component analysis (PCA), support vector machine (SVM), partial least squares regression (PLSR), artificial neural network (ANN), deep learning artificial neural network (ANNDL), multiple linear regression (MLR), partial least squares discriminant analysis (PLSDA), k-nearest neighbour (KNN) have been utilized successfully for analyzing hyperspectral data, determining the quality parameters and composition of food matrices and also for quantitatively predicting the targeted components and contaminants in food. Studies show that HSI has been successfully used to detect defects, bruises, decay and physical injury in fruits (apple, strawberries and citrus) and vegetables (onion, mushroom, cucumber). Studies on detecting adulterants, pesticides, microbial contaminants and other chemical contaminants have also been reported on fresh produce and other food products. (Sun 2010 ; Feng and Sun 2012 ; Ravikanth et al. 2017 ; Xu et al. 2023 ). Most studies on HSI utilize PLSR, SVMR, PCA and ANN regression models for prediction. PLSR and SVMR are commonly used to study linearity and nonlinearity in the datasets (Vapnik 2000 ; Abdi 2003 ; Cruz-Tirado et al. 2022 ; Saha et al. 2023 ). In addition, feature wavelength selection using different methods is currently utilized to improve the model performances and accurately detect and identify food components. These strategies reduce the complexity of the model by decreasing the collinearity and errors in the HSI data, thereby improving the precision of the model. Competitive Adaptive Reweighted Sampling (CARS) and Iteratively Retaining Informative Variables (IRIV) are two of the most successful wavelength selection strategies deployed in HSI data analysis (Zhang et al. 2022 ; Wang et al. 2022 ). In grain elevators, random sampling is performed to decide the DON levels of each lot and grains with different contamination levels are blended to achieve the permitted levels. Recent studies have proposed HSI classification to differentiate healthy and fusarium -infected grains to decrease the overall contamination levels by discarding the infected grains (Xing et al. 2019 ; Alisaac et al. 2019 ; Parrag et al. 2020 ; Femenias et al. 2022a ). However, limited studies quantify DON in corn kernels to remove DON-contaminated grains from entering the food chain. Therefore, the objectives of this research are 1. to investigate the potential of shortwave near-infrared hyperspectral imaging system (SWIR-HSI) to quantify the deoxynivalenol (DON) content in corn kernels, 2. to investigate the effect of the position of the corn grains (germ-side or endosperm-side) on the ability of HSI in predicting DON levels, 3. to determine the best combination of preprocessing and chemometric technique for accurate quantification of DON and 4. to investigate the model enhancement performances of CARS and IRIV feature wavelength selection methods. 2. Materials and Methods 2.1 Sample Preparation A separate study was first conducted to determine the suitable sample preparation technique to mimic the real DON contamination in corn kernels. The study explored DON absorption using the injection method on whole corn kernels and the soaking method on both whole and cracked kernels using water, methanol, and acetonitrile. The methods were validated by analyzing the absorbed DON, optical microscopic analysis, and scanning electron microscopic analysis. The soaking cracked method was best validated by DON absorption and recovery analysis (Priya and Manickavasagan 2023 ). The samples for this study were prepared using the soaking cracked method with four concentration levels of DON and one control sample– 0,1, 2, 5 and 10 µg/g (ppm).Schaafsma, Frégeau-Reid, and Phibbs n.d. explained the importance of making a small crack in the corn pericarp to facilitate better absorption of DON inside the corn kernel. The cracked (small crack in the pericarp layer) corn kernels were soaked in the DON solution made with DON procured from Millipore Sigma (Sigma-Aldrich, Oakville, Canada) and dissolved in distilled water explained inPriya and Manickavasagan 2023 was replicated in this study using the 2019 crop year corns procured from the Ministry of Agriculture, Ontario. The flowchart of the experimental design is shown in Fig. 1 . The moisture content of the corn kernels was determined by the hot air oven method(Shreve 2006 ) using a laboratory oven (Binder FD53-UL, Tuttlingen, Germany). After soaking treatments, the soaked kernels were again dried at 55℃ until the initial moisture content of 9.21% (dry basis) was achieved and stored at 4℃ until further analysis. 2.2 Corn kernel samples for image acquisition The Corn kernels stored at 4℃ were allowed to reach room temperature before hyperspectral image acquisition. Eighty individual corn kernels were picked from control, 1, 2, 5 and 10 µg/g concentration level samples for total corn kernels of 80 X 5 = 400 for this study. Schaafsma, Frégeau-Reid, and Phibbs n.d. studied the natural distribution of DON in different parts of the corn kernel. They found that corn kernel’s pericarp, germ, and endosperm had DON levels at 55%, 25% and 20%, respectively. The corn kernel's orientation or position during HSI would play a significant role in quantifying DON. So, for this study, each individual kernel was subjected to hyperspectral imaging on the germ-side and endosperm-side of the kernel. So, 400 germ-side and 400 endosperm-side individual kernels HSI images were acquired. 2.3 SWIR Hyperspectral Image Acquisition The SWIR hyperspectral imaging system (Headwall Photonics, USA) located at the APHTC, Lethbridge College, was utilized for this study. The HSI system, as shown in Fig. 3 , comprises 1. an MCT sensor-based camera unit coupled with a spectrograph, 2. an adjustable power level quartz halogen lamp (USHIO 150 W) as the illumination source, 3. a movable stage for line scanning operation, and 4. a data capture and handling system (Hyperspec III – v3.1.5). The corn kernels were arranged on the sample tray (18 kernels – 3 kernels arranged at equal distances in 6 rows) row-wise, as shown in Fig. 4 , and reflectance HSI images were captured in the SWIR spectral range 900–2500 nm. The line scan HSI system with a 9.6 nm spectral resolution collected 384 spatial and 169 spectral bands. The white reference was collected using a Spectralon white reference (99%, Labsphere, North Sutton, NH) and the black reference by closing the lens opening with a dark cap. The white and dark references were calculated every 30 minutes, and the corrections were automatically added to the sample images. The speed of the sample stage was set at 16.297 mm/s and an exposure time of 13 ms to eliminate vibrations and overlapping of spectral data on the same regions of the kernel. Also, the corn kernels were arranged on the stage between 44mm and 205mm, with an entire stage length of 230 nm, and the hyperspectral images were captured only between these lengths. The power level of the illumination was set at 105 W. The SWIR system, including the lights, was turned on 30 minutes before an imaging session to maintain stability and reduce variations in the system. Corn kernels were initially arranged on the sample stage with the germ-side facing upwards, and hyperspectral images were acquired. The sample stage will move horizontally till the set length, and the image with the spectral and spatial information will be captured line by line. Immediately after this, without changing the arrangement, the corn kernels were turned with the endosperm-side facing upwards, and a second hyperspectral image was acquired. Thus, every kernel had both the germ-side and the endosperm-side captured. Each corn kernel was given a number sequentially and labelled accordingly. Thus, the acquired hypercube consisted of two spatial axes (367 x 368 pixels) and one spectral axis with 169 bands collected at every 9.6nm wavelength interval between 900 and 2500 nm. The acquired hypercube in pixels was normalised as reflectance, and the discrepancies arising from the spectral and spatial radiations were corrected automatically using Hyperspec III software to obtain explicit and distortion-less images. The corrected images were stored in high dynamic range (HDR) format. 2.4 Quantification of DON content The DON uptake in corn kernels was determined using a commercial Deoxynivalenol ELISA kit, which can detect DON in concentrations between 3 to 243 ng/ml. The ELISA kit utilizes antigen-antibody interaction and followed by horseradish peroxidase colorimetric detection, the DON antigens in the corn kernel matrix are quantified (Berthiller et al. 2013 ; Munkvold et al. 2018 ). The corn kernels from the control and different levels of DON concentration samples in triplicates were grounded. The steps involved in the competitive assay for DON quantification are shown in Fig. 5 as a flowchart. The correction wavelength was set at 630 nm, and the optical density was measured at 450 nm using a spectrophotometer (Thermo Scientific Multiskan FC plate reader). The concentration of DON in each treatment method was determined by extrapolating the percentage of absorbance values (negative correlation) in the standard graph for various concentrations of DON. 2.5 Spectral Data Preprocessing The HDR format hypercubes were transformed into .mat files (Matlab files) for further processing. The dead pixels in the data were removed by applying a median, and the spatial window for each of the 18 corn kernels in a hyperspectral image was determined by column indexing. This window selection would facilitate the proper selection of ROI during segmentation. Each corn kernel was labelled using the bwlabel function. The threshold function created a logical mask to capture the 18 corn kernels from the original image at all 169 wavelengths to segment all 18 individual corn kernels. Finally, each corn kernel was cropped from the segmented image and stored separately as one ROI. The spectral data from every corn kernel was extracted for further preprocessing to remove unimportant information such as background disturbances, scattering effect and baseline drift. In this study, the raw data were preprocessed using both traditional and advanced preprocessing techniques to study their effects on the ability of the model to quantify DON content in corn kernels. A total of 15 preprocessing techniques were utilized in this study, including weighted least squares, external parameter orthogonalization filter (EPO), gap segment, detrend, mean centring, generalized least squares (GLS) weighting, multiplicative scatter correction (MSC), orthogonal signal correction (OSC), probabilistic quotient normalization (PQN), Savitsky – Golay smoothing, standard normal variate (SNV), Whitaker filter and their combinations. Since one preprocessing technique does not apply to all data, we must identify suitable preprocessing methods for our study. After analyzing and comparing the effects of each preprocessing technique on the model performance, a suitable preprocessing or combination of different methods was chosen for DON content prediction. 2.6 Principal Component Analysis (PCA) The preprocessed HSI data contains more variables and often requires chemometric tools to build and analyze different classification and regression approaches. There are numerous modelling techniques for pattern recognition and grouping, but principal component analysis (PCA), least discriminant analysis (LDA) and support vector machines (SVM) are the most used techniques. This study used PCA (PLS toolbox in SOLO software, Eigenvector Research, Inc.) to analyze the sources of variances or principal components (PCs), which capture the maximum variations in our hyperspectral data. PCA captures the maximum information in the first component, followed by the rest of the components, thus reducing higher dimensions of data into fewer components containing the most valuable information. 2.7 Feature Wavelength Selection Since the HSI data collected is massive, analyzing and model building could consume huge amounts of time and data, and owing to multi-collinearity, model performance could be lower. To overcome this disadvantage, selecting important wavelengths that contribute to the most valuable information for DON quantity prediction during model development becomes important. This would drastically reduce the hypercube data, enhancing the model-building speed, performance, and prediction accuracy. This study utilized two promising feature wavelength selection methods: competitive adaptive reweighted sampling (CARS) and iteratively retaining informative variables (IRIV). 2.7.1 CARS CARS algorithm is commonly used to select important variables or feature wavelengths based on absolute coefficients. The CARS algorithm is performed based on a series of steps. 1. Each feature weight is evaluated based on the regression coefficient's absolute value, and 2. The Monte Carlo technique groups N subsets of wavelengths obtained during every sampling run based on the absolute coefficient corresponding to each wavelength, 3. Exponentially decreasing function (EDF) and adaptive reweighted sampling (ARS) are utilized to choose the principal features. 4. the significant wavelengths are selected (Li et al. 2019 ; Saha et al. 2023 ). The Monte Carlo sampling runs were optimized to seventy. The selected CARS wavelengths were used for prediction model development (MATLAB version 2020a, The Mathworks Inc., Natick, USA). . 2.7.2 IRIV IRIV algorithm works based on binary matrix shuffling for the selection of features (Wang et al. 2022 ). The RMSE of cross-validation is used in the IRIV algorithm to evaluate each feature's performance. The model population analysis (MPA) technique categorizes each variable into strong, medium, weak, and no information variables. Several repetitions are performed, the variables repeating in each subset are given higher weights, and variables with lower weights and interference are eliminated, retaining only variables with effective information. Finally, a reverse elimination is performed, and the remaining variables are chosen as the feature variables. This study performed twenty-fold cross-validation, and the chosen wavelengths were utilized for prediction model development (MATLAB version 2020a, The Mathworks Inc., Natick, USA). 2.8 Model Building and Evaluation Three models were trained for this study – 1. germ-side up, 2. endosperm-side up, 3. combined model. The combined model was developed by integrating the dataset irrespective of the side of the corn kernel. This was used to study the difference in model performance when used in real-time inspection. PLSR and SVMR were utilized to build a model and predict DON in single corn kernels. PLSR is one of the most widely applied linear predictive methods and could be used for multivariate data analysis. PLSR is a supervised method for better predictions in multivariate problems (Mehmood et al. 2020 ). PLSR was initially trained on the full spectra using different preprocessing methods. The best combination of preprocessing method with PLSR was identified. Also, PLSR regression models were developed utilizing the wavelengths identified by feature selection methods. SVMR is a nonparametric, statistical learning technique that balances prediction accuracy and data generalization. SVMR establishes the non–linear relationship in the data and retains a sound generalization of the untested data (Zhong et al. 2019 ). SVMR has the advantage of handling big multivariate datasets with noisy patterns (Deiss et al.2020). Like PLSR, SVMR was also trained on the whole and selected wavelength spectra (PLS toolbox in SOLO software, Eigenvector Research, Inc.). The robust Venetian blinds ten-fold cross-validation was used for model building. The mean performance of all the models was then computed for cross-validation. The Kennard-Stone algorithm randomly splits the data into the calibration and predictive sets. The algorithm selected 290 samples for calibration sets and 126 for prediction sets for the individual models (germ-side and endosperm-side). For the combined model, 588 samples were selected for the calibration and 252 for the prediction set. All the models used the exact calibration and prediction datasets to eliminate dataset errors and bias in model training. The calibration, cross-validation, and prediction coefficient of determination ((R 2 c) , (R 2 cv ) and (R 2 p )) were chosen as the evaluation metrics for the model performance. The calibration, cross-validation, and prediction root mean square errors ((RMSEC), (RMSECV) and (RMSEP)) were also used to assess the variations between predicted and real values in the corresponding sets. For a model to perform well, the R 2 of calibration and prediction should be high, whereas the corresponding RMSE values should be low. The PLS toolbox by SOLO (Eigenvector Research Inc.) was utilized to develop PLSR and SVMR regression models. The feature wavelength selection, CARS and IRIV were performed in MATLAB (version 2020a, The Mathworks Inc., Natick, USA). 3. Results and Discussion 3.1 DON content in treated corn kernels The DON uptake levels in corn kernels by the soaking treatment method were determined by the ELISA method. The DON uptake levels ranged between 0 and 5.58 µg/g in the corn kernels. For DON treatment at concentrations 1, 2 and 5 µg/g, the average recovery rates of 68%, 66% and 72% were observed in the corn kernels, respectively. For higher concentrations at 10 µg/g, the average recovery rate was lower at 56%. This could be due to the slow rate of water absorption in the kernel matrix and loss of the DON deposited on the kernel surface due to drying or other handling procedures. 3.2 Spectral Analysis The spectral curves of individual corn kernels from the germ-side, endosperm-side and combined model are shown in Fig. 6 . The spectral curves for the germ and endosperm-side models showed similar trends but slight variations in the reflectance values. The variations in reflectance between the two positions of corn kernels can be seen in Fig. 6 d. The germ-side spectral reflectance curve was higher than the endosperm-side. Both curves overlap between the wavelength range of 1250 and 1450 nm, corresponding to the N-H combination bands of proteins in the kernels (Sharma et al. 2020 ). The slight changes in the spectral reflectance values between the germ-side and endosperm-side of the kernels could either be due to a change in the kernel composition between the two sides or the chemical modifications because of DON distribution between both sides. The germ portion is rich in oil and protein, whereas the endosperm-side is rich in starch (carbohydrate). This could cause a difference in the reflectance values. Seven individual peaks were observed for the corn kernels at 1101, 1301, 1650, 1825, 2016, 2225 and 2420nm from the germ and endosperm-side spectrum. The seven wavelengths can be attributed to fundamental Carbon-Hydrogen, Oxygen-Hydrogen and Nitrogen-Hydrogen bonds (Saha et al. 2023 ). The 1101, 1301 and 1650 nm wavelengths correspond to the Carbon-Hydrogen second overtone stretch in carbohydrates, the Nitrogen -Hydrogen first overtone stretch and the Carbon = Carbon stretch in protein molecules, respectively (Sharma et al. 2021 ). It has been widely known that the wavelengths between 1500–2000 nm are attributed to the Nitrogen-Hydrogen bonds in proteins, and between 1000–1100 and 2000–2500 nm are attributed to Carbon-Hydrogen bonds in carbohydrates. The wavelengths linked to DON toxin could not be directly identified using the spectral reflectance curve, and further analysis using chemometric tools is necessary. 3.3 Spectral Analysis using PCA PCA was used to examine the correlation or band dependency between variables by applying statistical properties. Weighted least squares preprocessing and mean centring were used to eliminate multi-collinearity in raw data. The principal components (PCs) were analyzed for data clustering and the percentage of variance captured. The highest contrast or variance was observed in the first PC, capturing 95.6% of the variance, and the lowest variance observed in the last band was 3.88%, as shown in Fig. 7 a. Thus, the overall variance was captured by PC1 alone. Data clustering was observed from the PCA plot, and the calibration and prediction set showed cluster formation (Fig. 7 b). This grouping indicates that the spectral characteristics are related to the DON concentration in corn kernels. Thus, the PCA results further support the potential of HSI in predicting the DON concentration in individual corn kernels. 3.4 Evaluation of developed models using whole spectra The PLSR and SVMR regression models were developed utilizing the entire spectra of the corn kernels and their reference DON content. Each model was trained with and without preprocessing raw spectral data to observe and study the impact of different preprocessing techniques on the model's performance. A total of 15 preprocessing techniques have been applied to all three models – 1. germ-side model, 2. endosperm-side model, and 3. combined model. The changes in raw spectral data during each preprocessing method were shown in Figs. 8 , 9 , and 10 for all three models. Tables 1 , 2 and 3 summarize the results for DON quantification in individual corn kernels for all three models (calibration, cross-validation and prediction). The predicted and actual DON content plot was used to identify the robust prediction models for DON quantification (The red line in the plot). If the sample points are closer to the best correlation fit line, the model's accuracy in predicting DON content will be higher and vice versa. Table 1 Prediction results of combined model (both germ-side and endosperm-side) to detect DON in individual corn grains using full spectrum Model Pre-processing (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP PLSR None 8 0.8239 1.0037 0.8162 1.0255 0.8382 0.9682 Weighted LS 10 0.9015 0.7504 0.8934 0.7811 0.8889 0.8029 Detrend 9 0.9099 0.7182 0.9037 0.7426 0.9112 0.7207 EPO 10 0.9276 3.018 0.9189 3.0251 0.9231 3.0063 Gap 1st derivative 10 0.8988 0.7611 0.8912 0.7894 0.9001 0.7622 GLS weighting 11 0.9313 3.0148 0.9234 3.0254 0.9251 3.0045 Mean centering 10 0.9112 1.4143 0.8957 1.7632 0.8854 1.6529 MSC (mean) 11 0.9288 0.6381 0.9182 0.6844 0.9214 0.6766 OSC 11 0.9281 0.6416 0.9184 0.6838 0.9211 0.6822 PQN 11 0.911 0.7133 0.9008 0.7534 0.9146 0.7124 Sav-Gol Smoothing 11 0.8466 0.9371 0.8264 0.9974 0.8557 0.9186 SNV 11 0.929 0.6375 0.9183 0.6837 0.921 0.6784 Whittaker Filter 10 0.8998 0.7571 0.893 0.7828 0.9039 0.7498 Detrend + SNV 11 0.922 0.6682 0.9139 0.7019 0.9158 0.6991 MSC + SNV 11 0.929 0.6375 0.9184 0.6836 0.921 0.6784 OSC + SNV 11 0.9294 0.6354 0.9196 0.6784 0.9211 0.6787 SVMR None 419 0.9812 0.3271 0.9309 0.6269 0.9649 0.4563 Weighted LS 443 0.9832 0.3106 0.9551 0.5058 0.9721 0.4089 Detrend 375 0.9823 0.3181 0.961 0.4707 0.9746 0.3889 EPO 483 0.9829 0.3115 0.9695 0.4186 0.9798 0.3434 Gap 1st derivative 554 0.8053 1.0721 0.7908 1.1082 0.822 1.0687 GLS weighting 542 0.9702 0.4139 0.9605 0.4748 0.9669 0.4465 Mean centering 419 0.9812 0.3271 0.9309 0.6269 0.9649 0.4564 MSC (mean) 366 0.9805 0.3346 0.9617 0.4669 0.9718 0.4101 OSC 406 0.9777 0.3565 0.9371 0.5978 0.9719 0.4076 PQN 429 0.3891 1.8764 0.3745 1.8951 0.4054 1.8865 Sav-Gol Smoothing 456 0.9672 0.4328 0.9113 0.7098 0.9459 0.5657 SNV 500 0.9947 0.1738 0.9674 0.4298 0.9851 0.2959 Whittaker filter 370 0.9817 0.3237 0.9651 0.4464 0.9751 0.3837 Detrend + SNV 511 0.9871 0.2725 0.968 0.4263 0.9791 0.3525 MSC + SNV 500 0.9947 0.1738 0.9674 0.4298 0.9851 0.2959 OSC + SNV 497 0.9913 0.2242 0.9585 0.4855 0.9818 0.3289 LS – Least squares; PLSR – Partial least square regression; SVMR – Support vector machine regression; EPO -external parameter orthogonalization; GLS – generalized least squares; MSC- multiplicative scatter correction; OSC - orthogonal signal correction; PQN -probabilistic quotient normalisation; Sav-Gol - Savitsky – Golay smoothing; SNV – standard normal variate; R 2 c, R 2 cv, R 2 p – coefficient of determination of calibration, cross-validation, and prediction; RMSEC, RMSECV, RMSEP – root mean square error of calibration, cross-validation and prediction. Table 2 Prediction results of the germ-side model to detect DON in individual corn grains using full spectrum Model Pre-processing (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP PLSR None 9 0.9151 0.7024 0.8994 0.7646 0.9359 0.6402 Weighted LS 10 0.9181 0.6782 0.9068 0.7236 0.9359 0.6469 Detrend 9 0.9243 0.6518 0.9137 0.6961 0.9482 0.5671 EPO 9 0.9323 3.0903 0.9213 3.0918 0.9478 2.9663 Gap 1st derivative 10 0.9168 0.6835 0.9052 0.7294 0.9453 0.5911 GLS weighting 8 0.9298 3.0925 0.9183 3.0946 0.9487 2.9587 Mean centering 7 0.8710 3.1455 0.8557 3.1577 0.8959 2.9937 MSC (mean) 11 0.9385 0.5872 0.9252 0.6484 0.9521 0.5467 OSC 11 0.9413 0.5740 0.9221 0.6620 0.9570 0.5139 PQN 9 0.9002 0.7484 0.8835 0.8087 0.9376 0.6332 Sav-Gol Smoothing 10 0.8598 0.8873 0.8463 0.9292 0.9079 0.7844 SNV 10 0.9337 0.6102 0.9228 0.6585 0.9481 0.5678 Whittaker Filter 10 0.9255 0.6468 0.9146 0.6926 0.9215 0.7010 Detrend + SNV 9 0.9248 0.6498 0.9136 0.6965 0.9396 0.6111 MSC + SNV 10 0.9337 0.6102 0.9228 0.6585 0.9481 0.5678 OSC + SNV 11 0.9444 0.5586 0.9265 0.6426 0.9531 0.5369 SVMR None 219 0.9520 0.5276 0.9222 0.6649 0.9317 0.6484 Weighted LS 160 0.9844 0.2984 0.9619 0.4654 0.9740 0.3983 Detrend 168 0.9836 0.3061 0.9637 0.4539 0.9758 0.3872 EPO 168 0.9927 0.2041 0.9698 0.4131 0.9823 0.3263 Gap 1st derivative 120 0.7832 1.1338 0.7694 1.1684 0.7837 1.1749 GLS weighting 192 0.9762 0.3705 0.9646 0.4484 0.9687 0.4404 Mean centering 219 0.9519 0.5276 0.9222 0.6649 0.9317 0.6484 MSC (mean) 173 0.9847 0.2944 0.9695 0.4151 0.9772 0.3726 OSC 187 0.9786 0.3491 0.9465 0.5503 0.9729 0.4069 PQN 214 0.3460 1.9387 0.3266 1.9637 0.4122 1.9308 Sav-Gol Smoothing 225 0.9295 0.6408 0.8941 0.7769 0.9099 0.7514 SNV 239 0.9955 0.1595 0.9742 0.3817 0.9854 0.2953 Whittaker filter 172 0.9817 0.3244 0.9658 0.4412 0.9787 0.3598 Detrend + SNV 244 0.9903 0.2347 0.9733 0.3891 0.9803 0.3443 MSC + SNV 239 0.9955 0.1595 0.9742 0.3817 0.9855 0.2953 OSC + SNV 169 0.9925 0.2057 0.9627 0.4593 0.9818 0.3300 Table 3 Prediction results of the endosperm-side model to detect DON in individual corn grains using full spectrum Model Pre-processing (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP PLSR None 6 0.7451 1.2072 0.7312 1.2397 0.8239 1.0112 Weighted LS 8 0.8771 0.8382 0.8440 0.9446 0.9075 0.7279 Detrend 9 0.9060 0.7331 0.8874 0.8028 0.9139 0.7060 EPO 9 0.9192 2.9621 0.8998 2.9768 0.9253 2.8997 Gap 1st derivative 11 0.9058 0.7355 0.8894 0.7971 0.9119 0.7164 GLS weighting 9 0.9244 2.9468 0.9074 2.9613 0.9194 2.9385 Mean centering 9 0.9053 2.9754 0.8840 3.0075 0.9109 2.9257 MSC (mean) 10 0.9238 0.6616 0.9106 0.7166 0.9152 0.6994 OSC 10 0.9246 0.6583 0.9053 0.7379 0.9188 0.6869 PQN 11 0.9189 0.6822 0.8980 0.7656 0.9184 0.7027 Sav-Gol Smoothing 10 0.8083 1.0493 0.7941 1.0885 0.8227 1.0025 SNV 11 0.9308 0.6305 0.9146 0.7006 0.9208 0.6825 Whittaker Filter 8 0.8604 0.8935 0.8440 0.9445 0.9031 0.7496 Detrend + SNV 11 0.9298 0.6348 0.9047 0.7416 0.9186 0.6858 MSC + SNV 11 0.9307 0.6305 0.9146 0.7006 0.9208 0.6825 OSC + SNV 11 0.9374 0.5994 0.9179 0.6874 0.9231 0.6718 SVMR None 226 0.9824 0.3209 0.8995 0.7648 0.9652 0.4490 Weighted LS 236 0.9792 0.3477 0.9338 0.6179 0.9650 0.4476 Detrend 268 0.9791 0.3515 0.9455 0.5621 0.9728 0.4022 EPO 257 0.9915 0.2218 0.9595 0.4834 0.9859 0.2853 GAP 1st derivative 260 0.7480 1.2216 0.7263 1.2687 0.8092 1.0971 GLS weighting 212 0.9719 0.4071 0.9568 0.5014 0.9705 0.4098 Mean centering 226 0.9824 0.3209 0.8995 0.7648 0.9652 0.4490 MSC (mean) 199 0.9783 0.3558 0.9482 0.5476 0.9752 0.3786 OSC 215 0.9742 0.3874 0.9074 0.7311 0.9669 0.4394 PQN 226 0.3214 1.9821 0.3116 1.9967 0.3072 1.9841 Sav-Gol Smoothing 240 0.9695 0.4225 0.8721 0.8607 0.9505 0.5321 SNV 270 0.9999 0.0099 0.9540 0.5155 0.9831 0.3108 Whittaker filter 255 0.9775 0.3620 0.9496 0.5411 0.9766 0.3658 Detrend + SNV 194 0.9980 0.1072 0.9557 0.5048 0.9859 0.2821 MSC + SNV 270 0.9999 0.0099 0.9540 0.5155 0.9831 0.3108 OSC + SNV 205 0.9637 0.4593 0.9238 0.6636 0.9629 0.4605 For the combined model where the corn kernels are imaged irrespective of the position of the kernel, SNV preprocessing with PLSR model development provided the best prediction coefficient of determination (R 2 p ) of 0.921 and RMSEP values of 0.6784 utilizing 11 LVs. The combination of the MSC + SNV preprocessing technique also yielded the same results. For the germ-side model, PLSR model with OSC + SNV yielded the best prediction coefficient of determination (R 2 p ) of 0.9531 and RMSEP of 0.5369 (11 LVs), followed by PLSR with MSC mean preprocessing technique with R 2 p value of 0.9521 and RMSEP values of 0.5467 with 11 LVs. For the endosperm-side model, PLSR models with OSC + SNV provided the best prediction coefficient of determination (R 2 p ) of 0.9231 and an RMSEP of 0.6718 with 11 LVs. The PLSR results obtained in this study were higher than those reported in the literature. Zhao et al. 2020 used PLSR to predict DON in wheat flour with R2 p in the range of 0.69–0.726. Tekle et al. 2015 used PLSR with SNV to quantify DON in single oat kernels with R 2 p of 0.81. In SVMR models with SNV provided the highest R 2 p of 0.9851 and RMSEP of 0.2959 for the combined model; the MSC + SNV preprocessing technique performed better (R 2 p 0.9851 and RMSEP of 0.2959) for germ-side model and EPO and Detrend + SNV preprocessing techniques performed better for endosperm-side model. These results are in accordance with the study utilizing SVMR for predicting DON levels in winter wheat with an accuracy greater than 80%. The developed SVMR model also predicted that the samples with high DON contamination were more significant than 200 µg/kg with an accuracy of 90% (Marzec-Schmidt et al. 2021 ). The SNV preprocessing technique is important in enhancing the model performance and predicting DON in all the models. SNV increases the signal-to-noise ratio to compensate for the differences and errors caused by the light scattering. EPO removes the difference in spectrometer temperature and corn kernel moisture. At the same time, detrend aims to reduce data interference due to kernels' size and other spectral peak shape issues. The germ-side model yielded the highest coefficient of determination for prediction results (Fig. 11 ). These results further support the fact that deposition and absorption of DON in fusarium- infected kernels will be higher in the pericarp and germ portion than the endosperm portion, as stated by Schaafsma, Frégeau-Reid, and Phibbs n.d. Also, from the results, it is evident that DON prediction in individual corn kernels greatly depends on the orientation or position of the corn kernel during imaging. Therefore, for DON prediction, the germ-side of corn kernels provided the best results and proved to be the best position to capture HSI. 3.5 Evaluation of developed models with CARS and IRIV selected feature wavelengths The CARS was utilized to select the feature wavelengths. The varying trends of the variables, RMSECV and regression coefficient path for the number of sampling runs are shown in Fig. 12 . The figure shows that the number of sampled variables with little or no information was removed rapidly with the number of sampling runs. Also, the 10-fold RMSECV values observed from 1 to 20 were deceased, and the lowest point was achieved at the sampling runs after 20, indicating the removal of ineffective wavelengths. After around 42 runs, the RMSECV values increased, suggesting that the wavelengths and variables containing important information for DON prediction are being removed. Thus, combining wavelengths with the lowest RMSECV values is collected for feature wavelength selection. Also, the blue patch in the figure of regression coefficient path for individual wavelength indicates the best subgroup with selected wavelengths with the lower RMSECV values. The CARS algorithm selected 43, 51 and 47 wavelengths for the germ-side, endosperm-side and combined models, respectively, as given in Table 4 . These CARS-selected wavelengths were utilized to develop PLSR and SVMR models preprocessed with the OSC + SNV techniques, which were identified as best for the germ-side position of corn kernels. Table 5 shows the DON prediction model developed using PLSR and SVMR with OSC + SNV with selected wavelengths. SVMR for the germ-side model was observed to provide the best prediction coefficient of determination R 2 p of 0.9847 and RMSEP of 0.3010. The scatter plot of the SVMR model with CARS selected wavelength for the germ-side is shown in Fig. 13 . The performance of the PLSR model was lower when compared with that of SVMR in predicting DON in corn kernels. Table 4 Feature wavelengths selected from the full spectrum (900–2500nm) of corn grains using CARS and IRIV Corn grain position Wavelength selection method Number of wavelengths Wavelength (nm) Germ-side up CARS 43 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1072.61, 1091.66, 1110.72, 1120.24, 1139.3, 1225.04, 1320.31, 1396.53, 1453.69, 1482.27, 1587.07, 1634.7, 1644.23, 1720.44, 1758.55, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09,1958.62, 1968.15, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78, 2025.31, 2082.47, 2101.52, 2111.05, 2187.27, 2215.85, 2225.37, 2263.48, 2273.01 IRIV 38 901.12, 920.17, 967.81, 986.86, 1015.45, 1072.61, 1091.66, 1110.72, 1120.24, 1129.77, 1139.3, 1225.04, 1272.67, 1301.26, 1339.36, 1377.47, 1396.53, 1453.69, 1463.21, 1482.27, 1558.48, 1587.07, 1720.44, 1768.08, 1863.35, 1882.4, 1910.98, 1949.09, 1977.67, 2025.31, 2034.83, 2044.36, 2101.52, 2177.74, 2187.27, 2215.85, 2273.01, 2330.17 Endosperm-side up CARS 51 901.12, 939.23, 948.76, 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1072.61, 1091.66, 1110.72, 1301.26, 1320.31, 1358.42, 1377.47, 1406.05, 1415.58, 1444.16, 1453.69, 1463.21, 1472.74, 1482.27, 1548.96, 1558.48, 1587.07, 1768.08, 1777.61, 1853.82, 1863.35, 1872.88, 1901.46, 1910.98, 1920.51, 1949.09, 1977.67, 1987.2, 1996.73, 2006.25, 2101.52, 2111.05, 2149.16, 2177.74, 2187.27, 2215.85, 2225.37, 2273.01, 2349.23, 2358.75, 2368.28 IRIV 49 901.12, 920.17, 939.23, 958.28, 967.81, 986.86, 996.39, 1044.03, 1063.08, 1072.61, 1091.66, 1110.72, 1158.35, 1234.57, 1263.15, 1301.26, 1358.42, 1377.47, 1406.05, 1415.58, 1444.16, 1453.69, 1463.21, 1482.27, 1491.8, 1520.38, 1539.43, 1548.96, 1558.48, 1587.07, 1768.08, 1777.61, 1825.24, 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1977.67, 1987.2, 2015.78, 2025.31, 2034.83, 2187.27, 2206.32, 2215.85, 2234.9, 2358.75, 2368.28 Mixed (combined model) CARS 47 901.12, 929.70, 939.23, 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1044.03, 1091.66, 1110.72, 1139.3, 1301.26, 1320.31, 1329.84, 1444.16, 1453.69, 1463.21, 1472.74, 1482.27, 1558.48, 1587.07, 1720.44, 1768.08, 1777.61, 1787.13, 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09, 1958.62, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78, 2111.05, 2177.74, 2215.85, 2225.37, 2273.01, 2358.75, 2368.28 IRIV 49 901.12, 910.65, 920.17, 939.23, 958.28, 967.81, 986.86, 996.39, 1044.03, 1072.61, 1082.13, 1091.66, 1101.19, 1110.72, 1120.24, 1129.77, 1139.3, 1148.82, 1234.57, 1301.26, 1377.47, 1396.53, 1415.58, 1444.16, 1453.69, 1463.21, 1491.8, 1558.48, 1577.54, 1587.07, 1710.92, 1720.44, 1758.55, 1768.08, 1863.35, 1910.98, 1949.09, 1987.2, 2025.31, 2053.89, 2072.94, 2101.52, 2111.05, 2139.63, 2177.74, 2273.01, 2330.17, 2358.75, 2368.28 Table 5 Prediction results of DON using CARS-selected wavelengths with OSC + SNV preprocessing techniques Position Model (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP Germ up PLSR 10 0.9530 0.5166 0.9424 0.5718 0.9494 0.5501 SVMR 205 0.9934 0.1949 0.9721 0.3993 0.9847 0.3010 Endosperm up PLSR 10 0.9364 0.6049 0.9262 0.6518 0.9290 0.6317 SVMR 206 0.9755 0.3772 0.9407 0.5830 0.9669 0.4357 Combined PLSR 10 0.9244 0.6555 0.9169 0.6877 0.9200 0.6834 SVMR 203 0.9628 0.4610 0.9417 0.5758 0.9645 0.4543 The IRIV algorithm collected 38, 49 and 49 wavelengths for the germ-side, endosperm-side and combined model, respectively (Table 4 ). The PLSR and SVMR models were developed with the IRIV-selected wavelengths for the germ-side and endosperm-side models with the same OSC + SNV preprocessing techniques to eliminate bias and to assess the performance of CARS and IRIV-selected wavelengths in model training. From Table 6 , it can be observed that the IRIV-selected wavelengths yielded higher coefficient of determination results than CARS. The SVMR results for the germ-side model with IRIV-selected wavelengths had the highest coefficient of determination with R 2 p of 0.9823 and RMSEP of 0.3297 (Fig. 14 ). The results further suggest that IRIV feature wavelength selection methods retain the effective wavelength for DON prediction. In contrast, the CARS algorithm could lose some effective wavelengths, contributing to the average model performance. Similar results were also observed when CARS and IRIV-selected wavelengths were used for model development to predict protein content in single chickpeas. (Saha et al. 2023 ). Table 6 Prediction results of DON using IRIV-selected wavelengths with OSC + SNV preprocessing techniques Position Model (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP Germ up PLSR 9 0.9627 0.4615 0.9548 0.5080 0.9557 0.5236 SVMR 234 0.9943 0.1792 0.9627 0.4604 0.9823 0.3297 Endosperm up PLSR 10 0.9415 0.5818 0.9309 0.6332 0.9309 0.6369 SVMR 201 0.9914 0.2225 0.9179 0.6862 0.9674 0.4361 Combined PLSR 10 0.9318 0.6236 0.9277 0.6418 0.9257 0.6569 SVMR 282 0.9714 0.4062 0.9503 0.5335 0.9629 0.4635 3.6 Discussion A study to detect DON contamination in oats and wheat using NIR hyperspectral imaging in the wavelength range between 900 and 1700 nm identified wavelengths in the 1200 and 1400 nm region as the most significant wavelengths to predict DON contamination (Delwiche et al. 2019 ; Teixido-Orries et al. 2023 ). The CARS and IRIV selected feature wavelengths 1225.04, 1234.57, 1272.67, 1396.53, 1406.05, 1415.58, 1444.16, and 1453.69 nm to predict DON in corn kernels observed in this current study are very similar to well established DON detection wavelengths 1200 and 1400 nm. Another study reported 1430 nm as a significant wavelength to detect DON in wheat, similar to the wavelengths in the 1400 nm range reported in this study (Shen et al. 2022 ). The common phenomenon observed in this study and previously reported studies is that the mean spectra did not provide any clear differences at the selected significant wavelengths, and so in this study, further data processing and chemometrics tools are needed to predict the DON in grains (He et al. 2021 ; Teixido-Orries et al. 2023 ). The NIR study focused on DON detection commonly used 900–1700 nm range camera (Femenias et al. 2020 ; Femenias et al. 2021b ; Femenias et al. 2022b ), and major comparisons of DON-specific wavelengths can be made in this NIR region. Very little exploration was attempted in the SWIR region (Vicens-Sans et al. 2024 ). A study using FT-NIR spectroscopy found 1880–2070 nm spectral region as a DON-specific wavelength in wheat, which is comparable to 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09, 1958.62, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78 nm wavelengths reported in this study (Peiris et al. 2009 ). A unique sample preparation technique was followed in this study by utilizing commercial DON for sample preparation instead of artificially inoculating the grains with fungal species to produce mycotoxins (Femenias et al. 2022a ), which will lead to quantification of DON and not the fungal infection. Many research studies focused on DON detection based on classification; only a few studies have focused on the quantification of DON (Femenias et al. 2020 ), this indicates the DON quantification studies using NIR hyperspectral imaging is in its development stage and further studies are required to utilize the potential of NIR hyperspectral imaging system completely (Nadimi et al. 2021 ). A recent study on DON quantification in oats unground samples achieved the highest R 2 value of 0.75 compared to the highest R 2 value of 0.9823 obtained in this study (Teixido-Orries et al. 2023 ); the lower R 2 value can be attributed to using12 wavelengths to build models compared to 38 to 51 wavelengths selected using CARS and IRIV used to build prediction models in this study. Another study on DON quantification in wheat kernels provided the highest R 2 value of 0.88 on SNV preprocessed data, similar to the current study providing the highest R 2 value with SNV preprocessed data (Femenias et al. 2021a ). The proposed NIR-based DON prediction tool can detect DON in a few minutes without disturbing the samples, without using any chemical reagents, without a need for a professional to operate the equipment and in a rapid manner compared to traditional analytical techniques like UPHLC and ELISA-based methods. While NIR-HSI offers strong potential for industrial applications due to its rapid and non-destructive capabilities, several challenges exist for scaling up to industrial deployment. These include the high initial cost of hyperspectral systems, robust calibration models that can accommodate sample diversity and environmental variation (e.g., lighting, temperature, motion blur), and the requirement for integration with automated conveyors and real-time processing hardware. Maintaining spectral accuracy under high-throughput conditions also requires careful optical and mechanical alignment. These challenges are actively being addressed in recent studies, and with technological advancements in sensor miniaturization and embedded computing, industrial deployment is increasingly feasible. For regulatory acceptance, additional validation studies would be required following standard guidelines such as those provided by Codex Alimentarius or international bodies like AOAC and ISO. These would include evaluating method accuracy, precision, specificity, linearity, limit of detection (LOD), limit of quantification (LOQ), reproducibility across different instruments and operators, and robustness to environmental variables such as temperature and humidity. Moreover, inter-laboratory studies and performance comparisons with established reference methods (e.g., LC-MS/MS) would be critical for demonstrating equivalency. While our current study establishes feasibility and performance under controlled conditions, future work will focus on systematic validation to support regulatory alignment. This study focused on single-kernel imaging; future studies should focus on bulk imaging and grounded samples to detect DON contamination at the grain storage and processor levels. Different types of mycotoxins can co-occur, and future studies also focus on detecting multiple mycotoxins in a single scan of an NIR hyperspectral imaging system. 4. Conclusion SWIR-HSI proves to be a promising technique for detecting DON in individual corn kernels and, when combined with chemometric tools and feature selection techniques, can significantly reduce the number of wavelengths without compromising the model performance. Also, the effect of the different orientations or positions of corn kernels on the prediction of DON was analyzed. It was identified that the germ-side of the corn kernels is the optimal position of corn kernels for hyperspectral imaging for better model performance and DON prediction. PLSR and SVMR with SNV, OSC + SNV and MSC preprocessing methods yielded a better coefficient of determination for DON prediction when using the entire spectrum. CARS and IRIV enhanced model training and quantification speed with a better coefficient of determination. SVMR on IRIV-selected wavelengths provided the highest R 2 p of 0.9823 and RMSE prediction of 0.3297. Future studies should focus on the quantification of DON in field samples with other co-produced secondary metabolites to enhance the sensitivity and specificity of the HSI system for real-time inspection in processing lines. Declarations Acknowledgement The authors thank the Ontario Ministry of Agriculture, Food and Rural Affairs (OMAFRA) for providing the healthy and FHB-infected corn grains for this study. The authors also thank the Barrett Family Foundation, Canada, for funding this study. We want to thank the NSERC Applied Research Tools and Instruments (ARTI) grant for the NIR hyperspectral imaging system at Lethbridge College and Headwall Photonics for its in-kind contribution to the NIR hyperspectral imaging system at the Lethbridge College. Funding This work was supported by Barrett Family Foundation, Canada. Author contributions Rathna Priya Thangaraj Sundaramurthy – Conceptualization; methodology; data collection; data analysis; manuscript writing. Thiruppathi Senthilkumar – Supervision; data analysis; writing- review and editing; reviewing manuscript. Chandra B. Singh – Resources; writing – review and editing; reviewing manuscript. Annamalai Manickavasagan – Supervision; resources; writing – review and editing; reviewing manuscript. Conflict of interest The authors have no conflicts of interest to declare that are relevant to the content of this article. Ethical Approval Not applicable Consent to participate Not applicable Consent to publish Not applicable Competing interest There is no competing Interest Data availability statement The dataset generated during this study and codes are available from the corresponding author on reasonable request. References Abdi H (2003) Partial Least Square Regression PLS-Regression. Encyclopedia for research methods for the social sciences 792–795 Alisaac E, Behmann J, Rathgeb A, Karlovsky P, Dehne HW, Mahlein AK (2019) Assessment of fusarium infection and mycotoxin contamination of wheat kernels and flour using hyperspectral imaging. Toxins (Basel) 11. https://doi.org/10.3390/toxins11100556 Berthiller F, Crews C, Dall’Asta C, Saeger S De, Haesaert G, Karlovsky P, Oswald IP, Seefelder W, Speijers G, Stroka J (2013) Masked mycotoxins: A review. Mol Nutr Food Res 57:165–186 Brumley WC, Trucksess MW, Adler SH, Cohen CK, White KD, Sphon JA (1985) Food Chem Castillo MÁ, Montes R, Navarro A, Segarra R, Cuesta G, Hernández E (2008) Occurrence of deoxynivalenol and nivalenol in Spanish corn-based food products. Journal of Food Composition and Analysis 21:423–427. https://doi.org/10.1016/j.jfca.2008.03.009 Cruz-Tirado JP, Amigo JM, Barbin DF (2022) Determination of protein content in single black fly soldier (Hermetia illucens L.) larvae by near infrared hyperspectral imaging (NIR-HSI) and chemometrics. Food Control 143. https://doi.org/10.1016/j.foodcont.2022.109266 Deiss L, Margenot AJ, Culman SW, Demyan MS (2020) Tuning support vector machines regression models improves prediction accuracy of soil properties in MIR spectroscopy. Geoderma 365. https://doi.org/10.1016/j.geoderma.2020.114227 Delwiche SR, Rodriguez IT, Rausch SR, Graybosch RA (2019) Estimating percentages of fusarium-damaged kernels in hard wheat by near-infrared hyperspectral imaging. J Cereal Sci 87:18–24. https://doi.org/10.1016/j.jcs.2019.02.008 EFSA (2013) Deoxynivalenol in food and feed: occurrence and exposure. EFSA Journal 11. https://doi.org/10.2903/j.efsa.2013.3379 FAOSTAT (2023) Maize (Corn) production indices . https://www.fao.org/faostat/en/#data/QCL. Accessed 12 Feb 2025 Femenias A, Bainotti MB, Gatius F, Ramos AJ, Marín S (2021a) Standardization of near infrared hyperspectral imaging for wheat single kernel sorting according to deoxynivalenol level. Food Research International 139. https://doi.org/10.1016/j.foodres.2020.109925 Femenias A, Gatius F, Ramos AJ, Sanchis V, Marín S (2020) Standardisation of near infrared hyperspectral imaging for quantification and classification of DON contaminated wheat samples. Food Control 111. https://doi.org/10.1016/j.foodcont.2019.107074 Femenias A, Gatius F, Ramos AJ, Sanchis V, Marín S (2021b) Near-infrared hyperspectral imaging for deoxynivalenol and ergosterol estimation in wheat samples. Food Chem 341. https://doi.org/10.1016/j.foodchem.2020.128206 Femenias A, Gatius F, Ramos AJ, Teixido-Orries I, Marín S (2022a) Hyperspectral imaging for the classification of individual cereal kernels according to fungal and mycotoxins contamination: A review. Food Research International 155 Femenias A, Llorens-Serentill E, Ramos AJ, Sanchis V, Marín S (2022b) Near-infrared hyperspectral imaging evaluation of Fusarium damage and DON in single wheat kernels. Food Control 142. https://doi.org/10.1016/j.foodcont.2022.109239 Feng YZ, Sun DW (2012) Application of Hyperspectral Imaging in Food Safety Inspection and Control: A Review. Crit Rev Food Sci Nutr 52:1039–1058 Food and Agriculture Organization of the United Nations (FAO) (2015) 38th Session of the Codex Alimentarius Commission. Geneva, Switzerland. https://www.fao.org/newsroom/detail/Codex-Alimentarius-Commission-6-11-July-2015/ar. Accessed 12 Feb 2025 He X, Zhao T, Shen F, Liu Q, Fang Y, Hu Q (2021) Online detection of naturally DON contaminated wheat grains from China using Vis-NIR spectroscopy and computer vision. Biosyst Eng 201:1–10. https://doi.org/10.1016/j.biosystemseng.2020.11.001 Jiang L, Zhu B, Tao Y (2010) Hyperspectral Image Classification Methods. In: Hyperspectral Imaging for Food Quality Analysis and Control. Elsevier, pp 79–98 Kautzman ME, Wickstrom ML, Scott TA (2015) The use of near infrared transmittance kernel sorting technology to salvage high quality grain from grain downgraded due to Fusarium damage. Animal Nutrition 1:41–46. https://doi.org/10.1016/j.aninu.2015.02.007 Li J, Wang Q, Xu L, Tian X, Xia Y, Fan S (2019) Comparison and Optimization of Models for Determination of Sugar Content in Pear by Portable Vis-NIR Spectroscopy Coupled with Wavelength Selection Algorithm. Food Anal Methods 12:12–22. https://doi.org/10.1007/s12161-018-1326-7 Marzec-Schmidt K, Börjesson T, Suproniene S, Jędryczka M, Janavičienė S, Góral T, Karlsson I, Kochiieru Y, Ochodzki P, Mankevičienė A, Piikki K (2021) Modelling the effects of weather conditions on cereal grain contamination with deoxynivalenol in the baltic sea region. Toxins (Basel) 13. https://doi.org/10.3390/toxins13110737 McMullin D, Mizaikoff B, Krska R (2015) Advancements in IR spectroscopic approaches for the determination of fungal derived contaminations in food crops. Anal Bioanal Chem 407:653–660. https://doi.org/10.1007/s00216-014-8145-5 Mehmood T, Sæbø S, Liland KH (2020) Comparison of variable selection methods in partial least squares regression. J Chemom 34. https://doi.org/10.1002/cem.3226 Munkvold GP, Arias S, Taschl I, Gruber-Dorninger C (2018) Mycotoxins in corn: Occurrence, impacts, and management. In: Corn: Chemistry and Technology, 3rd Edition. Elsevier, pp 235–287 Nadimi M, Brown JM, Morrison J, Paliwal J (2021) Examination of wheat kernels for the presence of Fusarium damage and mycotoxins using near-infrared hyperspectral imaging. Measurement: Food 4. https://doi.org/10.1016/j.meafoo.2021.100011 Parrag V, Gillay Z, Kovács Z, Zitek A, Böhm K, Hinterstoisser B, Krska R, Sulyok M, Felföldi J, Firtha F, Baranyai L (2020) Application of hyperspectral imaging to detect toxigenic Fusarium infection on cornmeal. Progress in Agricultural Engineering Sciences 16:51–60. https://doi.org/10.1556/446.2020.00009 Peiris KHS, Pumphrey MO, Dong Y, Maghirang EB, Berzonsky W, Dowell FE (2010) Near-infrared spectroscopic method for identification of Fusarium head blight damage and prediction of deoxynivalenol in single wheat kernels. Cereal Chem 87:511–517. https://doi.org/10.1094/CCHEM-01-10-0006 Peiris KHS, Pumphrey MO, Dowell FE (2009) NIR absorbance characteristics of deoxynivalenol and of sound and fusarium-damaged wheat kernels. J Near Infrared Spectrosc 17:213–221. https://doi.org/10.1255/jnirs.846 Prieto-Simón B, Noguer T, Campàs M (2007) Emerging biotools for assessment of mycotoxins in the past decade. TrAC - Trends in Analytical Chemistry 26:689–702. https://doi.org/10.1016/j.trac.2007.05.012 Priya TSR, Manickavasagan A (2023) Evaluation of treatment methods for spiking deoxynivalenol (DON) in single corn kernels. Canadian Journal of Plant Science 103:450–462. https://doi.org/10.1139/cjps-2022-0259 Rathna Priya TS, Manickavasagan A (2021) Characterising corn grain using infrared imaging and spectroscopic techniques: a review. Journal of Food Measurement and Characterization 15:3234–3249 Ravikanth L, Jayas DS, White NDG, Fields PG, Sun DW (2017) Extraction of Spectral Information from Hyperspectral Data and Application of Hyperspectral Imaging for Food and Agricultural Products. Food Bioproc Tech 10 Regulatory Guidance (RG-8). Government of Canada. (2017) Mycotoxins in Livestock Feed,Canadian Food Inspection Agency. https://inspection.canada.ca/en/animal-health/livestock-feeds/regulatory-guidance/rg-8#c1. Accessed 12 Feb 2025 Saha D, Senthilkumar T, Sharma S, Singh CB, Manickavasagan A (2023) Application of near-infrared hyperspectral imaging coupled with chemometrics for rapid and non-destructive prediction of protein content in single chickpea seed. Journal of Food Composition and Analysis 115:104938. https://doi.org/10.1016/j.jfca.2022.104938 Schaafsma AW, Frégeau-Reid J, Phibbs T Distribution of deoxynivalenol in Gibberella-infected food-grade corn kernels Schollenberger M, Suchy S, Jara HT, Drochner W, Müller H-M (1999) A survey of Fusarium toxins in cereal-based foods marketed in an area of southwest Germany Senthilkumar T, Jayas DS, White NDG, Fields PG, Gräfenhan T (2016) Near-Infrared (NIR) hyperspectral imaging: theory and applications to detect fungal infection and mycotoxin contamination in food products. Indian Journal of Entomology 78:91. https://doi.org/10.5958/0974-8172.2016.00029.8 Sharma S, Pradhan R, Manickavasagan A, Thimmanagari M, Dutta A (2020) Application of analytical pyrolysis to gain insights into proteins of condensed corn distillers solubles from selective milling technology. Food and Bioproducts Processing 124:354–368. https://doi.org/10.1016/j.fbp.2020.09.011 Sharma S, Pradhan R, Manickavasagan A, Thimmanagari M, Dutta A (2021) Evaluation of nitrogenous pyrolysates by Py–GC/MS for impacts of different proteolytic enzymes on corn distillers solubles. Food and Bioproducts Processing 127:225–243. https://doi.org/10.1016/j.fbp.2021.03.004 Shen G, Cao Y, Yin X, Dong F, Xu J, Shi J, Lee YW (2022) Rapid and nondestructive quantification of deoxynivalenol in individual wheat kernels using near-infrared hyperspectral imaging and chemometrics. Food Control 131. https://doi.org/10.1016/j.foodcont.2021.108420 Shi D, Hang J, Neufeld J, Zhao S, House JD (2022) Estimation of crude protein and amino acid contents in whole, ground and defatted ground soybeans by different types of near-infrared (NIR) reflectance spectroscopy. Journal of Food Composition and Analysis 111. https://doi.org/10.1016/j.jfca.2022.104601 Shreve B, TN, & WM (2006) National forage testing association reference method: dry matter by oven drying for 3 hours at 105 C. NFTA Reference Methods National Forage Testing Association, Omaha, NB (2006) Sun D-W (2010) Hyperspectral imaging for food quality analysis and control. Academic Press, an imprint of Elsevier Teixido-Orries I, Molino F, Femenias A, Ramos AJ, Marín S (2023) Quantification and classification of deoxynivalenol-contaminated oat samples by near-infrared hyperspectral imaging. Food Chem 417. https://doi.org/10.1016/j.foodchem.2023.135924 Tekle S, Mage I, Segtnan VH, Bjornstad A (2015) Near-infrared hyperspectral imaging of Fusarium-damaged oats (Avena sativa L.). Cereal Chem 92:73–80. https://doi.org/10.1094/CCHEM-04-14-0074-R Vapnik VN (2000) The Nature of Statistical Learning Theory. Springer New York, New York, NY Vicens-Sans A, Pascari X, Molino F, Ramos AJ, Marín S (2024) Near infrared hyperspectral imaging as a sorting tool for deoxynivalenol reduction in wheat batches. Food Research International 178. https://doi.org/10.1016/j.foodres.2024.113984 Wang S, Sun J, Fu L, Xu M, Tang N, Cao Y, Yao K, Jing J (2022) Identification of red jujube varieties based on hyperspectral imaging technology combined with CARS-IRIV and SSA-SVM. J Food Process Eng 45. https://doi.org/10.1111/jfpe.14137 Wu Q, Kuča K, Humpf HU, Klímová B, Cramer B (2017) Fate of deoxynivalenol and deoxynivalenol-3-glucoside during cereal-based thermal food processing: a review study. Mycotoxin Res 33:79–91 Xing F, Yao H, Liu Y, Dai X, Brown RL, Bhatnagar D (2019) Recent developments and applications of hyperspectral imaging for rapid detection of mycotoxins and mycotoxigenic fungi in food products. Crit Rev Food Sci Nutr 59:173–180 Xu H, Ren J, Lin J, Mao S, Xu Z, Chen Z, Zhao J, Wu Y, Xu N, Wang P (2023) The impact of high-quality data on the assessment results of visible/near-infrared hyperspectral imaging and development direction in the food fields: a review. Journal of Food Measurement and Characterization 17:2988–3004 Zhang J, Ma Y, Liu G, Fan N, Li Y, Sun Y (2022) Rapid evaluation of texture parameters of Tan mutton using hyperspectral imaging with optimization algorithms. Food Control 135. https://doi.org/10.1016/j.foodcont.2022.108815 Zhao T, Chen M, Jiang X, Shen F, He X, Fang Y, Liu Q, Hu Q (2020) Integration of spectra and image features of Vis/NIR hyperspectral imaging for prediction of deoxynivalenol contamination in whole wheat flour. Infrared Phys Technol 109. https://doi.org/10.1016/j.infrared.2020.103426 Zhong H, Wang J, Jia H, Mu Y, Lv S (2019) Vector field-based support vector regression for building energy consumption prediction. Appl Energy 242:403–414. https://doi.org/10.1016/j.apenergy.2019.03.078 Tables Table 1. Prediction results of combined model (both germ-side and endosperm-side) to detect DON in individual corn grains using full spectrum Model Pre-processing (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP PLSR None 8 0.8239 1.0037 0.8162 1.0255 0.8382 0.9682 Weighted LS 10 0.9015 0.7504 0.8934 0.7811 0.8889 0.8029 Detrend 9 0.9099 0.7182 0.9037 0.7426 0.9112 0.7207 EPO 10 0.9276 3.018 0.9189 3.0251 0.9231 3.0063 Gap 1st derivative 10 0.8988 0.7611 0.8912 0.7894 0.9001 0.7622 GLS weighting 11 0.9313 3.0148 0.9234 3.0254 0.9251 3.0045 Mean centering 10 0.9112 1.4143 0.8957 1.7632 0.8854 1.6529 MSC (mean) 11 0.9288 0.6381 0.9182 0.6844 0.9214 0.6766 OSC 11 0.9281 0.6416 0.9184 0.6838 0.9211 0.6822 PQN 11 0.911 0.7133 0.9008 0.7534 0.9146 0.7124 Sav-Gol Smoothing 11 0.8466 0.9371 0.8264 0.9974 0.8557 0.9186 SNV 11 0.929 0.6375 0.9183 0.6837 0.921 0.6784 Whittaker Filter 10 0.8998 0.7571 0.893 0.7828 0.9039 0.7498 Detrend + SNV 11 0.922 0.6682 0.9139 0.7019 0.9158 0.6991 MSC + SNV 11 0.929 0.6375 0.9184 0.6836 0.921 0.6784 OSC + SNV 11 0.9294 0.6354 0.9196 0.6784 0.9211 0.6787 SVMR None 419 0.9812 0.3271 0.9309 0.6269 0.9649 0.4563 Weighted LS 443 0.9832 0.3106 0.9551 0.5058 0.9721 0.4089 Detrend 375 0.9823 0.3181 0.961 0.4707 0.9746 0.3889 EPO 483 0.9829 0.3115 0.9695 0.4186 0.9798 0.3434 Gap 1st derivative 554 0.8053 1.0721 0.7908 1.1082 0.822 1.0687 GLS weighting 542 0.9702 0.4139 0.9605 0.4748 0.9669 0.4465 Mean centering 419 0.9812 0.3271 0.9309 0.6269 0.9649 0.4564 MSC (mean) 366 0.9805 0.3346 0.9617 0.4669 0.9718 0.4101 OSC 406 0.9777 0.3565 0.9371 0.5978 0.9719 0.4076 PQN 429 0.3891 1.8764 0.3745 1.8951 0.4054 1.8865 Sav-Gol Smoothing 456 0.9672 0.4328 0.9113 0.7098 0.9459 0.5657 SNV 500 0.9947 0.1738 0.9674 0.4298 0.9851 0.2959 Whittaker filter 370 0.9817 0.3237 0.9651 0.4464 0.9751 0.3837 Detrend + SNV 511 0.9871 0.2725 0.968 0.4263 0.9791 0.3525 MSC +SNV 500 0.9947 0.1738 0.9674 0.4298 0.9851 0.2959 OSC + SNV 497 0.9913 0.2242 0.9585 0.4855 0.9818 0.3289 LS – Least squares; PLSR – Partial least square regression; SVMR – Support vector machine regression; EPO -external parameter orthogonalization; GLS – generalized least squares; MSC- multiplicative scatter correction; OSC - orthogonal signal correction; PQN -probabilistic quotient normalisation; Sav-Gol - Savitsky – Golay smoothing; SNV – standard normal variate; R 2 c, R 2 cv, R 2 p – coefficient of determination of calibration, cross-validation, and prediction; RMSEC, RMSECV, RMSEP – root mean square error of calibration, cross-validation and prediction. Table 2. Prediction results of the germ-side model to detect DON in individual corn grains using full spectrum Model Pre-processing (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP PLSR None 9 0.9151 0.7024 0.8994 0.7646 0.9359 0.6402 Weighted LS 10 0.9181 0.6782 0.9068 0.7236 0.9359 0.6469 Detrend 9 0.9243 0.6518 0.9137 0.6961 0.9482 0.5671 EPO 9 0.9323 3.0903 0.9213 3.0918 0.9478 2.9663 Gap 1st derivative 10 0.9168 0.6835 0.9052 0.7294 0.9453 0.5911 GLS weighting 8 0.9298 3.0925 0.9183 3.0946 0.9487 2.9587 Mean centering 7 0.8710 3.1455 0.8557 3.1577 0.8959 2.9937 MSC (mean) 11 0.9385 0.5872 0.9252 0.6484 0.9521 0.5467 OSC 11 0.9413 0.5740 0.9221 0.6620 0.9570 0.5139 PQN 9 0.9002 0.7484 0.8835 0.8087 0.9376 0.6332 Sav-Gol Smoothing 10 0.8598 0.8873 0.8463 0.9292 0.9079 0.7844 SNV 10 0.9337 0.6102 0.9228 0.6585 0.9481 0.5678 Whittaker Filter 10 0.9255 0.6468 0.9146 0.6926 0.9215 0.7010 Detrend + SNV 9 0.9248 0.6498 0.9136 0.6965 0.9396 0.6111 MSC + SNV 10 0.9337 0.6102 0.9228 0.6585 0.9481 0.5678 OSC + SNV 11 0.9444 0.5586 0.9265 0.6426 0.9531 0.5369 SVMR None 219 0.9520 0.5276 0.9222 0.6649 0.9317 0.6484 Weighted LS 160 0.9844 0.2984 0.9619 0.4654 0.9740 0.3983 Detrend 168 0.9836 0.3061 0.9637 0.4539 0.9758 0.3872 EPO 168 0.9927 0.2041 0.9698 0.4131 0.9823 0.3263 Gap 1st derivative 120 0.7832 1.1338 0.7694 1.1684 0.7837 1.1749 GLS weighting 192 0.9762 0.3705 0.9646 0.4484 0.9687 0.4404 Mean centering 219 0.9519 0.5276 0.9222 0.6649 0.9317 0.6484 MSC (mean) 173 0.9847 0.2944 0.9695 0.4151 0.9772 0.3726 OSC 187 0.9786 0.3491 0.9465 0.5503 0.9729 0.4069 PQN 214 0.3460 1.9387 0.3266 1.9637 0.4122 1.9308 Sav-Gol Smoothing 225 0.9295 0.6408 0.8941 0.7769 0.9099 0.7514 SNV 239 0.9955 0.1595 0.9742 0.3817 0.9854 0.2953 Whittaker filter 172 0.9817 0.3244 0.9658 0.4412 0.9787 0.3598 Detrend + SNV 244 0.9903 0.2347 0.9733 0.3891 0.9803 0.3443 MSC +SNV 239 0.9955 0.1595 0.9742 0.3817 0.9855 0.2953 OSC + SNV 169 0.9925 0.2057 0.9627 0.4593 0.9818 0.3300 Table 3. Prediction results of the endosperm-side model to detect DON in individual corn grains using full spectrum Model Pre-processing (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP PLSR None 6 0.7451 1.2072 0.7312 1.2397 0.8239 1.0112 Weighted LS 8 0.8771 0.8382 0.8440 0.9446 0.9075 0.7279 Detrend 9 0.9060 0.7331 0.8874 0.8028 0.9139 0.7060 EPO 9 0.9192 2.9621 0.8998 2.9768 0.9253 2.8997 Gap 1st derivative 11 0.9058 0.7355 0.8894 0.7971 0.9119 0.7164 GLS weighting 9 0.9244 2.9468 0.9074 2.9613 0.9194 2.9385 Mean centering 9 0.9053 2.9754 0.8840 3.0075 0.9109 2.9257 MSC (mean) 10 0.9238 0.6616 0.9106 0.7166 0.9152 0.6994 OSC 10 0.9246 0.6583 0.9053 0.7379 0.9188 0.6869 PQN 11 0.9189 0.6822 0.8980 0.7656 0.9184 0.7027 Sav-Gol Smoothing 10 0.8083 1.0493 0.7941 1.0885 0.8227 1.0025 SNV 11 0.9308 0.6305 0.9146 0.7006 0.9208 0.6825 Whittaker Filter 8 0.8604 0.8935 0.8440 0.9445 0.9031 0.7496 Detrend + SNV 11 0.9298 0.6348 0.9047 0.7416 0.9186 0.6858 MSC + SNV 11 0.9307 0.6305 0.9146 0.7006 0.9208 0.6825 OSC + SNV 11 0.9374 0.5994 0.9179 0.6874 0.9231 0.6718 SVMR None 226 0.9824 0.3209 0.8995 0.7648 0.9652 0.4490 Weighted LS 236 0.9792 0.3477 0.9338 0.6179 0.9650 0.4476 Detrend 268 0.9791 0.3515 0.9455 0.5621 0.9728 0.4022 EPO 257 0.9915 0.2218 0.9595 0.4834 0.9859 0.2853 GAP 1st derivative 260 0.7480 1.2216 0.7263 1.2687 0.8092 1.0971 GLS weighting 212 0.9719 0.4071 0.9568 0.5014 0.9705 0.4098 Mean centering 226 0.9824 0.3209 0.8995 0.7648 0.9652 0.4490 MSC (mean) 199 0.9783 0.3558 0.9482 0.5476 0.9752 0.3786 OSC 215 0.9742 0.3874 0.9074 0.7311 0.9669 0.4394 PQN 226 0.3214 1.9821 0.3116 1.9967 0.3072 1.9841 Sav-Gol Smoothing 240 0.9695 0.4225 0.8721 0.8607 0.9505 0.5321 SNV 270 0.9999 0.0099 0.9540 0.5155 0.9831 0.3108 Whittaker filter 255 0.9775 0.3620 0.9496 0.5411 0.9766 0.3658 Detrend + SNV 194 0.9980 0.1072 0.9557 0.5048 0.9859 0.2821 MSC +SNV 270 0.9999 0.0099 0.9540 0.5155 0.9831 0.3108 OSC + SNV 205 0.9637 0.4593 0.9238 0.6636 0.9629 0.4605 Table 4. Feature wavelengths selected from the full spectrum (900 – 2500nm) of corn grains using CARS and IRIV Corn grain position Wavelength selection method Number of wavelengths Wavelength (nm) Germ-side up CARS 43 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1072.61, 1091.66, 1110.72, 1120.24, 1139.3, 1225.04, 1320.31, 1396.53, 1453.69, 1482.27, 1587.07, 1634.7, 1644.23, 1720.44, 1758.55, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09,1958.62, 1968.15, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78, 2025.31, 2082.47, 2101.52, 2111.05, 2187.27, 2215.85, 2225.37, 2263.48, 2273.01 IRIV 38 901.12, 920.17, 967.81, 986.86, 1015.45, 1072.61, 1091.66, 1110.72, 1120.24, 1129.77, 1139.3, 1225.04, 1272.67, 1301.26, 1339.36, 1377.47, 1396.53, 1453.69, 1463.21, 1482.27, 1558.48, 1587.07, 1720.44, 1768.08, 1863.35, 1882.4, 1910.98, 1949.09, 1977.67, 2025.31, 2034.83, 2044.36, 2101.52, 2177.74, 2187.27, 2215.85, 2273.01, 2330.17 Endosperm-side up CARS 51 901.12, 939.23, 948.76, 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1072.61, 1091.66, 1110.72, 1301.26, 1320.31, 1358.42, 1377.47, 1406.05, 1415.58, 1444.16, 1453.69, 1463.21, 1472.74, 1482.27, 1548.96, 1558.48, 1587.07, 1768.08, 1777.61, 1853.82, 1863.35, 1872.88, 1901.46, 1910.98, 1920.51, 1949.09, 1977.67, 1987.2, 1996.73, 2006.25, 2101.52, 2111.05, 2149.16, 2177.74, 2187.27, 2215.85, 2225.37, 2273.01, 2349.23, 2358.75, 2368.28 IRIV 49 901.12, 920.17, 939.23, 958.28, 967.81, 986.86, 996.39, 1044.03, 1063.08, 1072.61, 1091.66, 1110.72, 1158.35, 1234.57, 1263.15, 1301.26, 1358.42, 1377.47, 1406.05, 1415.58, 1444.16, 1453.69, 1463.21, 1482.27, 1491.8, 1520.38, 1539.43, 1548.96, 1558.48, 1587.07, 1768.08, 1777.61, 1825.24, 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1977.67, 1987.2, 2015.78, 2025.31, 2034.83, 2187.27, 2206.32, 2215.85, 2234.9, 2358.75, 2368.28 Mixed (combined model) CARS 47 901.12, 929.70, 939.23, 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1044.03, 1091.66, 1110.72, 1139.3, 1301.26, 1320.31, 1329.84, 1444.16, 1453.69, 1463.21, 1472.74, 1482.27, 1558.48, 1587.07, 1720.44, 1768.08, 1777.61, 1787.13, 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09, 1958.62, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78, 2111.05, 2177.74, 2215.85, 2225.37, 2273.01, 2358.75, 2368.28 IRIV 49 901.12, 910.65, 920.17, 939.23, 958.28, 967.81, 986.86, 996.39, 1044.03, 1072.61, 1082.13, 1091.66, 1101.19, 1110.72, 1120.24, 1129.77, 1139.3, 1148.82, 1234.57, 1301.26, 1377.47, 1396.53, 1415.58, 1444.16, 1453.69, 1463.21, 1491.8, 1558.48, 1577.54, 1587.07, 1710.92, 1720.44, 1758.55, 1768.08, 1863.35, 1910.98, 1949.09, 1987.2, 2025.31, 2053.89, 2072.94, 2101.52, 2111.05, 2139.63, 2177.74, 2273.01, 2330.17, 2358.75, 2368.28 Table 5. Prediction results of DON using CARS-selected wavelengths with OSC + SNV preprocessing techniques Position Model (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP Germ up PLSR 10 0.9530 0.5166 0.9424 0.5718 0.9494 0.5501 SVMR 205 0.9934 0.1949 0.9721 0.3993 0.9847 0.3010 Endosperm up PLSR 10 0.9364 0.6049 0.9262 0.6518 0.9290 0.6317 SVMR 206 0.9755 0.3772 0.9407 0.5830 0.9669 0.4357 Combined PLSR 10 0.9244 0.6555 0.9169 0.6877 0.9200 0.6834 SVMR 203 0.9628 0.4610 0.9417 0.5758 0.9645 0.4543 Table 6. Prediction results of DON using IRIV-selected wavelengths with OSC + SNV preprocessing techniques Position Model (LVs/SVs) R 2 c RMSEC R 2 cv RMSECV R 2 p RMSEP Germ up PLSR 9 0.9627 0.4615 0.9548 0.5080 0.9557 0.5236 SVMR 234 0.9943 0.1792 0.9627 0.4604 0.9823 0.3297 Endosperm up PLSR 10 0.9415 0.5818 0.9309 0.6332 0.9309 0.6369 SVMR 201 0.9914 0.2225 0.9179 0.6862 0.9674 0.4361 Combined PLSR 10 0.9318 0.6236 0.9277 0.6418 0.9257 0.6569 SVMR 282 0.9714 0.4062 0.9503 0.5335 0.9629 0.4635 Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Major Revision 03 Feb, 2026 Reviewers agreed at journal 14 Aug, 2025 Reviewers invited by journal 29 Apr, 2025 Editor assigned by journal 24 Apr, 2025 First submitted to journal 22 Apr, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6465545","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":449640676,"identity":"a20128a3-c013-418f-a597-704031d06982","order_by":0,"name":"Rathna Priya Thangaraj Sundaramurthy","email":"","orcid":"","institution":"University of Guelph College of Engineering and Physical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Rathna","middleName":"Priya Thangaraj","lastName":"Sundaramurthy","suffix":""},{"id":449640677,"identity":"92fcb080-7c17-4a90-8cc9-f47666de29dc","order_by":1,"name":"Thiruppathi Senthilkumar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2klEQVRIie2QsQqCQBiALw5uOmx10ldQhKihd9G9XAShKUP4W2pv8xV6BI8DJ3NucInA2TbH7kgdHK7GhvuW+4b/g/9+hDSav4SifJRWPORrQYZECLv8moyCqXK0x87OjO+gDudS1lBbBsKPVpU4heGzGzSRKYRvofEIIp6pTAh12AF4kBTUEQkPQNxBmdjQJ5lMVsD3IsGd8jNFn1xlMgPuE0SJerFi47CkaiJXyqlqXMBksVQulpbeK4nr0OKl13ZxbdvH9HlXLvYh9wdBCP8wP0k0Go1GM+ENNzZPjIyTFwgAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0000-8044-1655","institution":"University of Prince Edward Island Faculty of Sustainable Design Engineering","correspondingAuthor":true,"prefix":"","firstName":"Thiruppathi","middleName":"","lastName":"Senthilkumar","suffix":""},{"id":449640678,"identity":"51399e56-e8b4-48b2-a6fa-c59ce85ee1a0","order_by":2,"name":"Chandra B. Singh","email":"","orcid":"","institution":"Lethbridge Community College: Lethbridge College","correspondingAuthor":false,"prefix":"","firstName":"Chandra","middleName":"B.","lastName":"Singh","suffix":""},{"id":449640679,"identity":"7768635c-7b90-4bbb-9282-585f49ff290d","order_by":3,"name":"Annamalai Manickavasagan","email":"","orcid":"","institution":"University of Guelph College of Engineering and Physical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Annamalai","middleName":"","lastName":"Manickavasagan","suffix":""}],"badges":[],"createdAt":"2025-04-16 17:11:00","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6465545/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6465545/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82155117,"identity":"db773602-a3b5-4f72-ad06-bba06f0764a4","added_by":"auto","created_at":"2025-05-07 07:38:20","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":341996,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlowchart of the experimental design to predict DON in individual corn grains\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/ce253f3e9ab4dfe64859bdd5.png"},{"id":82151917,"identity":"a63efd00-7046-426d-a0c8-6662cb280882","added_by":"auto","created_at":"2025-05-07 07:22:20","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":178254,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eCorn grains with a small crack in pericarp layer\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/63830875ad81aa9b93317889.png"},{"id":82154312,"identity":"59e9a6df-6a54-4d60-8292-d69248004431","added_by":"auto","created_at":"2025-05-07 07:30:20","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":775054,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eHyperspectral imaging system for acquiring corn grain images\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/c3f2602c79b7c1baa0c0290f.png"},{"id":82151919,"identity":"a88bb3dd-711e-4b46-b95c-74f8bc71b470","added_by":"auto","created_at":"2025-05-07 07:22:20","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":143270,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eA spectral image showing the arrangement of corn grains with germ-side up\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/9bba6cc503273dc711fe3cec.png"},{"id":82151913,"identity":"efa548fd-34e1-45bf-a26e-0b13c327fe3b","added_by":"auto","created_at":"2025-05-07 07:22:20","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":42213,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlowchart of the steps involved in competitive ELISA for DON detection\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/b7fa05d6c4e6f425821ddfee.png"},{"id":82154316,"identity":"e3aef3e0-9428-4bb7-8ac5-16b2e0d03f7c","added_by":"auto","created_at":"2025-05-07 07:30:20","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":483357,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eRaw spectra of the corn grain models and average reflectance spectra at germ-side and endosperm-side of corn grain\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/6a12b684b4bf4316977fd306.png"},{"id":82154315,"identity":"c6c6a806-f760-4b01-b85d-57564caacd6b","added_by":"auto","created_at":"2025-05-07 07:30:20","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":282913,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePrincipal Component Analysis (PCA) of the spectra showing the percentage of variances captured by first two principal components (PCs)\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/73bf55d4b21e4a696a59bd8a.png"},{"id":82155121,"identity":"7cccfaa5-5aa0-47df-a26a-964ce9ee8b78","added_by":"auto","created_at":"2025-05-07 07:38:20","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":1258022,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpectra of corn grains from the combined model with and without preprocessing techniques\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"8.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/3916d54512cd3ae462cef7f3.png"},{"id":82156265,"identity":"89781610-2e0e-4d8c-86ec-fc6372273c7a","added_by":"auto","created_at":"2025-05-07 07:46:20","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":1269634,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpectra of corn grains from endosperm-side model with and without preprocessing techniques\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"9.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/a439709923237617c122d441.png"},{"id":82155137,"identity":"10e417e6-c92e-4051-9e11-f3621abddef7","added_by":"auto","created_at":"2025-05-07 07:38:21","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":1144402,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpectra of corn grains from the germ-side model with and without preprocessing techniques\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"10.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/c758714f8f7c8a306efaa5ef.png"},{"id":82151926,"identity":"40490d1a-45bc-4a94-9e64-28c21afc6252","added_by":"auto","created_at":"2025-05-07 07:22:20","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":127364,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eScatter plot of predicted vs actual DON using the full spectrum with germ-side position using PLSR model\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"11.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/a5188659c8fd7a66dbfd6d6d.png"},{"id":82151953,"identity":"d755b31d-815e-4f0f-9e07-e5ed82def3eb","added_by":"auto","created_at":"2025-05-07 07:22:21","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":220419,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eThe varying trends of sampled variables, RMSECV and regression coefficient path for the number of sampling runs in CARS algorithm\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"12.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/2a1740d84aa39345371613f5.png"},{"id":82154412,"identity":"f52a2925-e07a-4947-9efa-8fb118c9e27c","added_by":"auto","created_at":"2025-05-07 07:30:21","extension":"png","order_by":13,"title":"Figure 13","display":"","copyAsset":false,"role":"figure","size":93378,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eScatter plot of predicted vs actual DON using the CARS selected wavelengths of germ-side position using SVMR model\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"13.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/4e9fa2e3620ddf3e40940489.png"},{"id":82151946,"identity":"151f29d2-c1e3-4180-b2a9-afb562e7d216","added_by":"auto","created_at":"2025-05-07 07:22:21","extension":"png","order_by":14,"title":"Figure 14","display":"","copyAsset":false,"role":"figure","size":104286,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eScatter plot of predicted vs actual DON using the IRIV selected wavelengths of germ-side position using SVMR model\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"14.png","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/2f7922814555af27e3a2f80b.png"},{"id":82157188,"identity":"4a700d6b-3764-4d4f-b336-432758f03807","added_by":"auto","created_at":"2025-05-07 07:54:33","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9937839,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6465545/v1/cffe9a24-d82f-467e-9400-24d0382701cb.pdf"}],"financialInterests":"","formattedTitle":"Application of Non-destructive and Chemical-free Short-Wave Infrared Hyperspectral Imaging (SWIR-HSI) coupled with Machine Learning Regression for Rapid Quantification of Deoxynivalenol (DON) in Individual Corn Kernels","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eCorn is the largest grain crop in the world, with a global production amounting to 1241\u0026nbsp;million tonnes in 2023 (FAOSTAT \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Corn is essential in the human diet because of its 72\u0026ndash;73 % carbohydrat content. Corn grain finds various applications as food, feed, and raw material for ethanol production, and the global demand for corn continuously increases yearly. Mycotoxins, the secondary metabolites in food and feed products, are predominantly produced by the pre-harvest Fusarium, post-harvest \u003cem\u003eAspergillus\u003c/em\u003e, and \u003cem\u003ePenicillium\u003c/em\u003e species. (Senthilkumar et al. \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). Fusarium infection in field corn before harvest and subsequent mycotoxin contamination of corn grains has affected the yield and quality of corn grains.\u003c/p\u003e \u003cp\u003eDeoxynivalenol (DON) (3,7,15-trihydroxy,12,13-epoxy-tricothec-9-en-8-one) predominantly present in corn, is a trichothecene secondary metabolite produced mainly by \u003cem\u003eFusarium graminearum\u003c/em\u003e and \u003cem\u003eFusarium culmorum.\u003c/em\u003e The DON is a very stable compound and can\u0026rsquo;t be removed from the food supply chain even at higher processing temperatures between 170 and 350℃. The DON content in corn kernels is a serious quality and safety issue, resulting in reduced yield, poor grade, and eventually reduced profit for the producers and processors. Corn remains the economical source of food for consumers around the world, and the presence of DON can severely affect consumers. Several incidents of DON have been reported in the past in cattle feed and processed foods (pasta, bread, flour, extruded foods) (Brumley et al. \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e1985\u003c/span\u003e; Schollenberger et al. \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e1999\u003c/span\u003e; Castillo et al. \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2008\u003c/span\u003e; EFSA \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2013\u003c/span\u003e; Wu et al. \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2017\u003c/span\u003e). A study on Swine Feed intake found reduced feed intake with 1 \u0026micro;g/g DON. The reduction rate increased proportionally, and complete feed refusal has been observed at concentrations greater than 10 \u0026micro;g/g DON in feed (Munkvold et al. \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). Consumption of DON-contaminated feed has triggered vomiting, nausea and adverse effects in cattle and swine. DON inhibits the cell signalling process in eukaryotic cells. Its compounds have been reported to cause throat irritation, esophageal cancer, diarrhea, dizziness, fever, headache, and other adverse effects when consumed. (Prieto-Sim\u0026oacute;n et al. \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e2007\u003c/span\u003e). The DON, due to its thermal stability and the potential health risk, is regulated by most countries with maximum allowable limits (MAL) for baby food products, adult foods, and animal feed. The DON MAL for infant and baby foods is in the range of 200 \u0026micro;g/kg to 600 \u0026micro;g/kg, direct adult human consumption is in the range of 750 \u0026micro;g/kg to 1200 \u0026micro;g/kg, and animal feed in the range of 1000 to 5000 \u0026micro;g/kg (EFSA \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2013\u003c/span\u003e; Food and Agriculture Organization of the United Nations (FAO) \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2015\u003c/span\u003e; Regulatory Guidance (RG-8). Government of Canada. 2017).\u003c/p\u003e \u003cp\u003eCurrent analytical methods to detect mycotoxins (DON and a combination of different mycotoxins) include immunochemical and analytical methods like liquid and gas chromatography (LC, GC) and assay-based. These methods are expensive, time-consuming, require professional knowledge, and cannot be applied directly in the field (McMullin et al. \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2015\u003c/span\u003e). Several non-destructive methods have been recently studied for their potential to detect mycotoxin contamination and fungal infections in cereals and cereal products, such as IR spectroscopic methods (Near-infrared (NIR), Shortwave infrared (SWIR), Visible NIR).Shi et al. \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e2022\u003c/span\u003e demonstrated using NIR spectroscopy to rapidly investigate different quality parameters associated with soybeans.Rathna Priya and Manickavasagan \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2021\u003c/span\u003e used NIR spectroscopy for corn grain characterization, including seed viability, kernel hardness, haploid kernel identification, moisture, oil, and starch content. Several studies utilized NIR spectroscopy between the 1000 and 2500 nm spectral range for rapid \u003cem\u003efusarium\u003c/em\u003e-damaged wheat kernel (FDK) identification and DON contamination (Peiris et al. \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2009\u003c/span\u003e; Peiris et al. \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2010\u003c/span\u003e; Kautzman et al. \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e2015\u003c/span\u003e). In maize, \u003cem\u003efusarium\u003c/em\u003e infection detection, aflatoxin and mycotoxin contamination detection, and quantification of AFB1 toxin and fumonisins have been widely studied. In addition, IR spectroscopic methods can only detect spectral characteristics and chemical changes at a single spot on the grain and do not reflect the true contamination levels of the individual grain. Hyperspectral imaging systems (HSI) can overcome this disadvantage of NIR spectroscopic techniques.\u003c/p\u003e \u003cp\u003eIn recent years, studies on the quality and safety aspects of food using hyperspectral imaging (HSI) have gained popularity. HSI acquires information in a wide range of the electromagnetic spectrum (250\u0026ndash;2500 nm), and depending upon the application, the HSI system could collect information from specific spectral ranges in the Ultraviolet-visible (UV-VIS) regions (250\u0026ndash;500 nm), visible and near-infrared (VIS-NIR) regions (400\u0026ndash;1000 nm), near-infrared (NIR) regions (900\u0026ndash;1700 nm), and short wave infrared (SWIR) regions (900\u0026ndash;2500 nm). HSI studies utilizing the UV-VIS range predominantly focus on visible changes, defects, and other physical features. In contrast, the NIR and SWIR ranges can detect physicochemical components and contaminants (Femenias et al.2022). Unlike conventional spectroscopic techniques, HSI is a hypercube comprising spectral and spatial information. The hypercube is a 3-D data cube with spatial axes (X, Y) and spectral axes (λ), enabling specific regions to be extracted and analyzed. (Jiang et al. \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2010\u003c/span\u003e). HSI has the potential to screen single grain and acquire individual kernel data for numerous grains simultaneously. The HSI allows the selection of X and Y axes of each individual kernel. Thus, the acquired HSI or hypercube contains spectral data from n x n pixels of every kernel. The background could be removed either manually or automatically. Thus, HSI is a potential tool for analyzing the chemical profile of a single kernel at the n x n pixel level acquired at different wavelengths.\u003c/p\u003e \u003cp\u003eIn combination with chemometric techniques, HSI has been successfully utilized to determine different quality characteristics in foods, including fruits, vegetables, cereals, pulses, oilseeds, fish, and meat, by extracting and analyzing relevant information from the hypercube. Regression and classification methods such as principal component analysis (PCA), support vector machine (SVM), partial least squares regression (PLSR), artificial neural network (ANN), deep learning artificial neural network (ANNDL), multiple linear regression (MLR), partial least squares discriminant analysis (PLSDA), k-nearest neighbour (KNN) have been utilized successfully for analyzing hyperspectral data, determining the quality parameters and composition of food matrices and also for quantitatively predicting the targeted components and contaminants in food. Studies show that HSI has been successfully used to detect defects, bruises, decay and physical injury in fruits (apple, strawberries and citrus) and vegetables (onion, mushroom, cucumber). Studies on detecting adulterants, pesticides, microbial contaminants and other chemical contaminants have also been reported on fresh produce and other food products. (Sun \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2010\u003c/span\u003e; Feng and Sun \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2012\u003c/span\u003e; Ravikanth et al. \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e2017\u003c/span\u003e; Xu et al. \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Most studies on HSI utilize PLSR, SVMR, PCA and ANN regression models for prediction. PLSR and SVMR are commonly used to study linearity and nonlinearity in the datasets (Vapnik \u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e2000\u003c/span\u003e; Abdi \u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2003\u003c/span\u003e; Cruz-Tirado et al. \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Saha et al. \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). In addition, feature wavelength selection using different methods is currently utilized to improve the model performances and accurately detect and identify food components. These strategies reduce the complexity of the model by decreasing the collinearity and errors in the HSI data, thereby improving the precision of the model. Competitive Adaptive Reweighted Sampling (CARS) and Iteratively Retaining Informative Variables (IRIV) are two of the most successful wavelength selection strategies deployed in HSI data analysis (Zhang et al. \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Wang et al. \u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e2022\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eIn grain elevators, random sampling is performed to decide the DON levels of each lot and grains with different contamination levels are blended to achieve the permitted levels. Recent studies have proposed HSI classification to differentiate healthy and \u003cem\u003efusarium\u003c/em\u003e-infected grains to decrease the overall contamination levels by discarding the infected grains (Xing et al. \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Alisaac et al. \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Parrag et al. \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Femenias et al. \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2022a\u003c/span\u003e). However, limited studies quantify DON in corn kernels to remove DON-contaminated grains from entering the food chain. Therefore, the objectives of this research are 1. to investigate the potential of shortwave near-infrared hyperspectral imaging system (SWIR-HSI) to quantify the deoxynivalenol (DON) content in corn kernels, 2. to investigate the effect of the position of the corn grains (germ-side or endosperm-side) on the ability of HSI in predicting DON levels, 3. to determine the best combination of preprocessing and chemometric technique for accurate quantification of DON and 4. to investigate the model enhancement performances of CARS and IRIV feature wavelength selection methods.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Sample Preparation\u003c/h2\u003e \u003cp\u003eA separate study was first conducted to determine the suitable sample preparation technique to mimic the real DON contamination in corn kernels. The study explored DON absorption using the injection method on whole corn kernels and the soaking method on both whole and cracked kernels using water, methanol, and acetonitrile. The methods were validated by analyzing the absorbed DON, optical microscopic analysis, and scanning electron microscopic analysis. The soaking cracked method was best validated by DON absorption and recovery analysis (Priya and Manickavasagan \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). The samples for this study were prepared using the soaking cracked method with four concentration levels of DON and one control sample\u0026ndash; 0,1, 2, 5 and 10 \u0026micro;g/g (ppm).Schaafsma, Fr\u0026eacute;geau-Reid, and Phibbs n.d. explained the importance of making a small crack in the corn pericarp to facilitate better absorption of DON inside the corn kernel. The cracked (small crack in the pericarp layer) corn kernels were soaked in the DON solution made with DON procured from Millipore Sigma (Sigma-Aldrich, Oakville, Canada) and dissolved in distilled water explained inPriya and Manickavasagan \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e2023\u003c/span\u003e was replicated in this study using the 2019 crop year corns procured from the Ministry of Agriculture, Ontario. The flowchart of the experimental design is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. The moisture content of the corn kernels was determined by the hot air oven method(Shreve \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e2006\u003c/span\u003e) using a laboratory oven (Binder FD53-UL, Tuttlingen, Germany). After soaking treatments, the soaked kernels were again dried at 55℃ until the initial moisture content of 9.21% (dry basis) was achieved and stored at 4℃ until further analysis.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Corn kernel samples for image acquisition\u003c/h2\u003e \u003cp\u003eThe Corn kernels stored at 4℃ were allowed to reach room temperature before hyperspectral image acquisition. Eighty individual corn kernels were picked from control, 1, 2, 5 and 10 \u0026micro;g/g concentration level samples for total corn kernels of 80 X 5\u0026thinsp;=\u0026thinsp;400 for this study. Schaafsma, Fr\u0026eacute;geau-Reid, and Phibbs n.d. studied the natural distribution of DON in different parts of the corn kernel. They found that corn kernel\u0026rsquo;s pericarp, germ, and endosperm had DON levels at 55%, 25% and 20%, respectively. The corn kernel's orientation or position during HSI would play a significant role in quantifying DON. So, for this study, each individual kernel was subjected to hyperspectral imaging on the germ-side and endosperm-side of the kernel. So, 400 germ-side and 400 endosperm-side individual kernels HSI images were acquired.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 SWIR Hyperspectral Image Acquisition\u003c/h2\u003e \u003cp\u003eThe SWIR hyperspectral imaging system (Headwall Photonics, USA) located at the APHTC, Lethbridge College, was utilized for this study. The HSI system, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, comprises 1. an MCT sensor-based camera unit coupled with a spectrograph, 2. an adjustable power level quartz halogen lamp (USHIO 150 W) as the illumination source, 3. a movable stage for line scanning operation, and 4. a data capture and handling system (Hyperspec III \u0026ndash; v3.1.5). The corn kernels were arranged on the sample tray (18 kernels \u0026ndash; 3 kernels arranged at equal distances in 6 rows) row-wise, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, and reflectance HSI images were captured in the SWIR spectral range 900\u0026ndash;2500 nm. The line scan HSI system with a 9.6 nm spectral resolution collected 384 spatial and 169 spectral bands. The white reference was collected using a Spectralon white reference (99%, Labsphere, North Sutton, NH) and the black reference by closing the lens opening with a dark cap. The white and dark references were calculated every 30 minutes, and the corrections were automatically added to the sample images. The speed of the sample stage was set at 16.297 mm/s and an exposure time of 13 ms to eliminate vibrations and overlapping of spectral data on the same regions of the kernel. Also, the corn kernels were arranged on the stage between 44mm and 205mm, with an entire stage length of 230 nm, and the hyperspectral images were captured only between these lengths. The power level of the illumination was set at 105 W. The SWIR system, including the lights, was turned on 30 minutes before an imaging session to maintain stability and reduce variations in the system.\u003c/p\u003e \u003cp\u003eCorn kernels were initially arranged on the sample stage with the germ-side facing upwards, and hyperspectral images were acquired. The sample stage will move horizontally till the set length, and the image with the spectral and spatial information will be captured line by line. Immediately after this, without changing the arrangement, the corn kernels were turned with the endosperm-side facing upwards, and a second hyperspectral image was acquired. Thus, every kernel had both the germ-side and the endosperm-side captured. Each corn kernel was given a number sequentially and labelled accordingly. Thus, the acquired hypercube consisted of two spatial axes (367 x 368 pixels) and one spectral axis with 169 bands collected at every 9.6nm wavelength interval between 900 and 2500 nm. The acquired hypercube in pixels was normalised as reflectance, and the discrepancies arising from the spectral and spatial radiations were corrected automatically using Hyperspec III software to obtain explicit and distortion-less images. The corrected images were stored in high dynamic range (HDR) format.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Quantification of DON content\u003c/h2\u003e \u003cp\u003eThe DON uptake in corn kernels was determined using a commercial Deoxynivalenol ELISA kit, which can detect DON in concentrations between 3 to 243 ng/ml. The ELISA kit utilizes antigen-antibody interaction and followed by horseradish peroxidase colorimetric detection, the DON antigens in the corn kernel matrix are quantified (Berthiller et al. \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2013\u003c/span\u003e; Munkvold et al. \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). The corn kernels from the control and different levels of DON concentration samples in triplicates were grounded. The steps involved in the competitive assay for DON quantification are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e as a flowchart. The correction wavelength was set at 630 nm, and the optical density was measured at 450 nm using a spectrophotometer (Thermo Scientific Multiskan FC plate reader). The concentration of DON in each treatment method was determined by extrapolating the percentage of absorbance values (negative correlation) in the standard graph for various concentrations of DON.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.5 Spectral Data Preprocessing\u003c/h2\u003e \u003cp\u003eThe HDR format hypercubes were transformed into .mat files (Matlab files) for further processing. The dead pixels in the data were removed by applying a median, and the spatial window for each of the 18 corn kernels in a hyperspectral image was determined by column indexing. This window selection would facilitate the proper selection of ROI during segmentation. Each corn kernel was labelled using the bwlabel function. The threshold function created a logical mask to capture the 18 corn kernels from the original image at all 169 wavelengths to segment all 18 individual corn kernels. Finally, each corn kernel was cropped from the segmented image and stored separately as one ROI. The spectral data from every corn kernel was extracted for further preprocessing to remove unimportant information such as background disturbances, scattering effect and baseline drift. In this study, the raw data were preprocessed using both traditional and advanced preprocessing techniques to study their effects on the ability of the model to quantify DON content in corn kernels. A total of 15 preprocessing techniques were utilized in this study, including weighted least squares, external parameter orthogonalization filter (EPO), gap segment, detrend, mean centring, generalized least squares (GLS) weighting, multiplicative scatter correction (MSC), orthogonal signal correction (OSC), probabilistic quotient normalization (PQN), Savitsky \u0026ndash; Golay smoothing, standard normal variate (SNV), Whitaker filter and their combinations. Since one preprocessing technique does not apply to all data, we must identify suitable preprocessing methods for our study. After analyzing and comparing the effects of each preprocessing technique on the model performance, a suitable preprocessing or combination of different methods was chosen for DON content prediction.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e2.6 Principal Component Analysis (PCA)\u003c/h2\u003e \u003cp\u003eThe preprocessed HSI data contains more variables and often requires chemometric tools to build and analyze different classification and regression approaches. There are numerous modelling techniques for pattern recognition and grouping, but principal component analysis (PCA), least discriminant analysis (LDA) and support vector machines (SVM) are the most used techniques. This study used PCA (PLS toolbox in SOLO software, Eigenvector Research, Inc.) to analyze the sources of variances or principal components (PCs), which capture the maximum variations in our hyperspectral data. PCA captures the maximum information in the first component, followed by the rest of the components, thus reducing higher dimensions of data into fewer components containing the most valuable information.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e2.7 Feature Wavelength Selection\u003c/h2\u003e \u003cp\u003eSince the HSI data collected is massive, analyzing and model building could consume huge amounts of time and data, and owing to multi-collinearity, model performance could be lower. To overcome this disadvantage, selecting important wavelengths that contribute to the most valuable information for DON quantity prediction during model development becomes important. This would drastically reduce the hypercube data, enhancing the model-building speed, performance, and prediction accuracy. This study utilized two promising feature wavelength selection methods: competitive adaptive reweighted sampling (CARS) and iteratively retaining informative variables (IRIV).\u003c/p\u003e \u003cdiv id=\"Sec10\" class=\"Section3\"\u003e \u003ch2\u003e2.7.1 CARS\u003c/h2\u003e \u003cp\u003eCARS algorithm is commonly used to select important variables or feature wavelengths based on absolute coefficients. The CARS algorithm is performed based on a series of steps. 1. Each feature weight is evaluated based on the regression coefficient's absolute value, and 2. The Monte Carlo technique groups N subsets of wavelengths obtained during every sampling run based on the absolute coefficient corresponding to each wavelength, 3. Exponentially decreasing function (EDF) and adaptive reweighted sampling (ARS) are utilized to choose the principal features. 4. the significant wavelengths are selected (Li et al. \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Saha et al. \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). The Monte Carlo sampling runs were optimized to seventy. The selected CARS wavelengths were used for prediction model development (MATLAB version 2020a, The Mathworks Inc., Natick, USA). .\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section3\"\u003e \u003ch2\u003e2.7.2 IRIV\u003c/h2\u003e \u003cp\u003eIRIV algorithm works based on binary matrix shuffling for the selection of features (Wang et al. \u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). The RMSE of cross-validation is used in the IRIV algorithm to evaluate each feature's performance. The model population analysis (MPA) technique categorizes each variable into strong, medium, weak, and no information variables. Several repetitions are performed, the variables repeating in each subset are given higher weights, and variables with lower weights and interference are eliminated, retaining only variables with effective information. Finally, a reverse elimination is performed, and the remaining variables are chosen as the feature variables. This study performed twenty-fold cross-validation, and the chosen wavelengths were utilized for prediction model development (MATLAB version 2020a, The Mathworks Inc., Natick, USA).\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003e2.8 Model Building and Evaluation\u003c/h2\u003e \u003cp\u003eThree models were trained for this study \u0026ndash; 1. germ-side up, 2. endosperm-side up, 3. combined model. The combined model was developed by integrating the dataset irrespective of the side of the corn kernel. This was used to study the difference in model performance when used in real-time inspection. PLSR and SVMR were utilized to build a model and predict DON in single corn kernels. PLSR is one of the most widely applied linear predictive methods and could be used for multivariate data analysis. PLSR is a supervised method for better predictions in multivariate problems (Mehmood et al. \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2020\u003c/span\u003e). PLSR was initially trained on the full spectra using different preprocessing methods. The best combination of preprocessing method with PLSR was identified. Also, PLSR regression models were developed utilizing the wavelengths identified by feature selection methods. SVMR is a nonparametric, statistical learning technique that balances prediction accuracy and data generalization. SVMR establishes the non\u0026ndash;linear relationship in the data and retains a sound generalization of the untested data (Zhong et al. \u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). SVMR has the advantage of handling big multivariate datasets with noisy patterns (Deiss et al.2020). Like PLSR, SVMR was also trained on the whole and selected wavelength spectra (PLS toolbox in SOLO software, Eigenvector Research, Inc.).\u003c/p\u003e \u003cp\u003eThe robust Venetian blinds ten-fold cross-validation was used for model building. The mean performance of all the models was then computed for cross-validation. The Kennard-Stone algorithm randomly splits the data into the calibration and predictive sets. The algorithm selected 290 samples for calibration sets and 126 for prediction sets for the individual models (germ-side and endosperm-side). For the combined model, 588 samples were selected for the calibration and 252 for the prediction set. All the models used the exact calibration and prediction datasets to eliminate dataset errors and bias in model training.\u003c/p\u003e \u003cp\u003eThe calibration, cross-validation, and prediction coefficient of determination ((R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec)\u003c/sub\u003e, (R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e) and (R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e)) were chosen as the evaluation metrics for the model performance. The calibration, cross-validation, and prediction root mean square errors ((RMSEC), (RMSECV) and (RMSEP)) were also used to assess the variations between predicted and real values in the corresponding sets. For a model to perform well, the R\u003csup\u003e2\u003c/sup\u003e of calibration and prediction should be high, whereas the corresponding RMSE values should be low. The PLS toolbox by SOLO (Eigenvector Research Inc.) was utilized to develop PLSR and SVMR regression models. The feature wavelength selection, CARS and IRIV were performed in MATLAB (version 2020a, The Mathworks Inc., Natick, USA).\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results and Discussion","content":"\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003e3.1 DON content in treated corn kernels\u003c/h2\u003e \u003cp\u003eThe DON uptake levels in corn kernels by the soaking treatment method were determined by the ELISA method. The DON uptake levels ranged between 0 and 5.58 \u0026micro;g/g in the corn kernels. For DON treatment at concentrations 1, 2 and 5 \u0026micro;g/g, the average recovery rates of 68%, 66% and 72% were observed in the corn kernels, respectively. For higher concentrations at 10 \u0026micro;g/g, the average recovery rate was lower at 56%. This could be due to the slow rate of water absorption in the kernel matrix and loss of the DON deposited on the kernel surface due to drying or other handling procedures.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Spectral Analysis\u003c/h2\u003e \u003cp\u003eThe spectral curves of individual corn kernels from the germ-side, endosperm-side and combined model are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e. The spectral curves for the germ and endosperm-side models showed similar trends but slight variations in the reflectance values. The variations in reflectance between the two positions of corn kernels can be seen in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003ed. The germ-side spectral reflectance curve was higher than the endosperm-side. Both curves overlap between the wavelength range of 1250 and 1450 nm, corresponding to the N-H combination bands of proteins in the kernels (Sharma et al. \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e2020\u003c/span\u003e). The slight changes in the spectral reflectance values between the germ-side and endosperm-side of the kernels could either be due to a change in the kernel composition between the two sides or the chemical modifications because of DON distribution between both sides. The germ portion is rich in oil and protein, whereas the endosperm-side is rich in starch (carbohydrate). This could cause a difference in the reflectance values.\u003c/p\u003e \u003cp\u003eSeven individual peaks were observed for the corn kernels at 1101, 1301, 1650, 1825, 2016, 2225 and 2420nm from the germ and endosperm-side spectrum. The seven wavelengths can be attributed to fundamental Carbon-Hydrogen, Oxygen-Hydrogen and Nitrogen-Hydrogen bonds (Saha et al. \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). The 1101, 1301 and 1650 nm wavelengths correspond to the Carbon-Hydrogen second overtone stretch in carbohydrates, the Nitrogen -Hydrogen first overtone stretch and the Carbon\u0026thinsp;=\u0026thinsp;Carbon stretch in protein molecules, respectively (Sharma et al. \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). It has been widely known that the wavelengths between 1500\u0026ndash;2000 nm are attributed to the Nitrogen-Hydrogen bonds in proteins, and between 1000\u0026ndash;1100 and 2000\u0026ndash;2500 nm are attributed to Carbon-Hydrogen bonds in carbohydrates. The wavelengths linked to DON toxin could not be directly identified using the spectral reflectance curve, and further analysis using chemometric tools is necessary.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Spectral Analysis using PCA\u003c/h2\u003e \u003cp\u003ePCA was used to examine the correlation or band dependency between variables by applying statistical properties. Weighted least squares preprocessing and mean centring were used to eliminate multi-collinearity in raw data. The principal components (PCs) were analyzed for data clustering and the percentage of variance captured. The highest contrast or variance was observed in the first PC, capturing 95.6% of the variance, and the lowest variance observed in the last band was 3.88%, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003ea. Thus, the overall variance was captured by PC1 alone. Data clustering was observed from the PCA plot, and the calibration and prediction set showed cluster formation (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003eb). This grouping indicates that the spectral characteristics are related to the DON concentration in corn kernels. Thus, the PCA results further support the potential of HSI in predicting the DON concentration in individual corn kernels.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section2\"\u003e \u003ch2\u003e3.4 Evaluation of developed models using whole spectra\u003c/h2\u003e \u003cp\u003eThe PLSR and SVMR regression models were developed utilizing the entire spectra of the corn kernels and their reference DON content. Each model was trained with and without preprocessing raw spectral data to observe and study the impact of different preprocessing techniques on the model's performance. A total of 15 preprocessing techniques have been applied to all three models \u0026ndash; 1. germ-side model, 2. endosperm-side model, and 3. combined model. The changes in raw spectral data during each preprocessing method were shown in Figs.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e8\u003c/span\u003e, \u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e9\u003c/span\u003e, and \u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e for all three models. Tables\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, \u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e summarize the results for DON quantification in individual corn kernels for all three models (calibration, cross-validation and prediction). The predicted and actual DON content plot was used to identify the robust prediction models for DON quantification (The red line in the plot). If the sample points are closer to the best correlation fit line, the model's accuracy in predicting DON content will be higher and vice versa.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePrediction results of combined model (both germ-side and endosperm-side) to detect DON in individual corn grains using full spectrum\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePre-processing\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e(LVs/SVs)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRMSEC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRMSECV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eRMSEP\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePLSR\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8239\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.0037\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8162\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.0255\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8382\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.9682\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWeighted LS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9015\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7504\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8934\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7811\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8889\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.8029\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9099\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7182\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9037\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7426\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9112\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7207\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eEPO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9276\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.018\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9189\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e3.0251\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9231\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e3.0063\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGap 1st derivative\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8988\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7611\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8912\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7894\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7622\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGLS weighting\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9313\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.0148\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9234\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e3.0254\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9251\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e3.0045\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMean centering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9112\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.4143\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8957\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.7632\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8854\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.6529\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC (mean)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9288\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6381\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9182\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6844\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9214\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6766\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9281\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6416\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9184\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6838\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9211\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6822\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePQN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.911\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7133\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9008\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7534\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9146\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7124\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8466\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9371\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8264\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.9974\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8557\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.9186\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.929\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6375\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9183\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6837\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.921\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6784\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWhittaker Filter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8998\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7571\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.893\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7828\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9039\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7498\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.922\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6682\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9139\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9158\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6991\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.929\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6375\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9184\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6836\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.921\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6784\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9294\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6354\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9196\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6784\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9211\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6787\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSVMR\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e419\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9812\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3271\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9309\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6269\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9649\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4563\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWeighted LS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e443\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9832\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3106\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9551\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5058\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9721\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4089\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e375\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9823\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3181\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.961\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4707\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9746\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3889\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eEPO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e483\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9829\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3115\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9695\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4186\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9798\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3434\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGap 1st derivative\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e554\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8053\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.0721\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7908\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.1082\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.822\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.0687\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGLS weighting\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e542\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9702\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4139\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9605\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4748\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9669\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4465\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMean centering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e419\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9812\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3271\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9309\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6269\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9649\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4564\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC (mean)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e366\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9805\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3346\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9617\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4669\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9718\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4101\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e406\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9777\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3565\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9371\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5978\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9719\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4076\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePQN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e429\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.3891\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.8764\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.3745\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.8951\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.4054\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.8865\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e456\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9672\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4328\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9113\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7098\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9459\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5657\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e500\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9947\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.1738\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9674\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4298\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9851\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.2959\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWhittaker filter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e370\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9817\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3237\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9651\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4464\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9751\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3837\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e511\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9871\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2725\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.968\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4263\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9791\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3525\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e500\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9947\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.1738\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9674\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4298\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9851\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.2959\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e497\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9913\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2242\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9585\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4855\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3289\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"9\"\u003eLS \u0026ndash; Least squares; PLSR \u0026ndash; Partial least square regression; SVMR \u0026ndash; Support vector machine regression; EPO -external parameter orthogonalization; GLS \u0026ndash; generalized least squares; MSC- multiplicative scatter correction; OSC - orthogonal signal correction; PQN -probabilistic quotient normalisation; Sav-Gol - Savitsky \u0026ndash; Golay smoothing; SNV \u0026ndash; standard normal variate; R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec,\u003c/sub\u003e R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv,\u003c/sub\u003e R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u0026ndash; coefficient of determination of calibration, cross-validation, and prediction; RMSEC, RMSECV, RMSEP \u0026ndash; root mean square error of calibration, cross-validation and prediction.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePrediction results of the germ-side model to detect DON in individual corn grains using full spectrum\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePre-processing\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e(LVs/SVs)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRMSEC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRMSECV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eRMSEP\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePLSR\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9151\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8994\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7646\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9359\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6402\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWeighted LS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9181\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6782\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9068\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7236\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9359\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6469\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9243\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6518\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9137\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6961\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9482\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5671\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eEPO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9323\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.0903\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9213\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e3.0918\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9478\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e2.9663\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGap 1st derivative\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9168\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6835\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9052\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7294\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9453\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5911\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGLS weighting\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9298\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.0925\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9183\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e3.0946\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9487\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e2.9587\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMean centering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8710\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.1455\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8557\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e3.1577\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8959\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e2.9937\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC (mean)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9385\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.5872\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9252\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6484\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9521\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5467\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9413\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.5740\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9221\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6620\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9570\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5139\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePQN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9002\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7484\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8835\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.8087\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9376\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6332\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8598\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.8873\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8463\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.9292\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9079\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7844\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9337\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6102\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9228\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6585\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9481\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5678\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWhittaker Filter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9255\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6468\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9146\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6926\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9215\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7010\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9248\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6498\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9136\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6965\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9396\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6111\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9337\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6102\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9228\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6585\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9481\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5678\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9444\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.5586\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9265\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6426\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9531\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5369\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSVMR\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e219\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9520\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.5276\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9222\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6649\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9317\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6484\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWeighted LS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e160\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9844\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2984\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9619\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4654\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9740\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3983\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e168\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9836\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3061\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9637\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4539\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9758\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3872\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eEPO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e168\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9927\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2041\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9698\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4131\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9823\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3263\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGap 1st derivative\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e120\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.7832\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.1338\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7694\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.1684\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.7837\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.1749\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGLS weighting\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e192\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9762\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3705\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9646\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4484\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9687\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4404\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMean centering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e219\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9519\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.5276\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9222\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6649\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9317\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6484\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC (mean)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e173\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9847\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2944\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9695\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4151\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9772\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3726\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e187\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9786\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3491\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9465\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5503\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9729\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4069\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePQN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e214\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.3460\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.9387\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.3266\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.9637\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.4122\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.9308\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e225\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9295\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6408\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8941\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7769\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9099\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7514\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e239\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9955\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.1595\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9742\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3817\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9854\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.2953\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWhittaker filter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e172\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9817\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3244\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9658\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4412\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9787\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3598\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e244\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9903\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2347\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9733\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3891\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9803\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3443\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e239\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9955\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.1595\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9742\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3817\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9855\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.2953\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e169\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9925\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2057\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9627\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4593\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3300\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePrediction results of the endosperm-side model to detect DON in individual corn grains using full spectrum\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePre-processing\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e(LVs/SVs)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRMSEC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRMSECV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eRMSEP\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePLSR\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.7451\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.2072\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7312\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.2397\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8239\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.0112\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWeighted LS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8771\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.8382\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8440\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.9446\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9075\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7279\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9060\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7331\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8874\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.8028\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9139\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7060\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eEPO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9192\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.9621\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8998\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e2.9768\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9253\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e2.8997\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGap 1st derivative\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9058\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7355\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8894\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7971\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9119\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7164\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGLS weighting\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9244\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.9468\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9074\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e2.9613\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9194\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e2.9385\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMean centering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9053\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.9754\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8840\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e3.0075\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9109\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e2.9257\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC (mean)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9238\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6616\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9106\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7166\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9152\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6994\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9246\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6583\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9053\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7379\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9188\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6869\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePQN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9189\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6822\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8980\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7656\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9184\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7027\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8083\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.0493\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7941\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.0885\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8227\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.0025\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9308\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6305\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9146\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7006\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9208\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6825\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWhittaker Filter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8604\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.8935\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8440\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.9445\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9031\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.7496\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9298\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6348\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9047\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7416\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9186\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6858\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9307\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6305\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9146\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7006\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9208\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6825\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9374\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.5994\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9179\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6874\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9231\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6718\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSVMR\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e226\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9824\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3209\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8995\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7648\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9652\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4490\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWeighted LS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e236\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9792\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3477\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9338\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6179\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9650\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4476\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e268\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9791\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3515\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9455\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5621\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9728\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4022\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eEPO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e257\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9915\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2218\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9595\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4834\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9859\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.2853\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGAP 1st derivative\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e260\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.7480\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.2216\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7263\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.2687\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8092\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.0971\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGLS weighting\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e212\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9719\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4071\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9568\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5014\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9705\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4098\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMean centering\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e226\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9824\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3209\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8995\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7648\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9652\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4490\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC (mean)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e199\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9783\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3558\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9482\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5476\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9752\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3786\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e215\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9742\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3874\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9074\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7311\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9669\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4394\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePQN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e226\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.3214\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.9821\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.3116\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.9967\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.3072\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e1.9841\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e240\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9695\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4225\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.8721\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.8607\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9505\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5321\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e270\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9999\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0099\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9540\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5155\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9831\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3108\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWhittaker filter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e255\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9775\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3620\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9496\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5411\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9766\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3658\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDetrend\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e194\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9980\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.1072\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9557\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5048\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9859\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.2821\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e270\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9999\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.0099\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9540\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5155\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9831\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3108\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOSC\u0026thinsp;+\u0026thinsp;SNV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e205\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9637\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4593\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9238\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6636\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9629\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4605\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eFor the combined model where the corn kernels are imaged irrespective of the position of the kernel, SNV preprocessing with PLSR model development provided the best prediction coefficient of determination (R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e) of 0.921 and RMSEP values of 0.6784 utilizing 11 LVs. The combination of the MSC\u0026thinsp;+\u0026thinsp;SNV preprocessing technique also yielded the same results. For the germ-side model, PLSR model with OSC\u0026thinsp;+\u0026thinsp;SNV yielded the best prediction coefficient of determination (R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e) of 0.9531 and RMSEP of 0.5369 (11 LVs), followed by PLSR with MSC mean preprocessing technique with R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e value of 0.9521 and RMSEP values of 0.5467 with 11 LVs. For the endosperm-side model, PLSR models with OSC\u0026thinsp;+\u0026thinsp;SNV provided the best prediction coefficient of determination (R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e) of 0.9231 and an RMSEP of 0.6718 with 11 LVs. The PLSR results obtained in this study were higher than those reported in the literature. Zhao et al. \u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e2020\u003c/span\u003e used PLSR to predict DON in wheat flour with R2\u003csub\u003ep\u003c/sub\u003e in the range of 0.69\u0026ndash;0.726. Tekle et al. \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e2015\u003c/span\u003e used PLSR with SNV to quantify DON in single oat kernels with R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e of 0.81.\u003c/p\u003e \u003cp\u003eIn SVMR models with SNV provided the highest R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e of 0.9851 and RMSEP of 0.2959 for the combined model; the MSC\u0026thinsp;+\u0026thinsp;SNV preprocessing technique performed better (R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e 0.9851 and RMSEP of 0.2959) for germ-side model and EPO and Detrend\u0026thinsp;+\u0026thinsp;SNV preprocessing techniques performed better for endosperm-side model. These results are in accordance with the study utilizing SVMR for predicting DON levels in winter wheat with an accuracy greater than 80%. The developed SVMR model also predicted that the samples with high DON contamination were more significant than 200 \u0026micro;g/kg with an accuracy of 90% (Marzec-Schmidt et al. \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). The SNV preprocessing technique is important in enhancing the model performance and predicting DON in all the models. SNV increases the signal-to-noise ratio to compensate for the differences and errors caused by the light scattering. EPO removes the difference in spectrometer temperature and corn kernel moisture. At the same time, detrend aims to reduce data interference due to kernels' size and other spectral peak shape issues.\u003c/p\u003e \u003cp\u003eThe germ-side model yielded the highest coefficient of determination for prediction results (Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e11\u003c/span\u003e). These results further support the fact that deposition and absorption of DON in \u003cem\u003efusarium-\u003c/em\u003einfected kernels will be higher in the pericarp and germ portion than the endosperm portion, as stated by Schaafsma, Fr\u0026eacute;geau-Reid, and Phibbs n.d. Also, from the results, it is evident that DON prediction in individual corn kernels greatly depends on the orientation or position of the corn kernel during imaging. Therefore, for DON prediction, the germ-side of corn kernels provided the best results and proved to be the best position to capture HSI.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003e3.5 Evaluation of developed models with CARS and IRIV selected feature wavelengths\u003c/h2\u003e \u003cp\u003eThe CARS was utilized to select the feature wavelengths. The varying trends of the variables, RMSECV and regression coefficient path for the number of sampling runs are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e12\u003c/span\u003e. The figure shows that the number of sampled variables with little or no information was removed rapidly with the number of sampling runs. Also, the 10-fold RMSECV values observed from 1 to 20 were deceased, and the lowest point was achieved at the sampling runs after 20, indicating the removal of ineffective wavelengths. After around 42 runs, the RMSECV values increased, suggesting that the wavelengths and variables containing important information for DON prediction are being removed. Thus, combining wavelengths with the lowest RMSECV values is collected for feature wavelength selection. Also, the blue patch in the figure of regression coefficient path for individual wavelength indicates the best subgroup with selected wavelengths with the lower RMSECV values. The CARS algorithm selected 43, 51 and 47 wavelengths for the germ-side, endosperm-side and combined models, respectively, as given in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. These CARS-selected wavelengths were utilized to develop PLSR and SVMR models preprocessed with the OSC\u0026thinsp;+\u0026thinsp;SNV techniques, which were identified as best for the germ-side position of corn kernels. Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e shows the DON prediction model developed using PLSR and SVMR with OSC\u0026thinsp;+\u0026thinsp;SNV with selected wavelengths. SVMR for the germ-side model was observed to provide the best prediction coefficient of determination R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e of 0.9847 and RMSEP of 0.3010. The scatter plot of the SVMR model with CARS selected wavelength for the germ-side is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e13\u003c/span\u003e. The performance of the PLSR model was lower when compared with that of SVMR in predicting DON in corn kernels.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eFeature wavelengths selected from the full spectrum (900\u0026ndash;2500nm) of corn grains using CARS and IRIV\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCorn grain position\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWavelength selection method\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNumber of wavelengths\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eWavelength (nm)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eGerm-side up\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCARS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1072.61, 1091.66, 1110.72, 1120.24, 1139.3, 1225.04, 1320.31, 1396.53, 1453.69, 1482.27, 1587.07, 1634.7, 1644.23, 1720.44, 1758.55, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09,1958.62, 1968.15, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78, 2025.31, 2082.47, 2101.52, 2111.05, 2187.27, 2215.85, 2225.37, 2263.48, 2273.01\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eIRIV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e901.12, 920.17, 967.81, 986.86, 1015.45, 1072.61, 1091.66, 1110.72, 1120.24, 1129.77, 1139.3, 1225.04, 1272.67, 1301.26, 1339.36, 1377.47, 1396.53, 1453.69, 1463.21, 1482.27, 1558.48, 1587.07, 1720.44, 1768.08, 1863.35, 1882.4, 1910.98, 1949.09, 1977.67, 2025.31, 2034.83, 2044.36, 2101.52, 2177.74, 2187.27, 2215.85, 2273.01, 2330.17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eEndosperm-side up\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCARS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e901.12, 939.23, 948.76, 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1072.61, 1091.66, 1110.72, 1301.26, 1320.31, 1358.42, 1377.47, 1406.05, 1415.58, 1444.16, 1453.69, 1463.21, 1472.74, 1482.27, 1548.96, 1558.48, 1587.07, 1768.08, 1777.61, 1853.82, 1863.35, 1872.88, 1901.46, 1910.98, 1920.51, 1949.09, 1977.67, 1987.2, 1996.73, 2006.25, 2101.52, 2111.05, 2149.16, 2177.74, 2187.27, 2215.85, 2225.37, 2273.01, 2349.23, 2358.75, 2368.28\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eIRIV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e901.12, 920.17, 939.23, 958.28, 967.81, 986.86, 996.39, 1044.03, 1063.08, 1072.61, 1091.66, 1110.72, 1158.35, 1234.57, 1263.15, 1301.26, 1358.42, 1377.47, 1406.05, 1415.58, 1444.16, 1453.69, 1463.21, 1482.27, 1491.8, 1520.38, 1539.43, 1548.96, 1558.48, 1587.07, 1768.08, 1777.61, 1825.24, 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1977.67, 1987.2, 2015.78, 2025.31, 2034.83, 2187.27, 2206.32, 2215.85, 2234.9, 2358.75, 2368.28\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eMixed (combined model)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCARS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e901.12, 929.70, 939.23, 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1044.03, 1091.66, 1110.72, 1139.3, 1301.26, 1320.31, 1329.84, 1444.16, 1453.69, 1463.21, 1472.74, 1482.27, 1558.48, 1587.07, 1720.44, 1768.08, 1777.61, 1787.13, 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09, 1958.62, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78, 2111.05, 2177.74, 2215.85, 2225.37, 2273.01, 2358.75, 2368.28\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eIRIV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e901.12, 910.65, 920.17, 939.23, 958.28, 967.81, 986.86, 996.39, 1044.03, 1072.61, 1082.13, 1091.66, 1101.19, 1110.72, 1120.24, 1129.77, 1139.3, 1148.82, 1234.57, 1301.26, 1377.47, 1396.53, 1415.58, 1444.16, 1453.69, 1463.21, 1491.8, 1558.48, 1577.54, 1587.07, 1710.92, 1720.44, 1758.55, 1768.08, 1863.35, 1910.98, 1949.09, 1987.2, 2025.31, 2053.89, 2072.94, 2101.52, 2111.05, 2139.63, 2177.74, 2273.01, 2330.17, 2358.75, 2368.28\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePrediction results of DON using CARS-selected wavelengths with OSC\u0026thinsp;+\u0026thinsp;SNV preprocessing techniques\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePosition\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e(LVs/SVs)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRMSEC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRMSECV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eRMSEP\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eGerm up\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePLSR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9530\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.5166\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9424\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5718\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9494\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5501\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVMR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e205\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9934\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.1949\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9721\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3993\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9847\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3010\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eEndosperm up\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePLSR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9364\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6049\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9262\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6518\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9290\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6317\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVMR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e206\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9755\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.3772\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9407\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5830\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9669\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4357\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eCombined\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePLSR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9244\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6555\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9169\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6877\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9200\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6834\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVMR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e203\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9628\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4610\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9417\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5758\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9645\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4543\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe IRIV algorithm collected 38, 49 and 49 wavelengths for the germ-side, endosperm-side and combined model, respectively (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). The PLSR and SVMR models were developed with the IRIV-selected wavelengths for the germ-side and endosperm-side models with the same OSC\u0026thinsp;+\u0026thinsp;SNV preprocessing techniques to eliminate bias and to assess the performance of CARS and IRIV-selected wavelengths in model training. From Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e, it can be observed that the IRIV-selected wavelengths yielded higher coefficient of determination results than CARS. The SVMR results for the germ-side model with IRIV-selected wavelengths had the highest coefficient of determination with R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e of 0.9823 and RMSEP of 0.3297 (Fig.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e14\u003c/span\u003e). The results further suggest that IRIV feature wavelength selection methods retain the effective wavelength for DON prediction. In contrast, the CARS algorithm could lose some effective wavelengths, contributing to the average model performance. Similar results were also observed when CARS and IRIV-selected wavelengths were used for model development to predict protein content in single chickpeas. (Saha et al. \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2023\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePrediction results of DON using IRIV-selected wavelengths with OSC\u0026thinsp;+\u0026thinsp;SNV preprocessing techniques\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePosition\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e(LVs/SVs)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRMSEC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRMSECV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eRMSEP\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eGerm up\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePLSR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9627\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4615\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9548\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5080\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9557\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.5236\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVMR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e234\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9943\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.1792\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9627\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.4604\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9823\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.3297\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eEndosperm up\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePLSR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9415\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.5818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9309\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6332\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9309\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6369\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVMR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e201\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9914\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.2225\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9179\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6862\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9674\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4361\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eCombined\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePLSR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9318\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6236\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9277\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6418\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9257\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.6569\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVMR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e282\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.9714\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.4062\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9503\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.5335\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9629\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.4635\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003e3.6 Discussion\u003c/h2\u003e \u003cp\u003eA study to detect DON contamination in oats and wheat using NIR hyperspectral imaging in the wavelength range between 900 and 1700 nm identified wavelengths in the 1200 and 1400 nm region as the most significant wavelengths to predict DON contamination (Delwiche et al. \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Teixido-Orries et al. \u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). The CARS and IRIV selected feature wavelengths 1225.04, 1234.57, 1272.67, 1396.53, 1406.05, 1415.58, 1444.16, and 1453.69 nm to predict DON in corn kernels observed in this current study are very similar to well established DON detection wavelengths 1200 and 1400 nm. Another study reported 1430 nm as a significant wavelength to detect DON in wheat, similar to the wavelengths in the 1400 nm range reported in this study (Shen et al. \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). The common phenomenon observed in this study and previously reported studies is that the mean spectra did not provide any clear differences at the selected significant wavelengths, and so in this study, further data processing and chemometrics tools are needed to predict the DON in grains (He et al. \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Teixido-Orries et al. \u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). The NIR study focused on DON detection commonly used 900\u0026ndash;1700 nm range camera (Femenias et al. \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Femenias et al. \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2021b\u003c/span\u003e; Femenias et al. \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2022b\u003c/span\u003e), and major comparisons of DON-specific wavelengths can be made in this NIR region. Very little exploration was attempted in the SWIR region (Vicens-Sans et al. \u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). A study using FT-NIR spectroscopy found 1880\u0026ndash;2070 nm spectral region as a DON-specific wavelength in wheat, which is comparable to 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09, 1958.62, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78 nm wavelengths reported in this study (Peiris et al. \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2009\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eA unique sample preparation technique was followed in this study by utilizing commercial DON for sample preparation instead of artificially inoculating the grains with fungal species to produce mycotoxins (Femenias et al. \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2022a\u003c/span\u003e), which will lead to quantification of DON and not the fungal infection. Many research studies focused on DON detection based on classification; only a few studies have focused on the quantification of DON (Femenias et al. \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2020\u003c/span\u003e), this indicates the DON quantification studies using NIR hyperspectral imaging is in its development stage and further studies are required to utilize the potential of NIR hyperspectral imaging system completely (Nadimi et al. \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). A recent study on DON quantification in oats unground samples achieved the highest R\u003csup\u003e2\u003c/sup\u003e value of 0.75 compared to the highest R\u003csup\u003e2\u003c/sup\u003e value of 0.9823 obtained in this study (Teixido-Orries et al. \u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e2023\u003c/span\u003e); the lower R\u003csup\u003e2\u003c/sup\u003e value can be attributed to using12 wavelengths to build models compared to 38 to 51 wavelengths selected using CARS and IRIV used to build prediction models in this study. Another study on DON quantification in wheat kernels provided the highest R\u003csup\u003e2\u003c/sup\u003e value of 0.88 on SNV preprocessed data, similar to the current study providing the highest R\u003csup\u003e2\u003c/sup\u003e value with SNV preprocessed data (Femenias et al. \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2021a\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThe proposed NIR-based DON prediction tool can detect DON in a few minutes without disturbing the samples, without using any chemical reagents, without a need for a professional to operate the equipment and in a rapid manner compared to traditional analytical techniques like UPHLC and ELISA-based methods. While NIR-HSI offers strong potential for industrial applications due to its rapid and non-destructive capabilities, several challenges exist for scaling up to industrial deployment. These include the high initial cost of hyperspectral systems, robust calibration models that can accommodate sample diversity and environmental variation (e.g., lighting, temperature, motion blur), and the requirement for integration with automated conveyors and real-time processing hardware. Maintaining spectral accuracy under high-throughput conditions also requires careful optical and mechanical alignment. These challenges are actively being addressed in recent studies, and with technological advancements in sensor miniaturization and embedded computing, industrial deployment is increasingly feasible.\u003c/p\u003e \u003cp\u003eFor regulatory acceptance, additional validation studies would be required following standard guidelines such as those provided by Codex Alimentarius or international bodies like AOAC and ISO. These would include evaluating method accuracy, precision, specificity, linearity, limit of detection (LOD), limit of quantification (LOQ), reproducibility across different instruments and operators, and robustness to environmental variables such as temperature and humidity. Moreover, inter-laboratory studies and performance comparisons with established reference methods (e.g., LC-MS/MS) would be critical for demonstrating equivalency. While our current study establishes feasibility and performance under controlled conditions, future work will focus on systematic validation to support regulatory alignment. This study focused on single-kernel imaging; future studies should focus on bulk imaging and grounded samples to detect DON contamination at the grain storage and processor levels. Different types of mycotoxins can co-occur, and future studies also focus on detecting multiple mycotoxins in a single scan of an NIR hyperspectral imaging system.\u003c/p\u003e \u003c/div\u003e"},{"header":"4. Conclusion","content":"\u003cp\u003eSWIR-HSI proves to be a promising technique for detecting DON in individual corn kernels and, when combined with chemometric tools and feature selection techniques, can significantly reduce the number of wavelengths without compromising the model performance. Also, the effect of the different orientations or positions of corn kernels on the prediction of DON was analyzed. It was identified that the germ-side of the corn kernels is the optimal position of corn kernels for hyperspectral imaging for better model performance and DON prediction. PLSR and SVMR with SNV, OSC\u0026thinsp;+\u0026thinsp;SNV and MSC preprocessing methods yielded a better coefficient of determination for DON prediction when using the entire spectrum. CARS and IRIV enhanced model training and quantification speed with a better coefficient of determination. SVMR on IRIV-selected wavelengths provided the highest R\u003csup\u003e2\u003c/sup\u003e \u003csub\u003ep\u003c/sub\u003e of 0.9823 and RMSE prediction of 0.3297. Future studies should focus on the quantification of DON in field samples with other co-produced secondary metabolites to enhance the sensitivity and specificity of the HSI system for real-time inspection in processing lines.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors thank the Ontario Ministry of Agriculture, Food and Rural Affairs (OMAFRA) for providing the healthy and FHB-infected corn grains for this study. The authors also thank the Barrett Family Foundation, Canada, for funding this study. We want to thank the NSERC Applied Research Tools and Instruments (ARTI) grant for the NIR hyperspectral imaging system at Lethbridge College and Headwall Photonics for its in-kind contribution to the NIR hyperspectral imaging system at the Lethbridge College.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was supported by Barrett Family Foundation, Canada.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRathna Priya Thangaraj Sundaramurthy\u003c/strong\u003e – Conceptualization; methodology; data collection; data analysis; manuscript writing. \u003cstrong\u003eThiruppathi\u003c/strong\u003e \u003cstrong\u003eSenthilkumar\u0026nbsp;\u003c/strong\u003e– Supervision; data analysis; writing- review and editing; reviewing manuscript. \u003cstrong\u003eChandra B. Singh\u003c/strong\u003e – Resources; writing – review and editing; reviewing manuscript.\u003cstrong\u003e\u0026nbsp;Annamalai Manickavasagan\u0026nbsp;\u003c/strong\u003e– Supervision; resources; writing – review and editing; reviewing manuscript.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors have no conflicts of interest to declare that are relevant to the content of this article.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical Approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to publish\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThere is no competing Interest\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe dataset generated during this study and codes are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n \u003cli\u003eAbdi H (2003) Partial Least Square Regression PLS-Regression. Encyclopedia for research methods for the social sciences 792\u0026ndash;795\u003c/li\u003e\n \u003cli\u003eAlisaac E, Behmann J, Rathgeb A, Karlovsky P, Dehne HW, Mahlein AK (2019) Assessment of fusarium infection and mycotoxin contamination of wheat kernels and flour using hyperspectral imaging. Toxins (Basel) 11. https://doi.org/10.3390/toxins11100556\u003c/li\u003e\n \u003cli\u003eBerthiller F, Crews C, Dall\u0026rsquo;Asta C, Saeger S De, Haesaert G, Karlovsky P, Oswald IP, Seefelder W, Speijers G, Stroka J (2013) Masked mycotoxins: A review. Mol Nutr Food Res 57:165\u0026ndash;186\u003c/li\u003e\n \u003cli\u003eBrumley WC, Trucksess MW, Adler SH, Cohen CK, White KD, Sphon JA (1985) Food Chem\u003c/li\u003e\n \u003cli\u003eCastillo M\u0026Aacute;, Montes R, Navarro A, Segarra R, Cuesta G, Hern\u0026aacute;ndez E (2008) Occurrence of deoxynivalenol and nivalenol in Spanish corn-based food products. Journal of Food Composition and Analysis 21:423\u0026ndash;427. https://doi.org/10.1016/j.jfca.2008.03.009\u003c/li\u003e\n \u003cli\u003eCruz-Tirado JP, Amigo JM, Barbin DF (2022) Determination of protein content in single black fly soldier (Hermetia illucens L.) larvae by near infrared hyperspectral imaging (NIR-HSI) and chemometrics. Food Control 143. https://doi.org/10.1016/j.foodcont.2022.109266\u003c/li\u003e\n \u003cli\u003eDeiss L, Margenot AJ, Culman SW, Demyan MS (2020) Tuning support vector machines regression models improves prediction accuracy of soil properties in MIR spectroscopy. Geoderma 365. https://doi.org/10.1016/j.geoderma.2020.114227\u003c/li\u003e\n \u003cli\u003eDelwiche SR, Rodriguez IT, Rausch SR, Graybosch RA (2019) Estimating percentages of fusarium-damaged kernels in hard wheat by near-infrared hyperspectral imaging. J Cereal Sci 87:18\u0026ndash;24. https://doi.org/10.1016/j.jcs.2019.02.008\u003c/li\u003e\n \u003cli\u003eEFSA (2013) Deoxynivalenol in food and feed: occurrence and exposure. EFSA Journal 11. https://doi.org/10.2903/j.efsa.2013.3379\u003c/li\u003e\n \u003cli\u003eFAOSTAT (2023) Maize (Corn) production indices . https://www.fao.org/faostat/en/#data/QCL. Accessed 12 Feb 2025\u003c/li\u003e\n \u003cli\u003eFemenias A, Bainotti MB, Gatius F, Ramos AJ, Mar\u0026iacute;n S (2021a) Standardization of near infrared hyperspectral imaging for wheat single kernel sorting according to deoxynivalenol level. Food Research International 139. https://doi.org/10.1016/j.foodres.2020.109925\u003c/li\u003e\n \u003cli\u003eFemenias A, Gatius F, Ramos AJ, Sanchis V, Mar\u0026iacute;n S (2020) Standardisation of near infrared hyperspectral imaging for quantification and classification of DON contaminated wheat samples. Food Control 111. https://doi.org/10.1016/j.foodcont.2019.107074\u003c/li\u003e\n \u003cli\u003eFemenias A, Gatius F, Ramos AJ, Sanchis V, Mar\u0026iacute;n S (2021b) Near-infrared hyperspectral imaging for deoxynivalenol and ergosterol estimation in wheat samples. Food Chem 341. https://doi.org/10.1016/j.foodchem.2020.128206\u003c/li\u003e\n \u003cli\u003eFemenias A, Gatius F, Ramos AJ, Teixido-Orries I, Mar\u0026iacute;n S (2022a) Hyperspectral imaging for the classification of individual cereal kernels according to fungal and mycotoxins contamination: A review. Food Research International 155\u003c/li\u003e\n \u003cli\u003eFemenias A, Llorens-Serentill E, Ramos AJ, Sanchis V, Mar\u0026iacute;n S (2022b) Near-infrared hyperspectral imaging evaluation of Fusarium damage and DON in single wheat kernels. Food Control 142. https://doi.org/10.1016/j.foodcont.2022.109239\u003c/li\u003e\n \u003cli\u003eFeng YZ, Sun DW (2012) Application of Hyperspectral Imaging in Food Safety Inspection and Control: A Review. Crit Rev Food Sci Nutr 52:1039\u0026ndash;1058\u003c/li\u003e\n \u003cli\u003eFood and Agriculture Organization of the United Nations (FAO) (2015) 38th Session of the Codex Alimentarius Commission. Geneva, Switzerland. https://www.fao.org/newsroom/detail/Codex-Alimentarius-Commission-6-11-July-2015/ar. Accessed 12 Feb 2025\u003c/li\u003e\n \u003cli\u003eHe X, Zhao T, Shen F, Liu Q, Fang Y, Hu Q (2021) Online detection of naturally DON contaminated wheat grains from China using Vis-NIR spectroscopy and computer vision. Biosyst Eng 201:1\u0026ndash;10. https://doi.org/10.1016/j.biosystemseng.2020.11.001\u003c/li\u003e\n \u003cli\u003eJiang L, Zhu B, Tao Y (2010) Hyperspectral Image Classification Methods. In: Hyperspectral Imaging for Food Quality Analysis and Control. Elsevier, pp 79\u0026ndash;98\u003c/li\u003e\n \u003cli\u003eKautzman ME, Wickstrom ML, Scott TA (2015) The use of near infrared transmittance kernel sorting technology to salvage high quality grain from grain downgraded due to Fusarium damage. Animal Nutrition 1:41\u0026ndash;46. https://doi.org/10.1016/j.aninu.2015.02.007\u003c/li\u003e\n \u003cli\u003eLi J, Wang Q, Xu L, Tian X, Xia Y, Fan S (2019) Comparison and Optimization of Models for Determination of Sugar Content in Pear by Portable Vis-NIR Spectroscopy Coupled with Wavelength Selection Algorithm. Food Anal Methods 12:12\u0026ndash;22. https://doi.org/10.1007/s12161-018-1326-7\u003c/li\u003e\n \u003cli\u003eMarzec-Schmidt K, B\u0026ouml;rjesson T, Suproniene S, Jędryczka M, Janavičienė S, G\u0026oacute;ral T, Karlsson I, Kochiieru Y, Ochodzki P, Mankevičienė A, Piikki K (2021) Modelling the effects of weather conditions on cereal grain contamination with deoxynivalenol in the baltic sea region. Toxins (Basel) 13. https://doi.org/10.3390/toxins13110737\u003c/li\u003e\n \u003cli\u003eMcMullin D, Mizaikoff B, Krska R (2015) Advancements in IR spectroscopic approaches for the determination of fungal derived contaminations in food crops. Anal Bioanal Chem 407:653\u0026ndash;660. https://doi.org/10.1007/s00216-014-8145-5\u003c/li\u003e\n \u003cli\u003eMehmood T, S\u0026aelig;b\u0026oslash; S, Liland KH (2020) Comparison of variable selection methods in partial least squares regression. J Chemom 34. https://doi.org/10.1002/cem.3226\u003c/li\u003e\n \u003cli\u003eMunkvold GP, Arias S, Taschl I, Gruber-Dorninger C (2018) Mycotoxins in corn: Occurrence, impacts, and management. In: Corn: Chemistry and Technology, 3rd Edition. Elsevier, pp 235\u0026ndash;287\u003c/li\u003e\n \u003cli\u003eNadimi M, Brown JM, Morrison J, Paliwal J (2021) Examination of wheat kernels for the presence of Fusarium damage and mycotoxins using near-infrared hyperspectral imaging. Measurement: Food 4. https://doi.org/10.1016/j.meafoo.2021.100011\u003c/li\u003e\n \u003cli\u003eParrag V, Gillay Z, Kov\u0026aacute;cs Z, Zitek A, B\u0026ouml;hm K, Hinterstoisser B, Krska R, Sulyok M, Felf\u0026ouml;ldi J, Firtha F, Baranyai L (2020) Application of hyperspectral imaging to detect toxigenic Fusarium infection on cornmeal. Progress in Agricultural Engineering Sciences 16:51\u0026ndash;60. https://doi.org/10.1556/446.2020.00009\u003c/li\u003e\n \u003cli\u003ePeiris KHS, Pumphrey MO, Dong Y, Maghirang EB, Berzonsky W, Dowell FE (2010) Near-infrared spectroscopic method for identification of Fusarium head blight damage and prediction of deoxynivalenol in single wheat kernels. Cereal Chem 87:511\u0026ndash;517. https://doi.org/10.1094/CCHEM-01-10-0006\u003c/li\u003e\n \u003cli\u003ePeiris KHS, Pumphrey MO, Dowell FE (2009) NIR absorbance characteristics of deoxynivalenol and of sound and fusarium-damaged wheat kernels. J Near Infrared Spectrosc 17:213\u0026ndash;221. https://doi.org/10.1255/jnirs.846\u003c/li\u003e\n \u003cli\u003ePrieto-Sim\u0026oacute;n B, Noguer T, Camp\u0026agrave;s M (2007) Emerging biotools for assessment of mycotoxins in the past decade. TrAC - Trends in Analytical Chemistry 26:689\u0026ndash;702. https://doi.org/10.1016/j.trac.2007.05.012\u003c/li\u003e\n \u003cli\u003ePriya TSR, Manickavasagan A (2023) Evaluation of treatment methods for spiking deoxynivalenol (DON) in single corn kernels. Canadian Journal of Plant Science 103:450\u0026ndash;462. https://doi.org/10.1139/cjps-2022-0259\u003c/li\u003e\n \u003cli\u003eRathna Priya TS, Manickavasagan A (2021) Characterising corn grain using infrared imaging and spectroscopic techniques: a review. Journal of Food Measurement and Characterization 15:3234\u0026ndash;3249\u003c/li\u003e\n \u003cli\u003eRavikanth L, Jayas DS, White NDG, Fields PG, Sun DW (2017) Extraction of Spectral Information from Hyperspectral Data and Application of Hyperspectral Imaging for Food and Agricultural Products. Food Bioproc Tech 10\u003c/li\u003e\n \u003cli\u003eRegulatory Guidance (RG-8). Government of Canada. (2017) Mycotoxins in Livestock Feed,Canadian Food Inspection Agency. https://inspection.canada.ca/en/animal-health/livestock-feeds/regulatory-guidance/rg-8#c1. Accessed 12 Feb 2025\u003c/li\u003e\n \u003cli\u003eSaha D, Senthilkumar T, Sharma S, Singh CB, Manickavasagan A (2023) Application of near-infrared hyperspectral imaging coupled with chemometrics for rapid and non-destructive prediction of protein content in single chickpea seed. Journal of Food Composition and Analysis 115:104938. https://doi.org/10.1016/j.jfca.2022.104938\u003c/li\u003e\n \u003cli\u003eSchaafsma AW, Fr\u0026eacute;geau-Reid J, Phibbs T Distribution of deoxynivalenol in Gibberella-infected food-grade corn kernels\u003c/li\u003e\n \u003cli\u003eSchollenberger M, Suchy S, Jara HT, Drochner W, M\u0026uuml;ller H-M (1999) A survey of Fusarium toxins in cereal-based foods marketed in an area of southwest Germany\u003c/li\u003e\n \u003cli\u003eSenthilkumar T, Jayas DS, White NDG, Fields PG, Gr\u0026auml;fenhan T (2016) Near-Infrared (NIR) hyperspectral imaging: theory and applications to detect fungal infection and mycotoxin contamination in food products. Indian Journal of Entomology 78:91. https://doi.org/10.5958/0974-8172.2016.00029.8\u003c/li\u003e\n \u003cli\u003eSharma S, Pradhan R, Manickavasagan A, Thimmanagari M, Dutta A (2020) Application of analytical pyrolysis to gain insights into proteins of condensed corn distillers solubles from selective milling technology. Food and Bioproducts Processing 124:354\u0026ndash;368. https://doi.org/10.1016/j.fbp.2020.09.011\u003c/li\u003e\n \u003cli\u003eSharma S, Pradhan R, Manickavasagan A, Thimmanagari M, Dutta A (2021) Evaluation of nitrogenous pyrolysates by Py\u0026ndash;GC/MS for impacts of different proteolytic enzymes on corn distillers solubles. Food and Bioproducts Processing 127:225\u0026ndash;243. https://doi.org/10.1016/j.fbp.2021.03.004\u003c/li\u003e\n \u003cli\u003eShen G, Cao Y, Yin X, Dong F, Xu J, Shi J, Lee YW (2022) Rapid and nondestructive quantification of deoxynivalenol in individual wheat kernels using near-infrared hyperspectral imaging and chemometrics. Food Control 131. https://doi.org/10.1016/j.foodcont.2021.108420\u003c/li\u003e\n \u003cli\u003eShi D, Hang J, Neufeld J, Zhao S, House JD (2022) Estimation of crude protein and amino acid contents in whole, ground and defatted ground soybeans by different types of near-infrared (NIR) reflectance spectroscopy. Journal of Food Composition and Analysis 111. https://doi.org/10.1016/j.jfca.2022.104601\u003c/li\u003e\n \u003cli\u003eShreve B, TN, \u0026amp; WM (2006) National forage testing association reference method: dry matter by oven drying for 3 hours at 105 C. NFTA Reference Methods National Forage Testing Association, Omaha, NB (2006)\u003c/li\u003e\n \u003cli\u003eSun D-W (2010) Hyperspectral imaging for food quality analysis and control. Academic Press, an imprint of Elsevier\u003c/li\u003e\n \u003cli\u003eTeixido-Orries I, Molino F, Femenias A, Ramos AJ, Mar\u0026iacute;n S (2023) Quantification and classification of deoxynivalenol-contaminated oat samples by near-infrared hyperspectral imaging. Food Chem 417. https://doi.org/10.1016/j.foodchem.2023.135924\u003c/li\u003e\n \u003cli\u003eTekle S, Mage I, Segtnan VH, Bjornstad A (2015) Near-infrared hyperspectral imaging of Fusarium-damaged oats (Avena sativa L.). Cereal Chem 92:73\u0026ndash;80. https://doi.org/10.1094/CCHEM-04-14-0074-R\u003c/li\u003e\n \u003cli\u003eVapnik VN (2000) The Nature of Statistical Learning Theory. Springer New York, New York, NY\u003c/li\u003e\n \u003cli\u003eVicens-Sans A, Pascari X, Molino F, Ramos AJ, Mar\u0026iacute;n S (2024) Near infrared hyperspectral imaging as a sorting tool for deoxynivalenol reduction in wheat batches. Food Research International 178. https://doi.org/10.1016/j.foodres.2024.113984\u003c/li\u003e\n \u003cli\u003eWang S, Sun J, Fu L, Xu M, Tang N, Cao Y, Yao K, Jing J (2022) Identification of red jujube varieties based on hyperspectral imaging technology combined with CARS-IRIV and SSA-SVM. J Food Process Eng 45. https://doi.org/10.1111/jfpe.14137\u003c/li\u003e\n \u003cli\u003eWu Q, Kuča K, Humpf HU, Kl\u0026iacute;mov\u0026aacute; B, Cramer B (2017) Fate of deoxynivalenol and deoxynivalenol-3-glucoside during cereal-based thermal food processing: a review study. Mycotoxin Res 33:79\u0026ndash;91\u003c/li\u003e\n \u003cli\u003eXing F, Yao H, Liu Y, Dai X, Brown RL, Bhatnagar D (2019) Recent developments and applications of hyperspectral imaging for rapid detection of mycotoxins and mycotoxigenic fungi in food products. Crit Rev Food Sci Nutr 59:173\u0026ndash;180\u003c/li\u003e\n \u003cli\u003eXu H, Ren J, Lin J, Mao S, Xu Z, Chen Z, Zhao J, Wu Y, Xu N, Wang P (2023) The impact of high-quality data on the assessment results of visible/near-infrared hyperspectral imaging and development direction in the food fields: a review. Journal of Food Measurement and Characterization 17:2988\u0026ndash;3004\u003c/li\u003e\n \u003cli\u003eZhang J, Ma Y, Liu G, Fan N, Li Y, Sun Y (2022) Rapid evaluation of texture parameters of Tan mutton using hyperspectral imaging with optimization algorithms. Food Control 135. https://doi.org/10.1016/j.foodcont.2022.108815\u003c/li\u003e\n \u003cli\u003eZhao T, Chen M, Jiang X, Shen F, He X, Fang Y, Liu Q, Hu Q (2020) Integration of spectra and image features of Vis/NIR hyperspectral imaging for prediction of deoxynivalenol contamination in whole wheat flour. Infrared Phys Technol 109. https://doi.org/10.1016/j.infrared.2020.103426\u003c/li\u003e\n \u003cli\u003eZhong H, Wang J, Jia H, Mu Y, Lv S (2019) Vector field-based support vector regression for building energy consumption prediction. Appl Energy 242:403\u0026ndash;414. https://doi.org/10.1016/j.apenergy.2019.03.078\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003eTable 1. Prediction results of combined model (both germ-side and endosperm-side) to detect DON in individual corn grains using full spectrum\u003c/strong\u003e\u003c/p\u003e\n\u003cdiv align=\"center\"\u003e\n \u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"879\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eModel\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePre-processing\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e(LVs/SVs)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSECV\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEP\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePLSR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eNone\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8239\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.0037\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.8162\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e1.0255\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.8382\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.9682\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWeighted LS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9015\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7504\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.8934\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7811\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.8889\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.8029\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9099\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7182\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9037\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7426\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9112\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7207\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eEPO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9276\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e3.018\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9189\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e3.0251\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9231\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e3.0063\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGap \u0026nbsp;1st derivative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8988\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7611\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.8912\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7894\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7622\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGLS weighting\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9313\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e3.0148\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9234\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e3.0254\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9251\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e3.0045\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMean centering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9112\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.4143\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.8957\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e1.7632\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.8854\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.6529\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC (mean)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9288\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6381\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9182\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.6844\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9214\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6766\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9281\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6416\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9184\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.6838\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9211\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6822\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003ePQN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.911\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7133\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9008\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7534\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9146\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7124\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8466\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9371\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.8264\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9974\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.8557\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.9186\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.929\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6375\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9183\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.6837\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.921\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6784\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWhittaker Filter\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8998\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7571\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.893\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7828\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9039\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7498\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.922\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6682\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9139\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7019\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9158\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6991\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.929\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6375\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9184\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.6836\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.921\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6784\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9294\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6354\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9196\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.6784\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9211\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6787\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSVMR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eNone\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e419\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9812\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3271\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9309\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.6269\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9649\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4563\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWeighted LS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e443\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9832\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3106\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9551\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.5058\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9721\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4089\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e375\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9823\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3181\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.961\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4707\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9746\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3889\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eEPO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e483\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9829\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3115\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9695\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4186\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9798\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3434\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGap \u0026nbsp;1st derivative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e554\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8053\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.0721\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.7908\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e1.1082\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.822\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.0687\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGLS weighting\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e542\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9702\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4139\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9605\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4748\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9669\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4465\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMean centering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e419\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9812\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3271\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9309\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.6269\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9649\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4564\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC (mean)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e366\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9805\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3346\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9617\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4669\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9718\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4101\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e406\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9777\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3565\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9371\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.5978\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9719\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4076\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003ePQN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e429\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.3891\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.8764\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.3745\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e1.8951\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4054\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.8865\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e456\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9672\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4328\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9113\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7098\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9459\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5657\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e500\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9947\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.1738\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9674\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4298\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9851\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2959\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWhittaker filter\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e370\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9817\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3237\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9651\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4464\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9751\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3837\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e511\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9871\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.2725\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.968\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4263\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9791\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3525\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC +SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e500\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9947\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.1738\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9674\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4298\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9851\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2959\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e497\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9913\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.2242\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 105px;\"\u003e\n \u003cp\u003e0.9585\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.4855\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9818\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3289\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eLS \u0026ndash; Least squares; PLSR \u0026ndash; Partial least square regression; SVMR \u0026ndash; Support vector machine regression; EPO -external parameter orthogonalization; GLS \u0026ndash; generalized least squares; MSC- multiplicative scatter correction; OSC -\u0026nbsp;orthogonal signal correction; PQN -probabilistic quotient normalisation; Sav-Gol - Savitsky \u0026ndash; Golay smoothing; SNV \u0026ndash; standard normal variate; R\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec,\u0026nbsp;\u003c/sub\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv,\u0026nbsp;\u003c/sub\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u0026ndash; coefficient of determination of calibration, cross-validation, and prediction; RMSEC, \u0026nbsp;RMSECV, RMSEP \u0026ndash; root mean square error of calibration, cross-validation and prediction.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2. Prediction results of the germ-side model to detect DON in individual corn grains using full spectrum\u003c/strong\u003e\u003c/p\u003e\n\u003cdiv align=\"center\"\u003e\n \u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"841\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eModel\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePre-processing\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e(LVs/SVs)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSECV\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEP\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePLSR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eNone\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9151\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7024\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8994\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7646\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9359\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6402\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWeighted LS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9181\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6782\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9068\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7236\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9359\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6469\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9243\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6518\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9137\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6961\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9482\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5671\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eEPO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9323\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e3.0903\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9213\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e3.0918\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9478\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e2.9663\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGap \u0026nbsp;1st derivative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9168\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6835\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9052\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7294\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9453\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5911\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGLS weighting\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9298\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e3.0925\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9183\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e3.0946\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9487\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e2.9587\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMean centering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8710\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e3.1455\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8557\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e3.1577\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.8959\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e2.9937\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC (mean)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9385\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5872\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9252\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6484\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9521\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5467\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9413\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5740\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9221\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6620\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9570\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5139\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003ePQN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9002\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7484\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8835\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.8087\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9376\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6332\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8598\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.8873\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8463\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9292\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9079\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7844\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9337\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6102\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9228\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6585\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9481\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5678\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWhittaker Filter\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9255\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6468\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9146\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6926\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9215\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7010\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9248\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6498\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9136\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6965\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9396\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6111\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9337\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6102\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9228\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6585\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9481\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5678\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9444\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5586\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9265\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6426\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9531\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5369\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSVMR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eNone\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e219\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9520\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5276\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9222\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6649\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9317\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6484\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWeighted LS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e160\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9844\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2984\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9619\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4654\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9740\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3983\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e168\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9836\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3061\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9637\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4539\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9758\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3872\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eEPO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e168\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9927\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2041\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9698\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4131\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9823\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3263\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGap \u0026nbsp;1st derivative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e120\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.7832\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.1338\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7694\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.1684\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.7837\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.1749\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGLS weighting\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e192\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9762\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3705\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9646\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4484\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9687\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4404\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMean centering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e219\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9519\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5276\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9222\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6649\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9317\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6484\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC (mean)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e173\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9847\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2944\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9695\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4151\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9772\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3726\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e187\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9786\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3491\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9465\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.5503\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9729\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4069\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003ePQN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e214\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.3460\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.9387\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.3266\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.9637\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.4122\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.9308\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e225\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9295\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6408\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8941\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7769\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9099\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7514\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e239\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9955\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.1595\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9742\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3817\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9854\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2953\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWhittaker filter\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e172\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9817\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3244\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9658\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4412\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9787\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3598\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e244\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9903\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2347\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9733\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3891\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9803\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3443\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC +SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e239\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9955\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.1595\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9742\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.3817\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9855\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2953\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e169\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9925\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2057\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9627\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4593\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9818\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3300\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 3. Prediction results of the endosperm-side model to detect DON in individual corn grains using full spectrum\u003c/strong\u003e\u003c/p\u003e\n\u003cdiv align=\"center\"\u003e\n \u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"832\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eModel\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePre-processing\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e(LVs/SVs)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSECV\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEP\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePLSR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eNone\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.7451\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.2072\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7312\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.2397\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.8239\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e1.0112\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWeighted LS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8771\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.8382\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8440\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9446\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9075\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.7279\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9060\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7331\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8874\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.8028\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9139\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.7060\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eEPO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9192\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e2.9621\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8998\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e2.9768\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9253\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e2.8997\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGap \u0026nbsp;1st derivative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9058\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.7355\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8894\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7971\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9119\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.7164\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGLS weighting\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9244\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e2.9468\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9074\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e2.9613\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9194\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e2.9385\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMean centering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9053\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e2.9754\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8840\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e3.0075\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9109\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e2.9257\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC (mean)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9238\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6616\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9106\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7166\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9152\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.6994\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9246\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6583\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9053\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7379\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9188\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.6869\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003ePQN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9189\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6822\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8980\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7656\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9184\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.7027\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8083\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.0493\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7941\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.0885\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.8227\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e1.0025\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9308\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6305\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9146\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7006\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9208\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.6825\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWhittaker Filter\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.8604\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.8935\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8440\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9445\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9031\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.7496\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9298\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6348\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9047\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7416\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9186\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.6858\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9307\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.6305\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9146\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7006\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9208\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.6825\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9374\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.5994\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9179\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6874\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9231\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.6718\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSVMR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eNone\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e226\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9824\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3209\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8995\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7648\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9652\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.4490\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWeighted LS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e236\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3477\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9338\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6179\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9650\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.4476\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e268\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9791\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3515\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9455\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.5621\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9728\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.4022\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eEPO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e257\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9915\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.2218\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9595\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.4834\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9859\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.2853\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGAP \u0026nbsp;1st derivative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e260\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.7480\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.2216\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.7263\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.2687\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.8092\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e1.0971\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eGLS weighting\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e212\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9719\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4071\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9568\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.5014\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9705\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.4098\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMean centering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e226\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9824\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3209\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8995\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7648\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9652\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.4490\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC (mean)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e199\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9783\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3558\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9482\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.5476\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9752\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.3786\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e215\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9742\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3874\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9074\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.7311\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9669\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.4394\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003ePQN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e226\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.3214\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e1.9821\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.3116\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e1.9967\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.3072\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e1.9841\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSav-Gol Smoothing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e240\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9695\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4225\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.8721\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.8607\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9505\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.5321\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eSNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e270\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9999\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.0099\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9540\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.5155\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9831\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.3108\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eWhittaker filter\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e255\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9775\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.3620\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9496\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.5411\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9766\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.3658\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eDetrend + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e194\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9980\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.1072\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9557\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.5048\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9859\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.2821\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eMSC +SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e270\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9999\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.0099\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9540\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.5155\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9831\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.3108\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 165px;\"\u003e\n \u003cp\u003eOSC + SNV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 83px;\"\u003e\n \u003cp\u003e205\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 93px;\"\u003e\n \u003cp\u003e0.9637\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 76px;\"\u003e\n \u003cp\u003e0.4593\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.9238\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0.6636\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.9629\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.4605\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eTable 4. Feature wavelengths selected from the full spectrum (900 \u0026ndash; 2500nm) of corn grains using CARS and IRIV\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eCorn grain position\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eWavelength selection method\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNumber of wavelengths\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 529px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eWavelength (nm)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003eGerm-side up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eCARS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 529px;\"\u003e\n \u003cp\u003e958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1072.61, 1091.66, 1110.72, 1120.24, 1139.3, 1225.04, 1320.31, 1396.53, 1453.69, 1482.27, 1587.07, 1634.7, 1644.23, 1720.44, 1758.55, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09,1958.62, 1968.15, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78, 2025.31, 2082.47, 2101.52, 2111.05, 2187.27, 2215.85, 2225.37, 2263.48, 2273.01\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eIRIV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 529px;\"\u003e\n \u003cp\u003e901.12, 920.17, 967.81, 986.86, 1015.45, 1072.61, 1091.66, 1110.72, 1120.24, 1129.77, 1139.3, 1225.04, 1272.67, 1301.26, 1339.36, 1377.47, 1396.53, 1453.69, 1463.21, 1482.27, 1558.48, 1587.07, 1720.44, 1768.08, 1863.35, 1882.4, 1910.98, 1949.09, 1977.67, 2025.31, 2034.83, 2044.36, 2101.52, 2177.74, 2187.27, 2215.85, 2273.01, 2330.17\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003eEndosperm-side up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eCARS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e51\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 529px;\"\u003e\n \u003cp\u003e901.12, 939.23, 948.76, 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1072.61, 1091.66, 1110.72, 1301.26, 1320.31, 1358.42, 1377.47, 1406.05, 1415.58, 1444.16, 1453.69, 1463.21, 1472.74, 1482.27, 1548.96, 1558.48, 1587.07, 1768.08, 1777.61, 1853.82, 1863.35, 1872.88, 1901.46, 1910.98, 1920.51, 1949.09, 1977.67, 1987.2, 1996.73, 2006.25, 2101.52, 2111.05, 2149.16, 2177.74, 2187.27, 2215.85, 2225.37, 2273.01, 2349.23, 2358.75, 2368.28\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eIRIV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e49\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 529px;\"\u003e\n \u003cp\u003e901.12, 920.17, 939.23, 958.28, 967.81, 986.86, 996.39, 1044.03, 1063.08, 1072.61, 1091.66, 1110.72, 1158.35, 1234.57, 1263.15, 1301.26, 1358.42, 1377.47, 1406.05, 1415.58, 1444.16, 1453.69, 1463.21, 1482.27, 1491.8, 1520.38, 1539.43, 1548.96, 1558.48, 1587.07, 1768.08, 1777.61, 1825.24, 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1977.67, 1987.2, 2015.78, 2025.31, 2034.83, 2187.27, 2206.32, 2215.85, 2234.9, 2358.75, 2368.28\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003eMixed (combined model)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eCARS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e47\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 529px;\"\u003e\n \u003cp\u003e\u0026nbsp;901.12, 929.70, 939.23, 958.28, 967.81, 977.34, 986.86, 996.39, 1005.92, 1015.45, 1044.03, 1091.66, 1110.72, 1139.3, 1301.26, 1320.31, 1329.84, 1444.16, 1453.69, 1463.21, 1472.74, 1482.27, 1558.48, 1587.07, 1720.44, 1768.08, 1777.61, 1787.13, 1863.35, 1891.93, 1901.46, 1910.98, 1920.51, 1949.09, 1958.62, 1977.67, 1987.2, 1996.73, 2006.25, 2015.78, 2111.05, 2177.74, 2215.85, 2225.37, 2273.01, 2358.75, 2368.28\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eIRIV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e49\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 529px;\"\u003e\n \u003cp\u003e901.12, 910.65, 920.17, 939.23, 958.28, 967.81, 986.86, 996.39, 1044.03, 1072.61, 1082.13, 1091.66, 1101.19, 1110.72, 1120.24, 1129.77, 1139.3, 1148.82, 1234.57, 1301.26, 1377.47, 1396.53, 1415.58, 1444.16, 1453.69, 1463.21, 1491.8, 1558.48, 1577.54, 1587.07, 1710.92, 1720.44, 1758.55, 1768.08, 1863.35, 1910.98, 1949.09, 1987.2, 2025.31, 2053.89, 2072.94, 2101.52, 2111.05, 2139.63, 2177.74, 2273.01, 2330.17, 2358.75, 2368.28\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eTable 5. Prediction results of DON using CARS-selected wavelengths with OSC + SNV preprocessing techniques\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"872\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 108px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePosition\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eModel\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e(LVs/SVs)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSECV\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEP\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 108px;\"\u003e\n \u003cp\u003eGerm up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003ePLSR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9530\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.5166\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9424\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.5718\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9494\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.5501\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003eSVMR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e205\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9934\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.1949\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9721\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.3993\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9847\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.3010\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 108px;\"\u003e\n \u003cp\u003eEndosperm up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003ePLSR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9364\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.6049\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9262\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.6518\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9290\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.6317\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003eSVMR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e206\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9755\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.3772\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9407\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.5830\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9669\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.4357\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 108px;\"\u003e\n \u003cp\u003eCombined\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003ePLSR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9244\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.6555\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9169\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.6877\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9200\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.6834\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003eSVMR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e203\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9628\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.4610\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9417\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.5758\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.9645\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003e0.4543\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e\u003c/strong\u003e\u003cstrong\u003eTable 6. Prediction results of DON using IRIV-selected wavelengths with OSC + SNV preprocessing techniques\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" class=\"fr-table-selection-hover\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 107px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePosition\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eModel\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e(LVs/SVs)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ec\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ecv\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSECV\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eR\u003csup\u003e2\u003c/sup\u003e\u003csub\u003ep\u003c/sub\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRMSEP\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 107px;\"\u003e\n \u003cp\u003eGerm up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003ePLSR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9627\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.4615\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9548\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.5080\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9557\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.5236\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eSVMR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e234\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9943\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.1792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9627\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.4604\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9823\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.3297\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 107px;\"\u003e\n \u003cp\u003eEndosperm up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003ePLSR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9415\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.5818\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9309\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.6332\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9309\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.6369\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eSVMR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e201\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9914\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.2225\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9179\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.6862\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9674\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.4361\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 107px;\"\u003e\n \u003cp\u003eCombined\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003ePLSR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9318\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.6236\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9277\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.6418\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9257\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.6569\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eSVMR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e282\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9714\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.4062\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9503\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.5335\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e0.9629\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e0.4635\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"environmental-science-and-pollution-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"espr","sideBox":"Learn more about [Environmental Science and Pollution Research](https://www.springer.com/journal/11356)","snPcode":"11356","submissionUrl":"https://submission.nature.com/new-submission/11356/3","title":"Environmental Science and Pollution Research","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Deoxynivalenol, near-infrared, HSI, CARS, IRIV, preprocessing","lastPublishedDoi":"10.21203/rs.3.rs-6465545/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6465545/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDeoxynivalenol (DON), found in corn, is a serious food safety issue. This study utilized a hyperspectral imaging system (HSI) in the shortwave infrared region (Reflectance, 900 – 2500 nm) to quantify the Deoxynivalenol (DON) content in corn kernels. The corn kernels pericarp layers were cracked and spiked with laboratory DON at five concentration levels – 0, 1, 2, 5 and 10 µg/g to mimic the natural distribution of DON. The HSI images were acquired at two different orientations of corn grain – germ-side and endosperm-side. The acquired images were subjected to 15 different preprocessing and feature selection methods.\u0026nbsp; Partial least square regression (PLSR) and support vector machine regression (SVMR) models were developed to correlate the processed spectra with the DON content measured by ELISA. The spectral data from the full spectrum and the spectral data from significant wavelengths obtained using feature selection methods were used to build regression models. The SVMR model developed from the germ-side full spectrum with SNV preprocessing provided the best R\u003csup\u003e2\u003c/sup\u003e prediction of 0.9855 and RMSE prediction of 0.2953. The SVMR model developed using germ-side significant wavelengths with Orthogonal Spectral Correction (OSC) + Standard Normal Variate (SNV)preprocessing provided the best R\u003csup\u003e2 \u003c/sup\u003eprediction of 0.9847 and RMSE prediction of 0.3010.\u003c/p\u003e","manuscriptTitle":"Application of Non-destructive and Chemical-free Short-Wave Infrared Hyperspectral Imaging (SWIR-HSI) coupled with Machine Learning Regression for Rapid Quantification of Deoxynivalenol (DON) in Individual Corn Kernels","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-07 07:22:15","doi":"10.21203/rs.3.rs-6465545/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major Revision","date":"2026-02-04T04:19:25+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2025-08-14T23:22:45+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-29T10:54:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-04-24T04:29:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"Environmental Science and Pollution Research","date":"2025-04-22T21:11:29+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"environmental-science-and-pollution-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"espr","sideBox":"Learn more about [Environmental Science and Pollution Research](https://www.springer.com/journal/11356)","snPcode":"11356","submissionUrl":"https://submission.nature.com/new-submission/11356/3","title":"Environmental Science and Pollution Research","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8ff342e7-fc05-42f0-a2f5-3ab1b8d2c31d","owner":[],"postedDate":"May 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-06T12:12:24+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-07 07:22:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6465545","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6465545","identity":"rs-6465545","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}