Multi-Class Plant Leaf Disease Detection: A CNN-based Approach with Mobile App Integration

Multi-Class Plant Leaf Disease Detection: A CNN-based Approach with Mobile App Integration | 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 Multi-Class Plant Leaf Disease Detection: A CNN-based Approach with Mobile App Integration Md Aziz Hosen Foysal, Foyez Ahmed, Md Zahurul Haque This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4629328/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Plant diseases significantly impact agricultural productivity, resulting in economic losses and food insecurity. Prompt and accurate detection is crucial for the efficient management and mitigation of plant diseases. This study investigates advanced techniques in plant disease detection, emphasizing the integration of image processing, machine learning, deep learning methods, and mobile technologies. High-resolution images of plant leaves were captured and analyzed using convolutional neural networks (CNNs) to detect symptoms of various diseases, such as blight, mildew, and rust. This study explores 14 classes of plants and diagnoses 26 unique plant diseases. We focus on common diseases affecting various crops. The model was trained on a diverse dataset encompassing multiple crops and disease types, achieving 98.14% accuracy in disease diagnosis. Finally integrated this model into mobile apps for real-time disease diagnosis. Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 I. INTRODUCTION Plant diseases are a major threat to the productivity of agriculture worldwide, resulting in large-scale financial losses and posing a risk to human and animal health. It is estimated that plant diseases account for approximately 40% of crop losses, underscoring the urgency of addressing this issue. In countries where agriculture is a primary source of income, early diagnosis and control of plant diseases are crucial for enhancing agricultural productivity and fostering economic growth. Timely identification of diseases is essential to prevent financial losses, yet farmers, especially in developing nations, often rely on manual inspection methods. Maize is a crucial crop in world due to its widespread acceptance among farmers and significant export potential. Maize serves multiple industries, including food and beverage, poultry, and animal feed, making it vital to the country’s economy. Huanglongbing, one of the most destructive diseases affecting citrus plants globally, poses a serious threat to orange production. Potatoes, a staple food rich in carbohydrates, are also at risk from diseases like early blight, which significantly hampers healthy yield. Tomatoes, celebrated for their taste and nutritional benefits, face challenges from pests and diseases that hinder their cultivation. Strawberries, with their high vitamin C and antioxidant content, can lower the risk of several serious diseases but are prone to leaf scorch. Blueberries, known for their health benefits and rich antioxidant content, are susceptible to diseases such as anthracnose and mummy berries. Cherries, peaches, peppers, raspberries, soybeans, and squash—all these crops, valued for their nutritional benefits and economic importance, are vulnerable to various diseases that impact their yield and quality. Nowadays, technology has greatly improved our lives. With the internet, almost everything is accessible. Using a regular camera, individuals can easily take photos of affected plant parts and upload them to a system that detects the specific disease and suggests the appropriate treatment, including any necessary pesticides. Our study aims to develop accurate models to meet the increasing demand for improved plant disease classification. Leveraging the large dataset, we designed a novel CNN architecture that outperforms several well-known pre-trained and custom models, including Bayesian Optimized SVM + Random Forest, YOLOv5 + Swim Transformer, VGG16, and AlexNet with GAP Layer. The proposed model achieved exceptionally high accuracy, highlighting the importance of large datasets in training robust and reliable disease detection systems. Additionally, the research aims to integrate this high-performing model into a user-friendly Android application using TensorFlow Lite, enabling real-time disease detection through image scanning or uploading. The ultimate goal is to provide farmers with immediate, actionable insights to manage plant health, reduce crop losses, and improve agricultural productivity and sustainability. II. RELATED WORKS Recent developments in plant disease identification have considerably benefitted from the deployment of Convolutional Neural Networks (CNN). CNNs have demonstrated exceptional accuracy in recognizing different plant diseases, making them a preferred choice over traditional methods, which are often time-consuming and less effective. Ferrentinos (2018) provided a comprehensive analysis of deep learning models for plant disease detection, highlighting their ability to diagnose multiple diseases from image data with high precision [ 3 ]. This work opened up new avenues for investigation into the application of deep learning to agricultural operations. Building on this foundation, Shrestha et al. (2020) applied CNNs to plant disease detection, demonstrating the robustness of these models in accurately classifying various diseases. Their work, presented at the IEEE Applied Signal Processing Conference, showed promising results and underscored the potential of CNN architectures in enhancing plant pathology diagnostics [ 2 ]. Similarly, Deepalakshmi et al. (2021) created a CNN-based method for identifying illnesses in plant leaves, further confirming the effectiveness of CNNs in handling large-scale image data and providing reliable disease classification [ 4 ]. Several studies have conducted comparative analyses of different CNN architectures to identify the most effective models for plant disease detection. Sardogan, Tuncer, and Ozen (2018) explored a hybrid approach by combining CNNs with learning vector quantization. (LVQ) for plant leaf disease detection. Their findings indicated that the integration of LVQ with CNNs improved classification accuracy, showcasing the advantages of hybrid models in enhancing diagnostic performance [ 5 ]. Agarwal, Gupta, and Biswas (2020) focused on developing an efficient CNN model specifically for tomato crop disease identification. Their model not only outperformed existing models in terms of accuracy but also demonstrated superior computational efficiency, making it a valuable tool for practical applications in agriculture [ 7 ]. The integration of machine learning models into mobile technologies has also been a significant focus in recent research. Wang et al. (2021) developed a trilinear CNN model (T-CNN) for the visual identification of plant illnesses, which was subsequently integrated into a mobile application for real-time diagnosis. This approach allowed farmers to use mobile devices for immediate disease detection, facilitating timely and effective disease management [ 8 ]. Joshi and Bhavsar (2023) suggested Night-CNN, a deep learning technology-based system designed mainly for mobile platform deployment, for the detection of nightshade crop leaf disease. Their model enabled real-time disease diagnosis in the field, emphasizing the practical benefits of mobile-ready diagnostic tools [ 9 ]. Further advancements have been made by incorporating additional techniques into CNN. models to improve their performance. Thakur, Sheorey, and Ojha (2023) proposed VGGICNN, a lightweight CNN model for crop disease identification. Their model achieved high accuracy while maintaining computational efficiency, making it suitable for use in resource-constrained environments [ 10 ]. Similarly, Lu, Tan, and Jiang (2021) reviewed various CNN applications in plant leaf disease classification, providing valuable insights into the strengths and limitations of different CNN architectures and their potential for improving agricultural practices [ 11 ]. Rao et al. (2022) developed a deep bilinear CNN for plant disease classification, which demonstrated significant improvements in classification accuracy by leveraging bilinear pooling techniques. This approach highlighted the potential of advanced CNN architectures in achieving higher diagnostic precision [ 12 ]. Suresh, Gnanaprakash, and Santhiya (2019) analyzed the execution of different CNN architectures with various optimizations for the categorization of plant diseases. Their study provided a comprehensive evaluation of CNN models, identifying optimal configurations for enhancing model performance [ 13 ]. In addition to these advancements, researchers have explored resilient CNN architectures to improve robustness against variations in image data. Gokulnath and Usha Devi (2021) developed a resilient LF-CNN for identifying and classifying plant diseases. Their model showed significant improvements in handling diverse image datasets, ensuring reliable disease detection under varying conditions [ 14 ]. Sun et al. (2022) conducted study on the diagnosis of plant diseases using CNN, further validating the efficacy of deep learning models in accurately diagnosing plant diseases [ 15 ]. The integration of hybrid models has also been explored to enhance disease detection accuracy. Singh et al. (2022) proposed a hybrid feature-based disease detection system that combined CNNs with Bayesian Optimized SVM and Random Forest classifiers. Their approach achieved high accuracy in plant leaf disease detection, demonstrating the benefits of hybrid models in leveraging the strengths of multiple machine learning techniques [ 16 ]. Ma et al. (2023) developed a YOLOv5n algorithm incorporating attention mechanisms for maize leaf disease identification. Their model showed significant improvements in detection accuracy, highlighting the potential of incorporating attention mechanisms in CNN architectures [ 17 ]. Lastly, evolutionary feature optimization has been explored to enhance the performance of deep learning models in plant disease detection. Al-bayati and Ustünda (2020) developed an optimization of evolutionary features technique for plant leaves disease detection using deep neural networks. Their approach demonstrated significant improvements in model performance by optimizing feature selection processes [ 18 ]. In order to detect diseases in plant leaves, Geetharamani and Arun Pandian (2019) used a nine-layer CNN. By using deep learning techniques, they were able to achieve high classification accuracy [ 19 ]. These studies collectively underscore the transformative potential of deep learning and mobile technologies in plant disease detection. The integration of CNN models into mobile applications represents a promising direction for real-time agricultural disease management, addressing critical challenges faced by farmers worldwide. As the field continues to evolve, further research is essential to enhance the robustness and scalability of these models, ensuring their widespread adoption and impact in agriculture. Our model's superior performance can be attributed to several key factors: Advanced CNN Architecture, Extensive Dataset, Data Augmentation and Robust Training, Real-time Application. TABLE I: COMPARING ACCURACY & TECHNIQUE FROM RELATED WORKS. Paper Technique Accuracy Singh et al. [ 16 ] Bayesian Optimized SVM, and Random Forest 96.1% Li Ma et al. [ 17 ] YOLOv5 + Swin Transformer 95.2% Arun Pandian et al. [ 19 ] VGG16 92.87% Mihir Kawatra et al. [ 20 ] AlexNet with GAP Layer 97.29% Our Model CNN 98.14% III. METHODOLOGY This study endeavors to create a precise and resilient plant disease detection model utilizing convolutional neural networks (CNNs) and a comprehensive, varied dataset. The methodology encompasses pivotal stages, including dataset preparation, model design, training, evaluation, and incorporation into a mobile application for real-time implementation. The following sections detail each step of the process. A. Dataset Preparation Data Collection A comprehensive dataset was sourced from Kaggle, comprising 87,867 images representing 26 different disease scenarios across 14 crops. The dataset comprises high-resolution images depicting both healthy and diseased plant leaves. Data Preprocessing To ensure the quality and consistency of the dataset, several preprocessing steps were undertaken Image Resizing : All images were resized to a consistent dimension (256x256 pixels) to match the input size required by our CNN model. Normalization : Pixel values were normalized to a range of 0 to 1 to facilitate faster convergence during training. Noise Removal : Any noisy or irrelevant images were identified and removed to ensure the quality of the training data. Data Augmentation : To enhance dataset variability and mitigate overfitting, techniques such as rotation, flipping, and zooming were employed. TABLE II: DATA DESCRIPTION Plant Names Leaf Types Samples in Training Samples in Validation Apple Apple Scab 2016 504 Black Rot 1987 497 Cedar Apple Rust 1760 440 Healthy 2008 502 Blueberry Healthy 1816 454 Cherry Powdery Mildew 1683 421 Healthy 1826 456 Corn Gray Leaf Spot 1642 410 Common Rust 1907 477 Northern Leaf Blight 1908 477 Healthy 1859 465 Grape Black Rot 1888 472 Black Measles (Esca) 1920 480 Leaf Blight 1722 430 Healthy 1692 423 Orange Citrus Greening 2010 503 Peach Bacterial Spot 1838 459 Healthy 1728 432 Bell Pepper Bacterial Spot 1913 478 Healthy 1988 497 Potato Early Blight 1939 485 Late Blight 1939 485 Healthy 1824 456 Raspberry Healthy 1781 445 Soybean Heathy 2022 505 Squash Powdery Mildew 1736 434 Strawberry Leaf Scorch 1774 444 Healthy 1824 456 Tomato Bacterial Spot 1702 425 Early Blight 1920 480 Late blight 1851 463 Leaf Mold 1882 470 Septoria Leaf Spot 1745 436 Spider Mites 1741 435 Target Spot 1827 457 Tomato Yellow Leaf Curl Virus 1961 490 Tomato Mosaic Virus 1790 448 Healthy 1926 481 B. Model Design CNN Architecture A novel CNN architecture was designed to optimize plant disease detection performance. The architecture includes Convolutional Layers : Multiple convolutional layers were used to extract features from the images, followed by ReLU activation functions. Pooling Layers : Max-pooling layers help minimize the dimension of the feature maps while keeping critical features. Fully Connected Layers : Dense layers to combine features and enable classification. Dropout Layers : Dropout layers were utilized to counter overfitting by randomly deactivating a fraction of input units during training. Hyperparameters and Settings We carefully selected the hyperparameters for our model to optimize performance Learning Rate : A learning rate of 0.0001 was selected to guarantee stable convergence. Batch Size : We used a batch size of 32, balancing computational efficiency and model accuracy. Epochs : Training the model for 15 epochs proved adequate to attain high accuracy without encountering overfitting. Data Splitting The dataset was partitioned into three subsets Training Set : The model was trained using 75% of the images. Validation Set : During training, 25% of the images were allocated for validating the model's performance. Test Set : A separate folder containing 33 images was used exclusively for testing and hyperparameter tweaking. The model summary with different parameter values is presented in Table II and Table III. TABLE III: MODEL OVERVIEW 1 LAYER OUTPUT PARAMETER conv2d (256, 256, 32) 896 conv2d_1 (254, 254, 32) 9248 max_pooling2d (127, 127, 32) 0 conv2d_2 (127, 127, 64) 18496 conv2d_3 (125, 125, 64) 36928 max_pooling2d_1 (62, 62, 64) 0 conv2d_4 (62, 62, 128) 73856 conv2d_5 (60, 60, 128) 147584 max_pooling2d_2 (30, 30, 128) 0 conv2d_6 (30, 30, 256) 295168 conv2d_7 (28, 28, 256) 590080 max_pooling2d_3 (14, 14, 256) 0 conv2d_8 (14, 14, 512) 3277312 conv2d_9 (10, 10, 512) 6554112 max_pooling2d_4 (5, 5, 512) 0 dropout (5, 5, 512) 0 flatten (12800) 0 dense (1536) 19662336 dropout_1 (1536) 0 Dense_1 (38) 58406 TABLE IV: MODEL OVERVIEW 2 Total_Parameters 30724422 Trainable_Parameters 30724422 Non-trainable Parameters 0 Evaluate Confusion Metrics : The confusion matrix showed that the majority of the misclassifications were among similar disease classes, which can be challenging even for human experts. The model performed exceptionally well in distinguishing between distinct disease classes. IV. EXPERIMENTAL RESULT The experimental results of this study showcase the effectiveness of the suggested CNN architecture in precisely detecting and categorizing illnesses in plants. The model underwent training and evaluation using a comprehensive dataset comprising 87,867 images, encompassing 26 different disease scenarios across 14 crops. The dataset was split into training, validation, and test sets to guarantee comprehensive training and evaluation of the model's performance. Training and Validation Accuracy : After training the model, we achieved a final training accuracy of approximately 99.7% and a validation accuracy of 98.14%. These high accuracy rates indicate that the model has learned to classify the plant disease images effectively. The loss values were also low, further confirming the model's performance. Loss Curves : The convergence of the training and validation loss curves indicates that the model effectively learned from the training data and demonstrated good generalization to unseen data. The final training and validation losses were low, further indicating a well-trained model. We present the performance metrics of our trained model after 15 epochs of training. The table provided below, referred to as TABLE IV, presents a summary of the training and validation accuracy, along with the corresponding loss values. These metrics offer insights into the efficacy of our model in classifying plant disease images. TABLE V: TRAINING & VALIDATION DATA Epoch Loss Accuracy Validation Loss Validation Accuracy 1st 1.2012 0.6456 0.4188 0.8631 2nd 0.3175 0.8983 0.2230 0.9272 3rd 0.1819 0.9415 0.1971 0.9352 4th 0.1254 0.9594 0.1327 0.9593 5th 0.0913 0.9704 0.1145 0.9637 6th 0.0716 0.9769 0.1255 0.9599 7th 0.0613 0.9801 0.1094 0.9670 8th 0.0506 0.9839 0.1172 0.9672 9th 0.0454 0.9855 0.1084 0.9684 10th 0.0420 0.9866 0.0782 0.9774 11th 0.0359 0.9885 0.0708 0.9788 12th 0.0329 0.9895 0.0857 0.9772 13th 0.0298 0.9904 0.0643 0.9829 14th 0.0298 0.9908 0.0722 0.9784 15th 0.0268 0.9914 0.0683 0.9814 Performance Analysis: One important indicator is accuracy, which expresses the percentage of cases properly identified relative to all instances. The suggested CNN model showed a higher degree of accuracy in classifying plant diseases with an accuracy of 98.14% on the test set. Real-Time Testing with Mobile Application To validate the model's practical applicability, it was integrated into a mobile app and tested in real-time scenarios. The goal was to develop an intuitive smartphone application that allows users to take or upload pictures and get detection results in real time. The following observations were made: V. CONCLUSION The successful development and implementation of the proposed CNN model for plant disease detection represent a significant advancement in agricultural technology. By providing an accurate, reliable, and practical solution for identifying plant diseases, this research enhances the sustainability and productivity of global agriculture. The integration of advanced deep learning models into mobile applications opens new avenues for real-time agricultural disease management, empowering farmers with the tools needed to address critical challenges effectively. Future work will focus on expanding the dataset, refining the model, and exploring additional applications of this technology in other areas of agriculture. Finally, we aim to integrate the model with Internet of Things (IoT) devices, including drones and smart sensors, to enable comprehensive monitoring of large agricultural fields and provide continuous, automated disease detection. Declarations Author Contribution Author 1 : Conceptualization, software development, validation, formal analysis, investigation, data curation, writing—original draft preparation, visualization.Author 2 : Supervision, writing—review and editing.Author 3 : Data curation, methodology, software testing, validation, writing—review and editing. Data Availability Data availabilityData generated for this study is available from the corresponding author on formal request References Bhattarai, S. (2018). New Plant Diseases Dataset. Kaggle. [Online]. Available: https://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset . Shrestha, G., Deepsikha, Das, M., & Dey, N. (2020). Plant Disease Detection Using CNN. 2020 IEEE Applied Signal Processing Conference (ASPCON), Kolkata, India, 109–113. https://doi.org/10.1109/ASPCON49795.2020.9276722 . Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311–318. https://doi.org/10.1016/j.compag.2018.01.009 . Deepalakshmi, P., Krishna, P. T., Chandana, S. S., & Srinivasu, P. N. (2021). Plant leaf disease detection using CNN algorithm. International Journal of Information System Modeling and Design, 12(1), 1–21. https://doi.org/10.4018/ijismd.2021010101 . Sardogan, M., Tuncer, A., & Ozen, Y. (2018). Plant Leaf Disease Detection and Classification Based on CNN with LVQ Algorithm. 2018 3rd International Conference on Computer Science and Engineering (UBMK), Sarajevo, Bosnia and Herzegovina, 382–385. https://doi.org/10.1109/UBMK.2018.8566635 . Wallelign, S., Polceanu, M., & Buche, C. (2018, May). Soybean plant disease identification using convolutional neural network. The Thirty-first International FLAIRS Conference. Agarwal, M., Gupta, S. K., & Biswas, K. K. (2020). Development of Efficient CNN model for Tomato crop disease identification. Sustainable Computing: Informatics and Systems, 28, 100407. https://doi.org/10.1016/j.suscom.2020.100407 . Wang, D., Wang, J., Li, W., & Guan, P. (2021). T-CNN: Trilinear convolutional neural networks model for visual detection of plant diseases. Computers and Electronics in Agriculture, 190, 106468. https://doi.org/10.1016/j.compag.2021.106468 . Joshi, M., & Bhavsar, H. (2023). Deep Learning Technology based Night-CNN for Nightshade Crop Leaf Disease Detection. International Journal of Intelligent Systems and Applications in Engineering, 11(1), 215–227. https://www.ijisae.org/index.php/IJISAE/article/view/2461 . Thakur, P. S., Sheorey, T., & Ojha, A. (2023). VGG-ICNN: A Lightweight CNN model for crop disease identification. Multimed Tools Appl, 82, 497–520. https://doi.org/10.1007/s11042-022-13144-z . Lu, J., Tan, L., & Jiang, H. (2021). Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification. Agriculture, 11(8), 707. https://doi.org/10.3390/agriculture11080707 . Rao, D. S., Ch, R. B., Kiran, V. S., Rajasekhar, N., Srinivas, K., et al. (2022). Plant disease classification using deep bilinear CNN. Intelligent Automation & Soft Computing, 31(1), 161–176. https://doi.org/10.32604/iasc.2022.017706 . Suresh, G., Gnanaprakash, V., & Santhiya, R. (2019). Performance Analysis of Different CNN Architecture with Different Optimisers for Plant Disease Classification. 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), Coimbatore, India, 916–921. https://doi.org/10.1109/ICACCS.2019.8728282 . Gokulnath, B. V., & Usha Devi, G. (2021). Identifying and classifying plant disease using resilient LF-CNN. Ecological Informatics, 63, 101283. https://doi.org/10.1016/j.ecoinf.2021.101283 . Sun, X., Li, G., Qu, P., Xie, X., Pan, X., & Zhang, W. (2022). Research on plant disease identification based on CNN. Cognitive Robotics, 2, 155–163. https://doi.org/10.1016/j.cogr.2022.07.001 . Singh, A. K., Khan, R., et al. (2022). Hybrid Feature-Based Disease Detection in Plant Leaf Using Convolutional Neural Network, Bayesian Optimized SVM, and Random Forest Classifier. Journal of Food Quality, 2022, 1–16. https://doi.org/10.1155/2022/2845320 . Ma, L., et al. (2023). Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism. Agronomy, 13, 521. https://doi.org/10.3390/agronomy13020521 . Al-bayati, J. S. H., & Ustündağ, B. B. (2020). Evolutionary feature optimization for plant leaf disease detection by deep neural networks. International Journal of Computational Intelligence Systems, 13(1), 12. [Online]. Available: https://doi.org/10.32604/iasc.2022.017706 Geetharamani, G., & Arun Pandian, J. (2019). Identification of plant leaf diseases using a nine-layer deep convolutional neural network. Computers and Electrical Engineering, 76, 323–338. https://doi.org/10.1016/j.compeleceng.2019.04.011 . Kawatra, M., Agarwal, S., & Kapur, R. (2020). Leaf Disease Detection using Neural Network Hybrid Models. 2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA), 225–230. https://doi.org/10.1109/ICCCA49541.2020.9250885 . Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-4629328","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":330661272,"identity":"5ff08912-c22e-437b-b31d-8b4c49d2c24e","order_by":0,"name":"Md Aziz Hosen Foysal","email":"","orcid":"","institution":"Manarat International University (MIU)","correspondingAuthor":false,"prefix":"","firstName":"Md","middleName":"Aziz Hosen","lastName":"Foysal","suffix":""},{"id":330661275,"identity":"1a98a785-eeb2-4329-9e40-895b40adfe31","order_by":1,"name":"Foyez Ahmed","email":"","orcid":"","institution":"Manarat International University (MIU)","correspondingAuthor":false,"prefix":"","firstName":"Foyez","middleName":"","lastName":"Ahmed","suffix":""},{"id":330661276,"identity":"289c42c0-573c-4879-8bf3-ef0850ee5ba4","order_by":2,"name":"Md Zahurul Haque","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDklEQVRIiWNgGAWjYBACxgYeEGWRAOZ9QJYyYEjAp0UCLMs4AyaITwsDA5IWZh5itDC3nz0mXdkmkcffnmP42DbHLo9/9uHnDxhq7BjM2XE4rCcvTfJsm0SxxJk3xsa525KLJc6lGTYwHEtmsOx5gMMvOWaSjW0SiQ03csykc7cxJzacYQBqYTvAYHADhy39byBa5t/IMf9tua0+cf4Z9o8NDP/waJkBtWUD0BZmxm2HEzec4TFsYGzDp+WNsWXDOYnEjWeeFUv2bjsOZPAUzkjsS+bB5RfD/hzDmw1lNonzjidv/PBzW3XivDPsGz58+GYnhyvEgD6FAWQFCdD4wgbkUZSNglEwCkbBKMAGAAAKY8+Dnry9AAAAAElFTkSuQmCC","orcid":"","institution":"Manarat International University (MIU)","correspondingAuthor":true,"prefix":"","firstName":"Md","middleName":"Zahurul","lastName":"Haque","suffix":""}],"badges":[],"createdAt":"2024-06-24 10:09:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4629328/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4629328/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61182353,"identity":"c5871312-15b5-442d-bc1b-dc3ba631e97e","added_by":"auto","created_at":"2024-07-26 16:57:03","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":157568,"visible":true,"origin":"","legend":"\u003cp\u003eCNN Model Architecture\u003c/p\u003e","description":"","filename":"image1.png","url":"https://assets-eu.researchsquare.com/files/rs-4629328/v1/5afe40ff8960396d0b2f2adc.png"},{"id":61183541,"identity":"6ca3dc47-4a38-4fde-88ab-209590828bde","added_by":"auto","created_at":"2024-07-26 17:05:03","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":1173308,"visible":true,"origin":"","legend":"\u003cp\u003eSample Images from Each Class of Dataset\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-4629328/v1/a6c3d64a0f4464b846ac9ada.png"},{"id":61183540,"identity":"9045233f-059e-41cf-ad6d-d01c52b2336c","added_by":"auto","created_at":"2024-07-26 17:05:03","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":71945,"visible":true,"origin":"","legend":"\u003cp\u003eConfusion Matrix\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-4629328/v1/c325a4cbfd1153ab134e8de3.png"},{"id":61182352,"identity":"8fdd8ed9-d079-4b31-88ab-9c000647d749","added_by":"auto","created_at":"2024-07-26 16:57:03","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":37847,"visible":true,"origin":"","legend":"\u003cp\u003eAccuracy Visualization Curve\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-4629328/v1/6ae452c483eb98285b47c9c9.png"},{"id":61182354,"identity":"e203cdfe-c167-4bbe-9b49-74c96e23b570","added_by":"auto","created_at":"2024-07-26 16:57:03","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":40963,"visible":true,"origin":"","legend":"\u003cp\u003eLoss Visualization Curve\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-4629328/v1/0c33cc5a67b0095b100134ee.png"},{"id":61182358,"identity":"733c4e28-6a8a-41f5-9968-344618e01ea5","added_by":"auto","created_at":"2024-07-26 16:57:03","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":523252,"visible":true,"origin":"","legend":"\u003cp\u003eHome Page of the Android Application (in the left) and Disease Detection (in the right)\u003c/p\u003e","description":"","filename":"image6.png","url":"https://assets-eu.researchsquare.com/files/rs-4629328/v1/8007bee9e581e3b33332c471.png"},{"id":71481370,"identity":"82953f66-2b4a-4cec-b6db-b822f2876bc0","added_by":"auto","created_at":"2024-12-16 06:03:31","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2573213,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4629328/v1/5402c8f6-dc55-46c1-9a9e-eed6dedcebbf.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Class Plant Leaf Disease Detection: A CNN-based Approach with Mobile App Integration","fulltext":[{"header":"I. INTRODUCTION","content":"\u003cp\u003ePlant diseases are a major threat to the productivity of agriculture worldwide, resulting in large-scale financial losses and posing a risk to human and animal health. It is estimated that plant diseases account for approximately 40% of crop losses, underscoring the urgency of addressing this issue. In countries where agriculture is a primary source of income, early diagnosis and control of plant diseases are crucial for enhancing agricultural productivity and fostering economic growth. Timely identification of diseases is essential to prevent financial losses, yet farmers, especially in developing nations, often rely on manual inspection methods. Maize is a crucial crop in world due to its widespread acceptance among farmers and significant export potential. Maize serves multiple industries, including food and beverage, poultry, and animal feed, making it vital to the country\u0026rsquo;s economy. Huanglongbing, one of the most destructive diseases affecting citrus plants globally, poses a serious threat to orange production. Potatoes, a staple food rich in carbohydrates, are also at risk from diseases like early blight, which significantly hampers healthy yield. Tomatoes, celebrated for their taste and nutritional benefits, face challenges from pests and diseases that hinder their cultivation. Strawberries, with their high vitamin C and antioxidant content, can lower the risk of several serious diseases but are prone to leaf scorch. Blueberries, known for their health benefits and rich antioxidant content, are susceptible to diseases such as anthracnose and mummy berries. Cherries, peaches, peppers, raspberries, soybeans, and squash\u0026mdash;all these crops, valued for their nutritional benefits and economic importance, are vulnerable to various diseases that impact their yield and quality. Nowadays, technology has greatly improved our lives. With the internet, almost everything is accessible. Using a regular camera, individuals can easily take photos of affected plant parts and upload them to a system that detects the specific disease and suggests the appropriate treatment, including any necessary pesticides. Our study aims to develop accurate models to meet the increasing demand for improved plant disease classification. Leveraging the large dataset, we designed a novel CNN architecture that outperforms several well-known pre-trained and custom models, including Bayesian Optimized SVM\u0026thinsp;+\u0026thinsp;Random Forest, YOLOv5\u0026thinsp;+\u0026thinsp;Swim Transformer, VGG16, and AlexNet with GAP Layer. The proposed model achieved exceptionally high accuracy, highlighting the importance of large datasets in training robust and reliable disease detection systems. Additionally, the research aims to integrate this high-performing model into a user-friendly Android application using TensorFlow Lite, enabling real-time disease detection through image scanning or uploading. The ultimate goal is to provide farmers with immediate, actionable insights to manage plant health, reduce crop losses, and improve agricultural productivity and sustainability.\u003c/p\u003e"},{"header":"II. RELATED WORKS","content":"\u003cp\u003eRecent developments in plant disease identification have considerably benefitted from the deployment of Convolutional Neural Networks (CNN). CNNs have demonstrated exceptional accuracy in recognizing different plant diseases, making them a preferred choice over traditional methods, which are often time-consuming and less effective. Ferrentinos (2018) provided a comprehensive analysis of deep learning models for plant disease detection, highlighting their ability to diagnose multiple diseases from image data with high precision [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. This work opened up new avenues for investigation into the application of deep learning to agricultural operations. Building on this foundation, Shrestha et al. (2020) applied CNNs to plant disease detection, demonstrating the robustness of these models in accurately classifying various diseases. Their work, presented at the IEEE Applied Signal Processing Conference, showed promising results and underscored the potential of CNN architectures in enhancing plant pathology diagnostics [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Similarly, Deepalakshmi et al. (2021) created a CNN-based method for identifying illnesses in plant leaves, further confirming the effectiveness of CNNs in handling large-scale image data and providing reliable disease classification [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Several studies have conducted comparative analyses of different CNN architectures to identify the most effective models for plant disease detection. Sardogan, Tuncer, and Ozen (2018) explored a hybrid approach by combining CNNs with learning vector quantization. (LVQ) for plant leaf disease detection. Their findings indicated that the integration of LVQ with CNNs improved classification accuracy, showcasing the advantages of hybrid models in enhancing diagnostic performance [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Agarwal, Gupta, and Biswas (2020) focused on developing an efficient CNN model specifically for tomato crop disease identification.\u003c/p\u003e \u003cp\u003eTheir model not only outperformed existing models in terms of accuracy but also demonstrated superior computational efficiency, making it a valuable tool for practical applications in agriculture [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. The integration of machine learning models into mobile technologies has also been a significant focus in recent research. Wang et al. (2021) developed a trilinear CNN model (T-CNN) for the visual identification of plant illnesses, which was subsequently integrated into a mobile application for real-time diagnosis. This approach allowed farmers to use mobile devices for immediate disease detection, facilitating timely and effective disease management [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Joshi and Bhavsar (2023) suggested Night-CNN, a deep learning technology-based system designed mainly for mobile platform deployment, for the detection of nightshade crop leaf disease. Their model enabled real-time disease diagnosis in the field, emphasizing the practical benefits of mobile-ready diagnostic tools [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Further advancements have been made by incorporating additional techniques into CNN. models to improve their performance. Thakur, Sheorey, and Ojha (2023) proposed VGGICNN, a lightweight CNN model for crop disease identification. Their model achieved high accuracy while maintaining computational efficiency, making it suitable for use in resource-constrained environments [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Similarly, Lu, Tan, and Jiang (2021) reviewed various CNN applications in plant leaf disease classification, providing valuable insights into the strengths and limitations of different CNN architectures and their potential for improving agricultural practices [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Rao et al. (2022) developed a deep bilinear CNN for plant disease classification, which demonstrated significant improvements in classification accuracy by leveraging bilinear pooling techniques. This approach highlighted the potential of advanced CNN architectures in achieving higher diagnostic precision [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. Suresh, Gnanaprakash, and Santhiya (2019) analyzed the execution of different CNN architectures with various optimizations for the categorization of plant diseases. Their study provided a comprehensive evaluation of CNN models, identifying optimal configurations for enhancing model performance [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. In addition to these advancements, researchers have explored resilient CNN architectures to improve robustness against variations in image data. Gokulnath and Usha Devi (2021) developed a resilient LF-CNN for identifying and classifying plant diseases. Their model showed significant improvements in handling diverse image datasets, ensuring reliable disease detection under varying conditions [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. Sun et al. (2022) conducted study on the diagnosis of plant diseases using CNN, further validating the efficacy of deep learning models in accurately diagnosing plant diseases [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. The integration of hybrid models has also been explored to enhance disease detection accuracy. Singh et al. (2022) proposed a hybrid feature-based disease detection system that combined CNNs with Bayesian Optimized SVM and Random Forest classifiers. Their approach achieved high accuracy in plant leaf disease detection, demonstrating the benefits of hybrid models in leveraging the strengths of multiple machine learning techniques [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Ma et al. (2023) developed a YOLOv5n algorithm incorporating attention mechanisms for maize leaf disease identification. Their model showed significant improvements in detection accuracy, highlighting the potential of incorporating attention mechanisms in CNN architectures [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. Lastly, evolutionary feature optimization has been explored to enhance the performance of deep learning models in plant disease detection. Al-bayati and Ust\u0026uuml;nda (2020) developed an optimization of evolutionary features technique for plant leaves disease detection using deep neural networks. Their approach demonstrated significant improvements in model performance by optimizing feature selection processes [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. In order to detect diseases in plant leaves, Geetharamani and Arun Pandian (2019) used a nine-layer CNN. By using deep learning techniques, they were able to achieve high classification accuracy [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. These studies collectively underscore the transformative potential of deep learning and mobile technologies in plant disease detection. The integration of CNN models into mobile applications represents a promising direction for real-time agricultural disease management, addressing critical challenges faced by farmers worldwide. As the field continues to evolve, further research is essential to enhance the robustness and scalability of these models, ensuring their widespread adoption and impact in agriculture. Our model's superior performance can be attributed to several key factors: Advanced CNN Architecture, Extensive Dataset, Data Augmentation and Robust Training, Real-time Application.\u003c/p\u003e \u003cp\u003eTABLE I: COMPARING ACCURACY \u0026amp; TECHNIQUE FROM RELATED WORKS.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Taba\" border=\"1\"\u003e \u003ccolgroup cols=\"3\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePaper\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTechnique\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSingh et al. [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBayesian Optimized SVM, and Random Forest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e96.1%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLi Ma et al. [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYOLOv5\u0026thinsp;+\u0026thinsp;Swin Transformer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e95.2%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArun Pandian et al. [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVGG16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e92.87%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMihir Kawatra et al. [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAlexNet with GAP Layer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e97.29%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eOur Model\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u003cb\u003eCNN\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003e98.14%\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e"},{"header":"III. METHODOLOGY","content":"\u003cp\u003eThis study endeavors to create a precise and resilient plant disease detection model utilizing convolutional neural networks (CNNs) and a comprehensive, varied dataset. The methodology encompasses pivotal stages, including dataset preparation, model design, training, evaluation, and incorporation into a mobile application for real-time implementation. The following sections detail each step of the process.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eA. Dataset Preparation\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Collection\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA comprehensive dataset was sourced from Kaggle, comprising 87,867 images representing 26 different disease scenarios across 14 crops. The dataset comprises high-resolution images depicting both healthy and diseased plant leaves.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Preprocessing\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTo ensure the quality and consistency of the dataset, several preprocessing steps were undertaken\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eImage Resizing\u003c/strong\u003e: All images were resized to a consistent dimension (256x256 pixels) to match the input size required by our CNN model.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eNormalization\u003c/strong\u003e: Pixel values were normalized to a range of 0 to 1 to facilitate faster convergence during training.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eNoise Removal\u003c/strong\u003e: Any noisy or irrelevant images were identified and removed to ensure the quality of the training data.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eData Augmentation\u003c/strong\u003e: To enhance dataset variability and mitigate overfitting, techniques such as rotation, flipping, and zooming were employed.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eTABLE II: DATA DESCRIPTION\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"char\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tabb\" border=\"1\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003ePlant Names\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eLeaf Types\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSamples in Training\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSamples in Validation\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"4\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eApple\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eApple Scab\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2016\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e504\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBlack Rot\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1987\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e497\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCedar Apple Rust\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1760\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e440\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2008\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e502\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eBlueberry\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1816\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e454\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eCherry\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePowdery Mildew\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1683\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e421\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1826\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e456\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"4\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eCorn\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eGray Leaf Spot\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1642\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e410\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCommon Rust\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1907\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e477\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNorthern Leaf Blight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1908\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e477\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1859\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e465\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"4\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eGrape\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBlack Rot\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1888\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e472\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBlack Measles (Esca)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1920\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e480\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLeaf Blight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1722\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e430\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1692\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e423\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eOrange\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCitrus Greening\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2010\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e503\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003ePeach\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBacterial Spot\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1838\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e459\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1728\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e432\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eBell Pepper\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBacterial Spot\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1913\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e478\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1988\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e497\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"3\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003ePotato\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eEarly Blight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1939\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e485\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLate Blight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1939\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e485\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1824\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e456\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eRaspberry\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1781\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e445\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eSoybean\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHeathy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2022\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e505\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eSquash\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePowdery Mildew\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1736\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e434\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eStrawberry\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLeaf Scorch\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1774\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e444\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1824\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e456\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"10\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eTomato\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBacterial Spot\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1702\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e425\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eEarly Blight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1920\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e480\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLate blight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1851\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e463\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLeaf Mold\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1882\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e470\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSeptoria Leaf Spot\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1745\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e436\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSpider Mites\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1741\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e435\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eTarget Spot\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1827\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e457\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eTomato Yellow Leaf Curl Virus\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1961\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e490\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eTomato Mosaic Virus\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1790\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e448\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHealthy\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1926\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e481\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"gridtable\"\u003e\u003cem\u003eB. Model Design\u003c/em\u003e\u003c/div\u003e\n\u003cp\u003e\u003cstrong\u003eCNN Architecture\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA novel CNN architecture was designed to optimize plant disease detection performance. The architecture includes\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eConvolutional Layers\u003c/strong\u003e: Multiple convolutional layers were used to extract features from the images, followed by ReLU activation functions.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003ePooling Layers\u003c/strong\u003e: Max-pooling layers help minimize the dimension of the feature maps while keeping critical features.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eFully Connected Layers\u003c/strong\u003e: Dense layers to combine features and enable classification.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eDropout Layers\u003c/strong\u003e: Dropout layers were utilized to counter overfitting by randomly deactivating a fraction of input units during training.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eHyperparameters and Settings\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe carefully selected the hyperparameters for our model to optimize performance\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eLearning Rate\u003c/strong\u003e: A learning rate of 0.0001 was selected to guarantee stable convergence.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eBatch Size\u003c/strong\u003e: We used a batch size of 32, balancing computational efficiency and model accuracy.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eEpochs\u003c/strong\u003e: Training the model for 15 epochs proved adequate to attain high accuracy without encountering overfitting.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong\u003eData Splitting\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe dataset was partitioned into three subsets\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eTraining Set\u003c/strong\u003e: The model was trained using 75% of the images.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eValidation Set\u003c/strong\u003e: During training, 25% of the images were allocated for validating the model's performance.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003e\u003cstrong\u003eTest Set\u003c/strong\u003e: A separate folder containing 33 images was used exclusively for testing and hyperparameter tweaking.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe model summary with different parameter values is presented in Table II and Table III.\u003c/p\u003e\n\u003cp\u003eTABLE III: MODEL OVERVIEW 1\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003ctable id=\"Tabc\" border=\"1\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eLAYER\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eOUTPUT\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003ePARAMETER\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(256, 256, 32)\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e896\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_1\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(254, 254, 32)\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e9248\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003emax_pooling2d\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(127, 127, 32)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_2\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(127, 127, 64)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e18496\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_3\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(125, 125, 64)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e36928\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003emax_pooling2d_1\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(62, 62, 64)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_4\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(62, 62, 128)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e73856\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_5\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(60, 60, 128)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e147584\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003emax_pooling2d_2\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(30, 30, 128)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_6\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(30, 30, 256)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e295168\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_7\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(28, 28, 256)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e590080\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003emax_pooling2d_3\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(14, 14, 256)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_8\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(14, 14, 512)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e3277312\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003econv2d_9\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(10, 10, 512)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e6554112\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003emax_pooling2d_4\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(5, 5, 512)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003edropout\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(5, 5, 512)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eflatten\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(12800)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003edense\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(1536)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e19662336\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003edropout_1\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(1536)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eDense_1\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e(38)\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e58406\u003c/em\u003e\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\u003eTABLE IV: MODEL OVERVIEW 2\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"char\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tabd\" border=\"1\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eTotal_Parameters\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003e30724422\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eTrainable_Parameters\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e30724422\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eNon-trainable Parameters\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cem\u003e0\u003c/em\u003e\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\u003eEvaluate Confusion Metrics\u003c/strong\u003e:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eThe confusion matrix showed that the majority of the misclassifications were among similar disease classes, which can be challenging even for human experts.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eThe model performed exceptionally well in distinguishing between distinct disease classes.\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e"},{"header":"IV. EXPERIMENTAL RESULT","content":"\u003cp\u003eThe experimental results of this study showcase the effectiveness of the suggested CNN architecture in precisely detecting and categorizing illnesses in plants. The model underwent training and evaluation using a comprehensive dataset comprising 87,867 images, encompassing 26 different disease scenarios across 14 crops. The dataset was split into training, validation, and test sets to guarantee comprehensive training and evaluation of the model's performance.\u003c/p\u003e \u003cp\u003e \u003cb\u003eTraining and Validation Accuracy\u003c/b\u003e:\u003c/p\u003e \u003cp\u003eAfter training the model, we achieved a final training accuracy of approximately 99.7% and a validation accuracy of 98.14%. These high accuracy rates indicate that the model has learned to classify the plant disease images effectively. The loss values were also low, further confirming the model's performance.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cb\u003eLoss Curves\u003c/b\u003e:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eThe convergence of the training and validation loss curves indicates that the model effectively learned from the training data and demonstrated good generalization to unseen data.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eThe final training and validation losses were low, further indicating a well-trained model.\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eWe present the performance metrics of our trained model after 15 epochs of training. The table provided below, referred to as TABLE IV, presents a summary of the training and validation accuracy, along with the corresponding loss values. These metrics offer insights into the efficacy of our model in classifying plant disease images.\u003c/p\u003e \u003cp\u003eTABLE V: TRAINING \u0026amp; VALIDATION DATA\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Tabe\" border=\"1\"\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" 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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003eEpoch\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u003cem\u003eLoss\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cem\u003eAccuracy\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eValidation Loss\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eValidation Accuracy\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e1st\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.2012\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.6456\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.4188\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.8631\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e2nd\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.3175\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.8983\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.2230\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9272\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e3rd\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.1819\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9415\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1971\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9352\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e4th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.1254\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9594\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1327\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9593\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e5th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0913\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9704\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1145\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9637\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e6th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0716\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9769\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1255\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9599\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e7th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0613\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9801\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1094\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9670\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e8th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0506\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9839\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1172\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9672\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e9th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0454\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9855\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.1084\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9684\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e10th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0420\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9866\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.0782\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9774\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e11th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0359\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9885\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.0708\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9788\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e12th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0329\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9895\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.0857\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9772\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e13th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0298\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9904\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.0643\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9829\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e14th\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0298\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.9908\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.0722\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.9784\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003e15th\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e\u003cb\u003e0.0268\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003e0.9914\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.0683\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e0.9814\u003c/b\u003e\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\u003ePerformance Analysis: One important indicator is accuracy, which expresses the percentage of cases properly identified relative to all instances. The suggested CNN model showed a higher degree of accuracy in classifying plant diseases with an accuracy of 98.14% on the test set.\u003c/p\u003e \u003cp\u003e \u003cb\u003eReal-Time Testing with Mobile Application\u003c/b\u003e \u003c/p\u003e \u003cp\u003eTo validate the model's practical applicability, it was integrated into a mobile app and tested in real-time scenarios. The goal was to develop an intuitive smartphone application that allows users to take or upload pictures and get detection results in real time. The following observations were made:\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"V. CONCLUSION","content":"\u003cp\u003eThe successful development and implementation of the proposed CNN model for plant disease detection represent a significant advancement in agricultural technology. By providing an accurate, reliable, and practical solution for identifying plant diseases, this research enhances the sustainability and productivity of global agriculture. The integration of advanced deep learning models into mobile applications opens new avenues for real-time agricultural disease management, empowering farmers with the tools needed to address critical challenges effectively. Future work will focus on expanding the dataset, refining the model, and exploring additional applications of this technology in other areas of agriculture. Finally, we aim to integrate the model with Internet of Things (IoT) devices, including drones and smart sensors, to enable comprehensive monitoring of large agricultural fields and provide continuous, automated disease detection.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eAuthor 1 : Conceptualization, software development, validation, formal analysis, investigation, data curation, writing\u0026mdash;original draft preparation, visualization.Author 2 : Supervision, writing\u0026mdash;review and editing.Author 3 : Data curation, methodology, software testing, validation, writing\u0026mdash;review and editing.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eData availabilityData generated for this study is available from the corresponding author on formal request\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eBhattarai, S. (2018). New Plant Diseases Dataset. Kaggle. [Online]. Available: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset\u003c/span\u003e\u003cspan address=\"https://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShrestha, G., Deepsikha, Das, M., \u0026amp; Dey, N. (2020). Plant Disease Detection Using CNN. 2020 IEEE Applied Signal Processing Conference (ASPCON), Kolkata, India, 109\u0026ndash;113. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/ASPCON49795.2020.9276722\u003c/span\u003e\u003cspan address=\"10.1109/ASPCON49795.2020.9276722\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFerentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311\u0026ndash;318. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.compag.2018.01.009\u003c/span\u003e\u003cspan address=\"10.1016/j.compag.2018.01.009\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDeepalakshmi, P., Krishna, P. T., Chandana, S. S., \u0026amp; Srinivasu, P. N. (2021). Plant leaf disease detection using CNN algorithm. International Journal of Information System Modeling and Design, 12(1), 1\u0026ndash;21. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.4018/ijismd.2021010101\u003c/span\u003e\u003cspan address=\"10.4018/ijismd.2021010101\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSardogan, M., Tuncer, A., \u0026amp; Ozen, Y. (2018). Plant Leaf Disease Detection and Classification Based on CNN with LVQ Algorithm. 2018 3rd International Conference on Computer Science and Engineering (UBMK), Sarajevo, Bosnia and Herzegovina, 382\u0026ndash;385. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/UBMK.2018.8566635\u003c/span\u003e\u003cspan address=\"10.1109/UBMK.2018.8566635\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWallelign, S., Polceanu, M., \u0026amp; Buche, C. (2018, May). Soybean plant disease identification using convolutional neural network. The Thirty-first International FLAIRS Conference.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAgarwal, M., Gupta, S. K., \u0026amp; Biswas, K. K. (2020). Development of Efficient CNN model for Tomato crop disease identification. Sustainable Computing: Informatics and Systems, 28, 100407. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.suscom.2020.100407\u003c/span\u003e\u003cspan address=\"10.1016/j.suscom.2020.100407\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang, D., Wang, J., Li, W., \u0026amp; Guan, P. (2021). T-CNN: Trilinear convolutional neural networks model for visual detection of plant diseases. Computers and Electronics in Agriculture, 190, 106468. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.compag.2021.106468\u003c/span\u003e\u003cspan address=\"10.1016/j.compag.2021.106468\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJoshi, M., \u0026amp; Bhavsar, H. (2023). Deep Learning Technology based Night-CNN for Nightshade Crop Leaf Disease Detection. International Journal of Intelligent Systems and Applications in Engineering, 11(1), 215\u0026ndash;227. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.ijisae.org/index.php/IJISAE/article/view/2461\u003c/span\u003e\u003cspan address=\"https://www.ijisae.org/index.php/IJISAE/article/view/2461\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThakur, P. S., Sheorey, T., \u0026amp; Ojha, A. (2023). VGG-ICNN: A Lightweight CNN model for crop disease identification. Multimed Tools Appl, 82, 497\u0026ndash;520. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11042-022-13144-z\u003c/span\u003e\u003cspan address=\"10.1007/s11042-022-13144-z\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLu, J., Tan, L., \u0026amp; Jiang, H. (2021). Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification. Agriculture, 11(8), 707. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/agriculture11080707\u003c/span\u003e\u003cspan address=\"10.3390/agriculture11080707\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRao, D. S., Ch, R. B., Kiran, V. S., Rajasekhar, N., Srinivas, K., et al. (2022). Plant disease classification using deep bilinear CNN. Intelligent Automation \u0026amp; Soft Computing, 31(1), 161\u0026ndash;176. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.32604/iasc.2022.017706\u003c/span\u003e\u003cspan address=\"10.32604/iasc.2022.017706\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSuresh, G., Gnanaprakash, V., \u0026amp; Santhiya, R. (2019). Performance Analysis of Different CNN Architecture with Different Optimisers for Plant Disease Classification. 2019 5th International Conference on Advanced Computing \u0026amp; Communication Systems (ICACCS), Coimbatore, India, 916\u0026ndash;921. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/ICACCS.2019.8728282\u003c/span\u003e\u003cspan address=\"10.1109/ICACCS.2019.8728282\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGokulnath, B. V., \u0026amp; Usha Devi, G. (2021). Identifying and classifying plant disease using resilient LF-CNN. Ecological Informatics, 63, 101283. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ecoinf.2021.101283\u003c/span\u003e\u003cspan address=\"10.1016/j.ecoinf.2021.101283\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSun, X., Li, G., Qu, P., Xie, X., Pan, X., \u0026amp; Zhang, W. (2022). Research on plant disease identification based on CNN. Cognitive Robotics, 2, 155\u0026ndash;163. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.cogr.2022.07.001\u003c/span\u003e\u003cspan address=\"10.1016/j.cogr.2022.07.001\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSingh, A. K., Khan, R., et al. (2022). Hybrid Feature-Based Disease Detection in Plant Leaf Using Convolutional Neural Network, Bayesian Optimized SVM, and Random Forest Classifier. Journal of Food Quality, 2022, 1\u0026ndash;16. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1155/2022/2845320\u003c/span\u003e\u003cspan address=\"10.1155/2022/2845320\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMa, L., et al. (2023). Maize Leaf Disease Identification Based on YOLOv5n Algorithm Incorporating Attention Mechanism. Agronomy, 13, 521. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/agronomy13020521\u003c/span\u003e\u003cspan address=\"10.3390/agronomy13020521\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAl-bayati, J. S. H., \u0026amp; Ust\u0026uuml;ndağ, B. B. (2020). Evolutionary feature optimization for plant leaf disease detection by deep neural networks. International Journal of Computational Intelligence Systems, 13(1), 12. [Online]. Available: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.32604/iasc.2022.017706\u003c/span\u003e\u003cspan address=\"10.32604/iasc.2022.017706\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGeetharamani, G., \u0026amp; Arun Pandian, J. (2019). Identification of plant leaf diseases using a nine-layer deep convolutional neural network. Computers and Electrical Engineering, 76, 323\u0026ndash;338. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.compeleceng.2019.04.011\u003c/span\u003e\u003cspan address=\"10.1016/j.compeleceng.2019.04.011\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKawatra, M., Agarwal, S., \u0026amp; Kapur, R. (2020). Leaf Disease Detection using Neural Network Hybrid Models. 2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA), 225\u0026ndash;230. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1109/ICCCA49541.2020.9250885\u003c/span\u003e\u003cspan address=\"10.1109/ICCCA49541.2020.9250885\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4629328/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4629328/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Plant diseases significantly impact agricultural productivity, resulting in economic losses and food insecurity. Prompt and accurate detection is crucial for the efficient management and mitigation of plant diseases. This study investigates advanced techniques in plant disease detection, emphasizing the integration of image processing, machine learning, deep learning methods, and mobile technologies. High-resolution images of plant leaves were captured and analyzed using convolutional neural networks (CNNs) to detect symptoms of various diseases, such as blight, mildew, and rust. This study explores 14 classes of plants and diagnoses 26 unique plant diseases. We focus on common diseases affecting various crops. The model was trained on a diverse dataset encompassing multiple crops and disease types, achieving 98.14% accuracy in disease diagnosis. Finally integrated this model into mobile apps for real-time disease diagnosis. ","manuscriptTitle":"Multi-Class Plant Leaf Disease Detection: A CNN-based Approach with Mobile App Integration","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-26 16:56:58","doi":"10.21203/rs.3.rs-4629328/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a49882d3-61bb-420e-b6d6-1476746d2904","owner":[],"postedDate":"July 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-16T05:54:52+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-26 16:56:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4629328","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4629328","identity":"rs-4629328","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}