Modeling Finger Movements of a Prosthetic Hand from EEG Signals Using ARX SIMO Models

Modeling Finger Movements of a Prosthetic Hand from EEG Signals Using ARX SIMO Models | 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 Modeling Finger Movements of a Prosthetic Hand from EEG Signals Using ARX SIMO Models Jules Ngono Mvondo, Léandre Nneme Nneme This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8500934/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 This study presents a comparative modeling analysis of a prosthetic hand controlled by electroencephalographic (EEG) signals. A Single Input Multiple Output (SIMO) framework is adopted, where a single EEG signal is used to predict the movements of five fingers (thumb, index, middle, ring, and little finger). Four dynamic models are evaluated: Auto-Regressive with eXogenous input (ARX), Auto-Regressive Moving Average with eXogenous input (ARMAX), Box–Jenkins (BJ), and Transfer Function (TF) models. Performance is assessed using Root Mean Square Error (RMSE), coefficient of determination (R²), robustness index (1/RMSE), and ANOVA statistical analysis. Results demonstrate that the ARX model achieves the best overall performance, with a low global RMSE of 28.6782 and a high global R² of 0.7784 . Finger-wise analysis confirms the superiority of the ARX model, particularly for the thumb and index fingers. ANOVA results further validate the statistical significance of EEG influence on most finger movements, confirming the feasibility of real-time EEG-based prosthetic hand control. EEG prosthetic hand ARX modeling SIMO systems RMSE R² ANOVA real-time control brain–machine interface finger movement prediction Figures Figure 1 Figure 2 Figure 3 Figure 4 1. Introduction Brain–machine interfaces (BMIs) enable the translation of neural signals into control commands, offering promising solutions for rehabilitation and assistive technologies for individuals with motor impairments [ 1 – 5 ]. Among non-invasive techniques, electroencephalography (EEG) is widely used due to its safety, portability, and relatively low cost [ 6 , 7 ]. However, EEG signals are inherently noisy, non-stationary, and highly variable, which makes accurate modeling of motor intentions a challenging task [ 8 , 9 ]. Linear system identification methods such as ARX, ARMAX, and Box–Jenkins models have been extensively used to model dynamic relationships between neural signals and motor outputs [ 10 – 12 ]. In prosthetic hand applications, most studies focus on single-output modeling, while real-world hand movements require the simultaneous control of multiple fingers. This work addresses this limitation by adopting a SIMO modeling framework, where a single EEG input drives multiple finger outputs. The objective is to identify the most suitable model for real-time multi-finger prosthetic control. 2. Methods 2.1. Data Acquisition EEG signals were recorded during actual or imagined finger movements tasks. The output signal correspond to the angular positions of the five fingers: thumb, index, middle, ring, and little finger. The dataset contains 66 samples per signal and is used for both training and validation. 2.2. Modeling Approach Four SIMO models were investigated: ARX (Auto-Regressive with eXogenous input) ARMAX (Auto-Regressive Moving Average with eXogenous input) Box‑Jenkins (BJ) Transfer Function (TF) Model performance was evaluated using: RMSE (Root Mean Square Error): measures prediction accuracy(lower is better), R² (Coefficient of Determination): evaluates goodness of fit ( higher is better), Robustness index (1/RMSE) : higher values indicates improved robustness, ANOVA : tests the statistical significance of EEG influence on each finger. 3. Results 3.1. Global Model Comparison Table 1 Global performance of the models for all five fingers Model Robustness(1/RMSE) Global RMSE Global R 2 ARX 0.0349 28.6782 0.7784 ARMAX 0.0147 67.9355 -0.2433 BJ 0.0328 30.5287 0.7489 TF 0.0155 64.3527 -0.1156 3.2. Finger-wise Performance Table 2 RMSE and R 2 values per finger for each model. Finger RMSE ARX RMSE ARMAX RMSE BJ RMSE TF R 2 ARX R 2 ARMAX R 2 BJ R 2 TF Thumb 14.7152 67.6565 25.0157 64.6890 0.9423 -0.2206 0.8331 -0.1159 Index 3.9330 50.6500 23.5132 66.5545 0.9961 0.3534 0.8606 -0.1165 Middle 34.3564 46.9155 42.4491 60.9582 0.6459 0.3397 0.4595 -0.1147 Ring 35.3186 48.4419 37.8849 62.8236 0.6475 0.3369 0.5944 -0.1153 Little 38.1108 106.7037 15.6263 66.5545 0.6339 -1.8698 0.9385 -0.1165 3.3. Real vs Predicted Finger Angles (Best Model) Figure 3. Real (solid lines) and predicted (dashed lines) finger angles for all fingers using the best-performing ARX model. 3.4. Statistical Analysis: ANOVA Table 3 ANOVA p-values for EEG influence on finger movements. Finger p-value Significant? Thumb 0.0101 Yes Index 0.2063 No Middle 0.0001 Yes Ring 0.0001 Yes Little 0.0001 Yes Figure 4 . ANOVA-based statistical significance analysis of EEG influence on finger movements. Bars represent –log 10 (p-value), and the dashed red line indicates the significance threshold( α = 0.05 ). 4. Discussion The ARX model demonstrated superior performance in terms of both prediction accuracy and robustness. Its simplicity and efficiency make it particularly suitable for real-time EEG-based prosthetic control. The poorer performance of ARMAX and TF models can be attributed to their sensitivity to noise and model complexity [ 10 , 14 ]. These findings are consistent with recent studies emphasizing the effectiveness of linear models in EEG-to-motion mapping [ 6 , 8 , 13 ]. Future improvements may include hybrid EEG–EMG systems or deep learning approaches to further enhance robustness and adaptability [ 15 – 17 ]. 5. Conclusion This study confirms that an ARX-based SIMO model can reliably predict multiple finger movements from a single EEG signal. The model exhibits strong robustness and statistically significant performance for most fingers, supporting its suitability for real-time prosthetic hand control. Future work will focus on deep learning integration and multi-sensor fusion to improve adaptability and precision. Declarations Conflicts of interest: The authors declare that they have no conflict of interest. Ethics approval and compliance with guidelines : This study was approved by the Institutional Ethics Committee for Research of Human Health of the University of Douala (Authorization N04731CEI-Udo/01/2025/T). All methods were carried out in accordance with the relevant guidelines and regulations of this ethics committee. Consent to participate: Informed consent was obtained from the participant. Consent to publish: Not applicable. Funding: This research received no external funding. Author Contribution J.N.M. and L.N.N. conceived and designed the study. J.N.M. performed the experiments and data acquisition. L.N.N. performed the data analysis and modeling. J.N.M. and L.N.N. wrote the manuscript. All authors reviewed and approved the final manuscript. Data Availability Data are available from the corresponding author upon reasonable request. References Li X et al. IEEE Trans Neural Syst Rehabil Eng, 2020. Wang Y et al. Front Neurosci, 2020. Zhang Q et al. Sensors, 2021. Chen L et al. J Neural Eng, 2021. Kumar P et al. Biomed. Signal Process. Control, 2021. Singh R et al. IEEE Access, 2022. Lee H et al. Front Hum Neurosci, 2022. Zhao J et al. Med Biol Eng Comput, 2022. Ahmed S et al. Comput Biol Med, 2023. Park J et al. IEEE Trans Biomed Eng, 2023. Li W et al. Neural Comput Appl, 2023. Wu T et al. J Biomech, 2023. Garcia M et al. Front. Robot. AI, 2024. Tan L et al. Sensors, 2024. Huang Y et al. IEEE Trans Neural Syst Rehabil Eng, 2024. Reddy K et al. Biomed. Signal Process. Control, 2025. Santos A et al. Front Neurosci, 2025. Chen Y et al. J Neural Eng, 2025. Patel V et al. IEEE Access, 2025. Kim D et al. Sensors, 2025. 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-8500934","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":579721983,"identity":"d6cc3b13-7b89-4ba0-ab5b-9ed11c367180","order_by":0,"name":"Jules Ngono Mvondo","email":"data:image/png;base64,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","orcid":"","institution":"University of Douala","correspondingAuthor":true,"prefix":"","firstName":"Jules","middleName":"Ngono","lastName":"Mvondo","suffix":""},{"id":579721986,"identity":"22967fc5-e92b-48f1-b28e-627355e6b578","order_by":1,"name":"Léandre Nneme Nneme","email":"","orcid":"","institution":"University of Douala","correspondingAuthor":false,"prefix":"","firstName":"Léandre","middleName":"Nneme","lastName":"Nneme","suffix":""}],"badges":[],"createdAt":"2026-01-02 12:38:48","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8500934/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8500934/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101195130,"identity":"1484d43c-64e0-40cc-bf6c-444f9a4767ab","added_by":"auto","created_at":"2026-01-27 07:58:15","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":20121,"visible":true,"origin":"","legend":"Global RMSE comparison between ARX, ARMAX, BJ and TF","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8500934/v1/a0e3eee300414d8d1d54903e.png"},{"id":101195107,"identity":"5e5806ce-d829-41e7-b604-c441cb98168a","added_by":"auto","created_at":"2026-01-27 07:58:13","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":21197,"visible":true,"origin":"","legend":"RMSE per finger for each model.","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8500934/v1/813c64f53a275779e9289532.png"},{"id":101195128,"identity":"5c2a64eb-c959-4cde-b77f-2d9a9c1d29d0","added_by":"auto","created_at":"2026-01-27 07:58:14","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":43851,"visible":true,"origin":"","legend":"Real (solid lines) and predicted (dashed lines) finger angles for all fingers using the best-performing ARX model.","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8500934/v1/fa0b3a3faf248c267f8742f1.png"},{"id":101195077,"identity":"304f7d31-5eda-456d-9212-192af754c5de","added_by":"auto","created_at":"2026-01-27 07:58:05","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":28085,"visible":true,"origin":"","legend":"ANOVA significance of EEG influence","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8500934/v1/ca0cd3c64dda8b52e6920502.png"},{"id":106402158,"identity":"7cc6e28a-ce27-464a-a133-acc4cea0d373","added_by":"auto","created_at":"2026-04-08 09:11:21","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":621233,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8500934/v1/ecf1b6f2-1c25-46c1-954d-b00eb9f067d2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Modeling Finger Movements of a Prosthetic Hand from EEG Signals Using ARX SIMO Models","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eBrain\u0026ndash;machine interfaces (BMIs) enable the translation of neural signals into control commands, offering promising solutions for rehabilitation and assistive technologies for individuals with motor impairments [\u003cspan additionalcitationids=\"CR2 CR3 CR4\" citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Among non-invasive techniques, electroencephalography (EEG) is widely used due to its safety, portability, and relatively low cost [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. However, EEG signals are inherently noisy, non-stationary, and highly variable, which makes accurate modeling of motor intentions a challenging task [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eLinear system identification methods such as ARX, ARMAX, and Box\u0026ndash;Jenkins models have been extensively used to model dynamic relationships between neural signals and motor outputs [\u003cspan additionalcitationids=\"CR11\" citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. In prosthetic hand applications, most studies focus on single-output modeling, while real-world hand movements require the simultaneous control of multiple fingers. This work addresses this limitation by adopting a SIMO modeling framework, where a single EEG input drives multiple finger outputs. The objective is to identify the most suitable model for real-time multi-finger prosthetic control.\u003c/p\u003e"},{"header":"2. Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1. Data Acquisition\u003c/h2\u003e \u003cp\u003eEEG signals were recorded during actual or imagined finger movements tasks. The output signal correspond to the angular positions of the five fingers: thumb, index, middle, ring, and little finger. The dataset contains 66 samples per signal and is used for both training and validation.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2. Modeling Approach\u003c/h2\u003e \u003cp\u003eFour SIMO models were investigated:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eARX (Auto-Regressive with eXogenous input)\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eARMAX (Auto-Regressive Moving Average with eXogenous input)\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eBox‑Jenkins (BJ)\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTransfer Function (TF)\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003eModel performance was evaluated using:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eRMSE\u003c/b\u003e (Root Mean Square Error): measures prediction accuracy(lower is better),\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eR\u0026sup2;\u003c/b\u003e (Coefficient of Determination): evaluates goodness of fit ( higher is better),\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eRobustness index (1/RMSE)\u003c/b\u003e: higher values indicates improved robustness,\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eANOVA\u003c/b\u003e: tests the statistical significance of EEG influence on each finger.\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e3.1. Global Model Comparison\u003c/h2\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eGlobal performance of the models for all five fingers\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRobustness(1/RMSE)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eGlobal RMSE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eGlobal R\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eARX\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0349\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e28.6782\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.7784\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eARMAX\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0147\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e67.9355\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e-0.2433\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBJ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0328\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e30.5287\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.7489\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0155\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e64.3527\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e-0.1156\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e3.2. Finger-wise Performance\u003c/h2\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eRMSE and R\u003csup\u003e2\u003c/sup\u003e values per finger for each model.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"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 \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFinger\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRMSE ARX\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRMSE ARMAX\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRMSE BJ\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRMSE TF\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eARX\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eARMAX\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eBJ\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eTF\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThumb\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e14.7152\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e67.6565\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e25.0157\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e64.6890\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9423\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e-0.2206\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8331\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e-0.1159\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIndex\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3.9330\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e50.6500\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e23.5132\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e66.5545\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9961\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3534\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.8606\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e-0.1165\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMiddle\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e34.3564\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e46.9155\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e42.4491\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e60.9582\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.6459\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3397\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.4595\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e-0.1147\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e35.3186\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e48.4419\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e37.8849\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e62.8236\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.6475\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.3369\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.5944\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e-0.1153\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLittle\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e38.1108\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e106.7037\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e15.6263\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e66.5545\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.6339\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e-1.8698\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.9385\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e-0.1165\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e3.3. Real vs Predicted Finger Angles (Best Model)\u003c/h2\u003e \u003cp\u003eFigure 3. Real (solid lines) and predicted (dashed lines) finger angles for all fingers using the best-performing ARX model.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e3.4. Statistical Analysis: ANOVA\u003c/h2\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eANOVA p-values for EEG influence on finger movements.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\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=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFinger\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ep-value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSignificant?\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThumb\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0101\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIndex\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.2063\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMiddle\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRing\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLittle\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. ANOVA-based statistical significance analysis of EEG influence on finger movements. Bars represent \u0026ndash;log\u003csub\u003e10\u003c/sub\u003e(p-value), and the dashed red line indicates the significance threshold(\u003cb\u003eα\u0026thinsp;=\u0026thinsp;0.05\u003c/b\u003e).\u003c/p\u003e \u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eThe ARX model demonstrated superior performance in terms of both prediction accuracy and robustness. Its simplicity and efficiency make it particularly suitable for real-time EEG-based prosthetic control. The poorer performance of ARMAX and TF models can be attributed to their sensitivity to noise and model complexity [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. These findings are consistent with recent studies emphasizing the effectiveness of linear models in EEG-to-motion mapping [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Future improvements may include hybrid EEG\u0026ndash;EMG systems or deep learning approaches to further enhance robustness and adaptability [\u003cspan additionalcitationids=\"CR16\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e"},{"header":"5. Conclusion","content":"\u003cp\u003eThis study confirms that an ARX-based SIMO model can reliably predict multiple finger movements from a single EEG signal. The model exhibits strong robustness and statistically significant performance for most fingers, supporting its suitability for real-time prosthetic hand control. Future work will focus on deep learning integration and multi-sensor fusion to improve adaptability and precision.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eConflicts of interest:\u003c/h2\u003e \u003cp\u003eThe authors declare that they have no conflict of interest.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eEthics approval\u003c/strong\u003e \u003cp\u003e \u003cb\u003eand compliance with guidelines\u003c/b\u003e: This study was approved by the Institutional Ethics Committee for Research of Human Health of the University of Douala (Authorization N04731CEI-Udo/01/2025/T). All methods were carried out in accordance with the relevant guidelines and regulations of this ethics committee.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eConsent to participate:\u003c/strong\u003e \u003cp\u003eInformed consent was obtained from the participant.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eConsent to publish:\u003c/strong\u003e \u003cp\u003eNot applicable.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding:\u003c/h2\u003e \u003cp\u003eThis research received no external funding.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eJ.N.M. and L.N.N. conceived and designed the study. J.N.M. performed the experiments and data acquisition. L.N.N. performed the data analysis and modeling. J.N.M. and L.N.N. wrote the manuscript. All authors reviewed and approved the final manuscript.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eData are available from the corresponding author upon reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eLi X et al. IEEE Trans Neural Syst Rehabil Eng, 2020.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang Y et al. Front Neurosci, 2020.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang Q et al. Sensors, 2021.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen L et al. J Neural Eng, 2021.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKumar P et al. Biomed. Signal Process. Control, 2021.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSingh R et al. IEEE Access, 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee H et al. Front Hum Neurosci, 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao J et al. Med Biol Eng Comput, 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAhmed S et al. Comput Biol Med, 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePark J et al. IEEE Trans Biomed Eng, 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi W et al. Neural Comput Appl, 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu T et al. J Biomech, 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGarcia M et al. Front. Robot. AI, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTan L et al. Sensors, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang Y et al. IEEE Trans Neural Syst Rehabil Eng, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eReddy K et al. Biomed. Signal Process. Control, 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSantos A et al. Front Neurosci, 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen Y et al. J Neural Eng, 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePatel V et al. IEEE Access, 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim D et al. Sensors, 2025.\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":"EEG, prosthetic hand, ARX modeling, SIMO systems, RMSE, R², ANOVA, real-time control, brain–machine interface, finger movement prediction","lastPublishedDoi":"10.21203/rs.3.rs-8500934/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8500934/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study presents a comparative modeling analysis of a prosthetic hand controlled by electroencephalographic (EEG) signals. A Single Input Multiple Output (SIMO) framework is adopted, where a single EEG signal is used to predict the movements of five fingers (thumb, index, middle, ring, and little finger). Four dynamic models are evaluated: Auto-Regressive with eXogenous input (ARX), Auto-Regressive Moving Average with eXogenous input (ARMAX), Box\u0026ndash;Jenkins (BJ), and Transfer Function (TF) models. Performance is assessed using Root Mean Square Error (RMSE), coefficient of determination (R\u0026sup2;), robustness index (1/RMSE), and ANOVA statistical analysis. Results demonstrate that the ARX model achieves the best overall performance, with a low global \u003cb\u003eRMSE of 28.6782\u003c/b\u003e and a high global \u003cb\u003eR\u0026sup2; of 0.7784\u003c/b\u003e. Finger-wise analysis confirms the superiority of the ARX model, particularly for the thumb and index fingers. ANOVA results further validate the statistical significance of EEG influence on most finger movements, confirming the feasibility of real-time EEG-based prosthetic hand control.\u003c/p\u003e","manuscriptTitle":"Modeling Finger Movements of a Prosthetic Hand from EEG Signals Using ARX SIMO Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-27 07:57:24","doi":"10.21203/rs.3.rs-8500934/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":"42896988-276e-4b35-92c3-e2c84db9bbe1","owner":[],"postedDate":"January 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-03T12:09:56+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-27 07:57:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8500934","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8500934","identity":"rs-8500934","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}