Cost-Effective Prediction of Knee Joint Angle from Surface Electromyography Signals During Free Motion using Transformer Regression

Cost-Effective Prediction of Knee Joint Angle from Surface Electromyography Signals During Free Motion using Transformer Regression | 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 Cost-Effective Prediction of Knee Joint Angle from Surface Electromyography Signals During Free Motion using Transformer Regression Aaron Xiong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8100497/v4 This work is licensed under a CC BY 4.0 License Status: Posted Version 4 posted You are reading this latest preprint version Show more versions Abstract This paper outlines a proof-of-concept for the precise forecasting, using a Time-Series Transformer (TST) regression framework, of the angle of the knee joint based on Surface Electromyography (sEMG) data from just three sensors on the upper thigh. To facilitate real-time prediction, the Transformer was given a hybrid input of autoregressive and exogenous data from two Inertial Measurement Units (IMUs) and the three sEMG sensors. Furthermore, the flexibility of a Transformer Model meant that the data could be continuously recorded during spontaneous, unplanned motion of the lower leg. A sliding-window approach was used to allow the model to continuously predict from a stream of live data. The model achieved high cross-validation accuracy (70-15-15 split) predicting the knee joint angle (in degrees) on a relatively small dataset of 35,613 samples--RMSE=3.97, nRMSE=0.0208, MAE=2.61, MBE=-0.45, Adjusted R 2 = 0.9928 on unseen data--and outperformed benchmarks set by state-of-the-art methods, such as CNN and LSTM, while making use of fewer sensors and demonstrating sub-millisecond prediction time per sample. Additionally, the limited number of sensors and equipment used in this method allows for greater accessibility to patients in need. Artificial Intelligence and Machine Learning Biomedical Engineering Transformer Time-series Regression Surface Electromyography Joint Angle Forecasting Wearable Sensors Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 4 posted You are reading this latest preprint version Show more versions 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-8100497","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":550138513,"identity":"baf0d752-519c-46f6-8f75-095fd29bb4aa","order_by":0,"name":"Aaron Xiong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYJCCA0Asx8bMfPABkMHDR6wWY372tmQDkBY2Ym1KnNlzxkwCxCKohb/9jOGBjztqGTfcSEur/JpjJ8PGwPzw0Q08WiTOpCUcnHnmOLPBjeRjt2W3JQMdxmZsnIPXI8kHDvO2HWMzANpyW3IbM1ALD5s0Pi3y5x82gLTwGNzIMSuW3FZPWAvQPSBbaiQkgd5n/LjtMGEthjeeAf3SdsAAFMjSjNuO87AxE/CL3Pkc4w8f2+rq24BR+fHntmp7fvbmh4/xeh8CDoNJZh4wSVg5CNSBScYfxKkeBaNgFIyCEQYANOhNzHRJCv8AAAAASUVORK5CYII=","orcid":"","institution":"Spring Branch Academic Institute","correspondingAuthor":true,"prefix":"","firstName":"Aaron","middleName":"","lastName":"Xiong","suffix":""}],"badges":[],"createdAt":"2025-11-13 02:05:19","currentVersionCode":4,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8100497/v4","doiUrl":"https://doi.org/10.21203/rs.3.rs-8100497/v4","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98430071,"identity":"d910c55b-0cc1-497a-9bdb-728a3e74ccc0","added_by":"auto","created_at":"2025-12-17 16:44:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":468303,"visible":true,"origin":"","legend":"","description":"","filename":"CostEffectivesEMGTransformerJointAnglePrediction4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8100497/v4_covered_a79ec354-2785-4f16-b686-cf7438732f19.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Cost-Effective Prediction of Knee Joint Angle from Surface Electromyography Signals During Free Motion using Transformer Regression","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Spring Branch Academic Institute","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"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":"Transformer, Time-series Regression, Surface Electromyography, Joint Angle Forecasting, Wearable Sensors","lastPublishedDoi":"10.21203/rs.3.rs-8100497/v4","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8100497/v4","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper outlines a proof-of-concept for the precise forecasting, using a Time-Series Transformer (TST) regression framework, of the angle of the knee joint based on Surface Electromyography (sEMG) data from just three sensors on the upper thigh. To facilitate real-time prediction, the Transformer was given a hybrid input of autoregressive and exogenous data from two Inertial Measurement Units (IMUs) and the three sEMG sensors. Furthermore, the flexibility of a Transformer Model meant that the data could be continuously recorded during spontaneous, unplanned motion of the lower leg. A sliding-window approach was used to allow the model to continuously predict from a stream of live data. The model achieved high cross-validation accuracy (70-15-15 split) predicting the knee joint angle (in degrees) on a relatively small dataset of 35,613 samples--RMSE=3.97, nRMSE=0.0208, \u0026nbsp;MAE=2.61, MBE=-0.45, Adjusted R\u003csup\u003e2\u003c/sup\u003e\u003csup\u003e\u003csub\u003e \u003c/sub\u003e\u003c/sup\u003e= 0.9928 on unseen data--and outperformed benchmarks set by state-of-the-art methods, such as CNN and LSTM, while making use of fewer sensors and demonstrating sub-millisecond prediction time per sample. Additionally, the limited number of sensors and equipment used in this method allows for greater accessibility to patients in need.\u003c/p\u003e","manuscriptTitle":"Cost-Effective Prediction of Knee Joint Angle from Surface Electromyography Signals During Free Motion using Transformer Regression","msid":"","msnumber":"","nonDraftVersions":[{"code":4,"date":"2025-12-12 20:33:32","doi":"10.21203/rs.3.rs-8100497/v4","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}},{"code":3,"date":"2025-11-24 18:55:22","doi":"10.21203/rs.3.rs-8100497/v3","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}},{"code":2,"date":"2025-11-20 20:40:03","doi":"10.21203/rs.3.rs-8100497/v2","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}},{"code":1,"date":"2025-11-14 04:08:37","doi":"10.21203/rs.3.rs-8100497/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":"717d3a43-2824-4bb8-ac75-a5d5c6380cdd","owner":[],"postedDate":"December 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58533817,"name":"Artificial Intelligence and Machine Learning"},{"id":58533818,"name":"Biomedical Engineering"}],"tags":[],"updatedAt":"2025-11-14T04:08:37+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-12 20:33:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v4","identity":"rs-8100497","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8100497","identity":"rs-8100497","version":["v4"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}