Deep Learning for Motion Classification in Ankle Exoskeletons Using Surface EMG and IMU Signals

Deep Learning for Motion Classification in Ankle Exoskeletons Using Surface EMG and IMU Signals | 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 Article Deep Learning for Motion Classification in Ankle Exoskeletons Using Surface EMG and IMU Signals Silas Ruhrberg Estévez, Josée Mallah, Dominika Kazieczko, Chenyu Tang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5446652/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 Ankle exoskeletons have garnered considerable interest for their potential to enhance mobility and reduce fall risks, particularly among the aging population. The efficacy of these devices relies on accurate real-time prediction of the user’s intended movements through sensor-based inputs. This paper presents a novel motion prediction framework that integrates three Inertial Measurement Units (IMUs) and eight surface Electromyography (sEMG) sensors to capture both kinematic and muscular activity data. A comprehensive set of activities, representative of everyday movements in barrier-free environments, was recorded for the purpose. Our findings reveal that Convolutional Neural Networks (CNNs) slightly outperform Long Short-Term Memory (LSTM) networks on a dataset of five motion tasks, achieving classification accuracies of 96.5°æ0.8% and 87.5°æ2.9%, respectively. Furthermore, we demonstrate the system’s proficiency in transfer learning, enabling accurate motion classification for new subjects using just ten samples per class for finetuning. The robustness of the model is demonstrated by its resilience to sensor failures resulting in absent signals, maintaining reliable performance in real-world scenarios. These results underscore the potential of deep learning algorithms to enhance the functionality and safety of ankle exoskeletons, ultimately improving their usability in daily life. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Nanoscience and technology/Graphene/Electronic properties and devices Full Text 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-5446652","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":382876869,"identity":"5d346334-689a-4740-97f0-16aa40d2dab3","order_by":0,"name":"Silas Ruhrberg Estévez","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Silas","middleName":"Ruhrberg","lastName":"Estévez","suffix":""},{"id":382876870,"identity":"57ef7d5d-af29-460b-bfc8-4d1aed4a7dda","order_by":1,"name":"Josée Mallah","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Josée","middleName":"","lastName":"Mallah","suffix":""},{"id":382876871,"identity":"f234f1b1-70bb-4ae6-b935-cb53693b64e3","order_by":2,"name":"Dominika Kazieczko","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Dominika","middleName":"","lastName":"Kazieczko","suffix":""},{"id":382876872,"identity":"d7078d41-49fb-4e10-8dfc-603f09f4b365","order_by":3,"name":"Chenyu Tang","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Chenyu","middleName":"","lastName":"Tang","suffix":""},{"id":382876873,"identity":"6200ad7b-e176-4c8e-b6ca-c8326e0f9fe5","order_by":4,"name":"Luigi Giuseppe Occhipinti","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvUlEQVRIiWNgGAWjYBACPgYGxocfKuD8BMJa2BgYmI0lzpCohU2Ct40kLfyLD0hIzrOT121gfviBsS2NCC0SzxIMCrclG247wGYswdiWQ4yWMwYJktsOMG47wGDGwNhWQZyWA7xzDthvO8D+jUgt/D2GDbwNBxK3HeAB2UKUw9iSmSWOJSdvO8xTLJFwjgjv8/MfPv7zQ42d7bbj7Rs/fChLJqyFQSIBymBmICpWQNYcIErZKBgFo2AUjGQAAFgCNTFpaMgHAAAAAElFTkSuQmCC","orcid":"","institution":"University of Cambridge","correspondingAuthor":true,"prefix":"","firstName":"Luigi","middleName":"Giuseppe","lastName":"Occhipinti","suffix":""}],"badges":[],"createdAt":"2024-11-13 11:38:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5446652/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5446652/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":70491394,"identity":"accd56d5-9481-44c1-8a48-0259d4a69519","added_by":"auto","created_at":"2024-12-03 17:09:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":597771,"visible":true,"origin":"","legend":"","description":"","filename":"DeepLearningforMotionClassificationinAnkleExoskeletons.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5446652/v1_covered_4c33c994-02b7-48f6-bdf0-4442f0b40387.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Learning for Motion Classification in Ankle Exoskeletons Using Surface EMG and IMU Signals","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","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":"","lastPublishedDoi":"10.21203/rs.3.rs-5446652/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5446652/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Ankle exoskeletons have garnered considerable interest for their potential to enhance mobility and reduce fall risks, particularly among the aging population. The efficacy of these devices relies on accurate real-time prediction of the user’s intended movements through sensor-based inputs. This paper presents a novel motion prediction framework that integrates three Inertial Measurement Units (IMUs) and eight surface Electromyography (sEMG) sensors to capture both kinematic and muscular activity data. A comprehensive set of activities, representative of everyday movements in barrier-free environments, was recorded for the purpose. Our findings reveal that Convolutional Neural Networks (CNNs) slightly outperform Long Short-Term Memory (LSTM) networks on a dataset of five motion tasks, achieving classification accuracies of 96.5°æ0.8% and 87.5°æ2.9%, respectively. Furthermore, we demonstrate the system’s proficiency in transfer learning, enabling accurate motion classification for new subjects using just ten samples per class for finetuning. The robustness of the model is demonstrated by its resilience to sensor failures resulting in absent signals, maintaining reliable performance in real-world scenarios. These results underscore the potential of deep learning algorithms to enhance the functionality and safety of ankle exoskeletons, ultimately improving their usability in daily life.","manuscriptTitle":"Deep Learning for Motion Classification in Ankle Exoskeletons Using Surface EMG and IMU Signals","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-02 02:48:48","doi":"10.21203/rs.3.rs-5446652/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":"35ebf0d7-f3aa-46e2-b4f8-a3bf154913eb","owner":[],"postedDate":"December 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":40779051,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":40779052,"name":"Physical sciences/Nanoscience and technology/Graphene/Electronic properties and devices"}],"tags":[],"updatedAt":"2025-01-24T04:53:26+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-02 02:48:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5446652","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5446652","identity":"rs-5446652","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}