Bidirectional Cross-Task Transfer Learning for Gait Phase Prediction in Frail Older Adults Using Wearable Sensors

Bidirectional Cross-Task Transfer Learning for Gait Phase Prediction in Frail Older Adults Using Wearable Sensors | 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 Bidirectional Cross-Task Transfer Learning for Gait Phase Prediction in Frail Older Adults Using Wearable Sensors Peng Wu, Jiachen Wang, Ziyun Ding, Yibin Li, Rui Song, Huanghe Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8333737/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 Transfer learning has been widely applied to gait analysis using wearable sensors to address data scarcity and improve model generalization. However, existing approaches predominantly focus on intra-task transfer (classification-to-classification or regression-to-regression), while cross-task transfer between fundamentally different learning objectives remains largely unexplored. This study proposes a novel bidirectional cross-task transfer learning framework to jointly improve both classification and regression performance in wearable-sensor-based gait analysis. As a proof of concept, we establish knowledge transfer between continuous gait cycle percentage prediction (regression) and discrete gait phase classification using the GSTRIDE dataset of frail older adults. Bidirectional transfer is implemented through end-to-end fine-tuning of deep neural network and Transformer architectures augmented with attention mechanisms. Experimental results demonstrate that model-level transfer yields an F1-score of 0.9778 (a 4.13% improvement) for gait phase classification and a mean absolute error (MAE) of 0.0358 for gait cycle percentage prediction (a 10.9% improvement) compared with models trained without transfer, while feature-level transfer provides a computationally efficient alternative with comparable performance. The proposed bidirectional framework shows strong potential for practical deployment in wearable systems, enabling widespread applications in fall risk assessment, rehabilitation monitoring, and early detection of neurodegenerative diseases in aging populations. Gait analysis Wearable sensor Transfer learning Bidirectional Cross-task Frail Older Adults 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-8333737","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":558919736,"identity":"3a2f2055-853a-4f60-a14c-825d9dbbe115","order_by":0,"name":"Peng Wu","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Wu","suffix":""},{"id":558919737,"identity":"db5ccf0d-1583-47af-b9d0-24637737f195","order_by":1,"name":"Jiachen Wang","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Jiachen","middleName":"","lastName":"Wang","suffix":""},{"id":558919738,"identity":"88695528-67c1-4e26-a3e2-7c44d58fe37a","order_by":2,"name":"Ziyun Ding","email":"","orcid":"","institution":"University of Birmingham","correspondingAuthor":false,"prefix":"","firstName":"Ziyun","middleName":"","lastName":"Ding","suffix":""},{"id":558919739,"identity":"71fa6371-873b-46cd-8ea1-e4de8ef0ce51","order_by":3,"name":"Yibin Li","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Yibin","middleName":"","lastName":"Li","suffix":""},{"id":558919740,"identity":"16e8fcaf-f476-4dcc-92e2-b6470077e498","order_by":4,"name":"Rui Song","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Song","suffix":""},{"id":558919741,"identity":"e8513394-4ef7-4afc-af27-5922ffaa7b8c","order_by":5,"name":"Huanghe Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABA0lEQVRIiWNgGAWjYDACCSBmbACxeBgYPjAwg1gGxGthnEGyFmYeYrTIz25+9vDrjsPy5vxrDz62+WOd2MDevE2CoeYOTi2Mc46ZG8ueOWy4c8a7ZOPctvTEBp5jZRIMx57h1MIskWAmLdl2mHHDjTNm0rkNhxMbJHLMJBgbDuPUwiaR/g2kxR6oxfy3xR+gFvk3+LXwAM2U/Nh2OHHD+R4zZgY2kC08+LVISOSUSTO2pSdvuMFjLNnblm7cxpNWbJFwDLcW+Rnp2yR/tlnbbjh/xvDDjz/Wsv3shzfe+FCDWws4CHjA9iVAfQciEvBqAAb0DxDJf4CAslEwCkbBKBixAABScFbZK4+1dgAAAABJRU5ErkJggg==","orcid":"","institution":"Shandong University","correspondingAuthor":true,"prefix":"","firstName":"Huanghe","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-12-11 07:23:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8333737/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8333737/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98299084,"identity":"4135aa57-e97a-4a25-a2e3-24cb8a2fa2ce","added_by":"auto","created_at":"2025-12-16 09:50:27","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7320,"visible":true,"origin":"","legend":"","description":"","filename":"860aadc4ed8f443dab357548c9db29bb.json","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/0b61313c6fa2a953373ba07d.json"},{"id":98434583,"identity":"67c16193-e0dc-4092-b402-642b5e6e35a3","added_by":"auto","created_at":"2025-12-17 16:52:22","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":111838,"visible":true,"origin":"","legend":"","description":"","filename":"860aadc4ed8f443dab357548c9db29bb1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/6f02ba7c4c568c5d2d2a8123.xml"},{"id":98299086,"identity":"c311e228-735e-449e-9bc2-d3cfa8328db7","added_by":"auto","created_at":"2025-12-16 09:50:27","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1654809,"visible":true,"origin":"","legend":"","description":"","filename":"BidirectionalCrossTaskTransferLearningforGaitPhasePredictioninFrailOlderAdultsUsingWearableSensors.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/9b43971cafbb0f55e289671f.pdf"},{"id":98434957,"identity":"4abf55b1-931a-4dd0-b2ff-3eb3dc0f2c50","added_by":"auto","created_at":"2025-12-17 16:52:49","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2466726,"visible":true,"origin":"","legend":"","description":"","filename":"bidirectionaltransferfinal.png","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/111beb9058c190bd79b44450.png"},{"id":98436346,"identity":"b317a997-5040-44b0-9f88-adf3d491f586","added_by":"auto","created_at":"2025-12-17 16:55:27","extension":"eps","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/6c8defd5ddb0e5f10bce4598.eps"},{"id":98299094,"identity":"c317cbac-3c65-4435-a3c6-a22b7dc8bcf6","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":59781,"visible":true,"origin":"","legend":"","description":"","filename":"f1.png","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/b0c48fcab102988e428eb787.png"},{"id":98434945,"identity":"4fa40acc-ee3a-4233-98c8-a9796307c418","added_by":"auto","created_at":"2025-12-17 16:52:48","extension":"eps","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/af52fd6e4cef2eccbc12c6d3.eps"},{"id":98299091,"identity":"db6eb017-5614-4a91-b509-c71106b07787","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":728386,"visible":true,"origin":"","legend":"","description":"","filename":"figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/14f5ede3592c40fce6bdb099.png"},{"id":98299085,"identity":"bd70481a-3632-4741-a8a2-3dc12303dd32","added_by":"auto","created_at":"2025-12-16 09:50:27","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50112,"visible":true,"origin":"","legend":"","description":"","filename":"mae.png","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/04ae43e2f7e6a652028a1e17.png"},{"id":98437134,"identity":"a71a46e4-d328-4543-b778-bd4c0086fa8b","added_by":"auto","created_at":"2025-12-17 16:57:01","extension":"bst","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/2962dbdb24419b422e84b82e.bst"},{"id":98299101,"identity":"b592749d-76c4-4f07-982e-e9278cadfa77","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"bst","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/c349b1e595bd474e9ca7cccc.bst"},{"id":98435634,"identity":"45efe81a-ff37-41f7-97fd-54f3d8e32a66","added_by":"auto","created_at":"2025-12-17 16:54:09","extension":"pdf","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/3288ca950d350385d4427455.pdf"},{"id":98299099,"identity":"d02a6f86-722d-48e5-952f-3131c048d0dd","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/30cccfd7558acdc6a877c8b7.bst"},{"id":98435815,"identity":"3f6edaa3-5b74-4596-bbf7-9e1cdf6e050b","added_by":"auto","created_at":"2025-12-17 16:54:27","extension":"bst","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/5746eff824834d9144953ae6.bst"},{"id":98436825,"identity":"65e0381d-6535-4bf6-b9e4-9066f93dc2e1","added_by":"auto","created_at":"2025-12-17 16:56:18","extension":"cls","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/88ce3a6484e9a0b57113dd9d.cls"},{"id":98299102,"identity":"c20e6c8e-0c8e-412f-892b-e717b231fe3d","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/9147d9edc65d1b766eeb0922.bst"},{"id":98299090,"identity":"6e1c109c-64e3-4a2b-8813-926986e0bcbb","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/e1ccbc5556117dce6b0a610f.bst"},{"id":98436101,"identity":"44dc9bcf-b2fc-4d79-a27a-f5b5224c05a7","added_by":"auto","created_at":"2025-12-17 16:54:56","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/7cb67f5fae9eee4ca0f1337b.bst"},{"id":98299088,"identity":"03fc4413-1f72-4d84-8d76-171589480d45","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/fab1332ce723de8f2ccb75c8.bst"},{"id":98299089,"identity":"d61bbb2c-c122-4d3d-acdd-096b4eff5af4","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"bst","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/eda9f004089cf45fab4a6552.bst"},{"id":98299100,"identity":"14daf598-25fe-4b6b-b9bf-9d994a92403c","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"pdf","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/25991028941f18ebd6bf65a7.pdf"},{"id":98299097,"identity":"f83eea25-7d88-4eaf-a929-bbeea2183ca6","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"xml","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119520,"visible":true,"origin":"","legend":"","description":"","filename":"860aadc4ed8f443dab357548c9db29bb1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/958d4456cb6b0079a431a77c.xml"},{"id":98299106,"identity":"a07ccb60-6375-4129-8b37-03c4918851cc","added_by":"auto","created_at":"2025-12-16 09:50:28","extension":"html","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":127717,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1/df4fa8614bff3f9bb363ffd1.html"},{"id":98778455,"identity":"7418423a-4885-4bd6-87d1-a0692c48a661","added_by":"auto","created_at":"2025-12-22 12:29:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1251980,"visible":true,"origin":"","legend":"","description":"","filename":"BidirectionalCrossTaskTransferLearningforGaitPhasePredictioninFrailOlderAdultsUsingWearableSensors.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8333737/v1_covered_65c288d0-00dd-47fd-ad79-acf22527999d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Bidirectional Cross-Task Transfer Learning for Gait Phase Prediction in Frail Older Adults Using Wearable Sensors","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Gait analysis, Wearable sensor, Transfer learning, Bidirectional Cross-task, Frail Older Adults","lastPublishedDoi":"10.21203/rs.3.rs-8333737/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8333737/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTransfer learning has been widely applied to gait analysis using wearable sensors to address data scarcity and improve model generalization. However, existing approaches predominantly focus on intra-task transfer (classification-to-classification or regression-to-regression), while cross-task transfer between fundamentally different learning objectives remains largely unexplored. This study proposes a novel bidirectional cross-task transfer learning framework to jointly improve both classification and regression performance in wearable-sensor-based gait analysis. As a proof of concept, we establish knowledge transfer between continuous gait cycle percentage prediction (regression) and discrete gait phase classification using the GSTRIDE dataset of frail older adults. Bidirectional transfer is implemented through end-to-end fine-tuning of deep neural network and Transformer architectures augmented with attention mechanisms. Experimental results demonstrate that model-level transfer yields an F1-score of 0.9778 (a 4.13% improvement) for gait phase classification and a mean absolute error (MAE) of 0.0358 for gait cycle percentage prediction (a 10.9% improvement) compared with models trained without transfer, while feature-level transfer provides a computationally efficient alternative with comparable performance. The proposed bidirectional framework shows strong potential for practical deployment in wearable systems, enabling widespread applications in fall risk assessment, rehabilitation monitoring, and early detection of neurodegenerative diseases in aging populations.\u003c/p\u003e","manuscriptTitle":"Bidirectional Cross-Task Transfer Learning for Gait Phase Prediction in Frail Older Adults Using Wearable Sensors","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-16 09:50:19","doi":"10.21203/rs.3.rs-8333737/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":"b9132369-1607-4109-a422-220fda4208b4","owner":[],"postedDate":"December 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-22T09:55:53+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-16 09:50:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8333737","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8333737","identity":"rs-8333737","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}