Transformer-Based Recognition of Activities of Daily Living from Wearable Sensor Data

Transformer-Based Recognition of Activities of Daily Living from Wearable Sensor Data | 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 Transformer-Based Recognition of Activities of Daily Living from Wearable Sensor Data GABRIELA AUGUSTINOV, MUHAMMAD ADEEL NISAR, FRÉDÉRIC LI, AMIR TABATABAEI, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2015249/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 Smart support systems for the recognition of Activities of Daily Living (ADLs) can help elderly people live independently for longer improving their standard of living. Many machine learning approaches have been proposed lately for Human Activity Recognition (HAR), including elaborated networks that contain convolutional, recurrent, and attentive layers. The ubiquity of wearable devices has provided an increasing amount of time-series data that can be used for such applications in an unobtrusive manner. But there are not many studies on the performance of the attention-based Transformer model in HAR, especially not for complex activities such as ADLs. This work implements and evaluates the novel self-attention Transformer model for the classification of ADLs and compares it to the already well-established approach of recurrent Long-Short Term Memory (LSTM) networks. The proposed method is a two-level hierarchical model, in which atomic activities are initially recognized in the first step and their probability scores are extracted and utilized for the Transformer-based classification of seven more complex ADLs in the second step. The Transformer is used at the second step to classify seven ADLs. Our results show that the Transformer model reaches the same performance and even outperforms LSTM networks cleary in the subject-dependent configuration (73.36 % and 69.09 %), while relying only on attention-mechanism to depict global dependencies between input and output without the need to use any recurrence. The proposed model was tested using two different segment lengths, indicating its effectiveness in learning long-range dependencies of shorter actions in complex activities. Artificial Intelligence and Machine Learning transformer human activity recognition atomic activities activities of daily living attention lstm neural networks Full Text Declarations Competing interests: The authors declare no competing interests. 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-2015249","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":132927416,"identity":"9aa1cd80-06b4-4d16-8a30-836e41ae43c4","order_by":0,"name":"GABRIELA AUGUSTINOV","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0001-9443-7825","institution":"Institute of Medical Informatics, University of Lübeck, Germany","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"GABRIELA","middleName":"","lastName":"AUGUSTINOV","suffix":""},{"id":132927417,"identity":"fb14e8e5-8eb7-4987-94ac-0a1a4b75afd9","order_by":1,"name":"MUHAMMAD ADEEL NISAR","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"MUHAMMAD","middleName":"ADEEL","lastName":"NISAR","suffix":""},{"id":132927418,"identity":"d4248ce5-0bae-48de-a9f3-37b341e164d0","order_by":2,"name":"FRÉDÉRIC LI","email":"","orcid":"","institution":"Institute of Medical Informatics, University of Lübeck, Germany","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"FRÉDÉRIC","middleName":"","lastName":"LI","suffix":""},{"id":132927419,"identity":"e7d2047f-edfd-4532-ab96-d904fe57f452","order_by":3,"name":"AMIR TABATABAEI","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"AMIR","middleName":"","lastName":"TABATABAEI","suffix":""},{"id":132927420,"identity":"9222a8b6-87ee-4890-9e27-327d25841c30","order_by":4,"name":"MARCIN GRZEGORZEK","email":"","orcid":"","institution":"Institute of Medical Informatics, University of Lübeck, Germany","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"MARCIN","middleName":"","lastName":"GRZEGORZEK","suffix":""},{"id":132927421,"identity":"fbb5c54b-8a63-4a35-ba90-5be7eefe0fe5","order_by":5,"name":"KEYWAN SOHRABI","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"KEYWAN","middleName":"","lastName":"SOHRABI","suffix":""},{"id":132927422,"identity":"c8d82aa1-306b-45c7-b168-4b53932cb57b","order_by":6,"name":"Sebastian Fudickar","email":"","orcid":"https://orcid.org/0000-0002-3553-5131","institution":"Institute of Medical Informatics, University of Lübeck, Germany","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Sebastian","middleName":"","lastName":"Fudickar","suffix":""}],"badges":[],"createdAt":"2022-08-30 19:48:40","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":true,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false,"coiExplicitlySet":false},"doi":"10.21203/rs.3.rs-2015249/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2015249/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":26001176,"identity":"a6cba050-9bfc-4a33-9688-71067544dd27","added_by":"auto","created_at":"2022-09-02 17:37:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":828125,"visible":true,"origin":"","legend":"","description":"","filename":"TransformerBasedArxivRecognitionofActivitiesofDailyLivingfromWearableSensorDataCopy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2015249/v1_covered.pdf"}],"financialInterests":"","formattedTitle":"\u003cp\u003eTransformer-Based Recognition of Activities of Daily Living from Wearable Sensor Data\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-2015249/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."},{"header":"Declarations","content":"Competing interests: The authors declare no competing interests."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Lübeck","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"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":"transformer, human activity recognition, atomic activities, activities of daily living, attention, lstm, neural networks","lastPublishedDoi":"10.21203/rs.3.rs-2015249/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2015249/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSmart support systems for the recognition of Activities of Daily Living (ADLs) can help elderly people live independently for longer improving their standard of living. Many machine learning approaches have been proposed lately for Human Activity Recognition (HAR), including elaborated networks that contain convolutional, recurrent, and attentive layers. The ubiquity of wearable devices has provided an increasing amount of time-series data that can be used for such applications in an unobtrusive manner. But there are not many studies on the performance of the attention-based Transformer model in HAR, especially not for complex activities such as ADLs. This work implements and evaluates the novel self-attention Transformer model for the classification of ADLs and compares it to the already well-established approach of recurrent Long-Short Term Memory (LSTM) networks. The proposed method is a two-level hierarchical model, in which atomic activities are initially recognized in the first step and their probability scores are extracted and utilized for the Transformer-based classification of seven more complex ADLs in the second step. The Transformer is used at the second step to classify seven ADLs. Our results show that the Transformer model reaches the same performance and even outperforms LSTM networks cleary in the subject-dependent configuration (73.36 % and 69.09 %), while relying only on attention-mechanism to depict global dependencies between input and output without the need to use any recurrence. The proposed model was tested using two different segment lengths, indicating its effectiveness in learning long-range dependencies of shorter actions in complex activities.\u0026nbsp;\u003c/p\u003e","manuscriptTitle":"Transformer-Based Recognition of Activities of Daily Living from Wearable Sensor Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-09-02 17:37:30","doi":"10.21203/rs.3.rs-2015249/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":"ff7d4147-0145-4070-8f89-c446dddda08d","owner":[],"postedDate":"September 2nd, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":15167373,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2022-09-02T17:37:30+00:00","versionOfRecord":[],"versionCreatedAt":"2022-09-02 17:37:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-2015249","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2015249","identity":"rs-2015249","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}