Unsupervised inference of driving behavior primitives considering feature correlations and temporal dynamics

Unsupervised inference of driving behavior primitives considering feature correlations and temporal dynamics | 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 Unsupervised inference of driving behavior primitives considering feature correlations and temporal dynamics Wenyu Kang, Xuelian Zheng, Yuanyuan Ren, Xiansheng Li, Biao Liang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6299556/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 As the smallest units of driving behavior, driving behavior primitive plays a crucial role in understanding driving dynamics. To better align the inferred driving behavior primitives with real-world driving scenarios, this paper proposes an unsupervised method consisting of two key stages: data segmentation and segments clustering. In data segmentation, a Hierarchical Bayesian Model-based Agglomerative Sequence Segmentation (H-BMASS) model is introduced to accurately capture the change points of variables across different dimensions, thereby avoiding under-segmentation issue that occurs when BMASS is applied to multivariate time series. In segments clustering, to address the limitation of LDA in capturing temporal dynamics in time series data, an Integrating Distribution- and Trend-based Latent Dirichlet Allocation (IDT-LDA) model is proposed. This model incorporates the change trend of data points to capture the temporal dynamics, determined by the derivatives and fluctuations. Compared to conventional BMASS, H-BMASS effectively identifies the change points of driving behavior, with clear structural differences between adjacent segments. Compared to the primitives obtained using Distribution-based LDA, the primitives clustered using IDT-LDA exhibit improved inter-class separability and enhanced interpretability. This unsupervised framework offers an effective method for inferring driving behavior primitives, which will benefit the development of AVs and ADASs. Physical sciences/Mathematics and computing/Applied mathematics Physical sciences/Mathematics and computing/Computational science Driving behavior primitive Data segmentation Segments clustering H-BMASS IDT-LDA 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-6299556","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":449923311,"identity":"61d9c08f-758f-426c-b9dd-7ef389cc6597","order_by":0,"name":"Wenyu Kang","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"prefix":"","firstName":"Wenyu","middleName":"","lastName":"Kang","suffix":""},{"id":449923312,"identity":"9f8bdce6-9f98-4e09-b234-76cf1ce55bc6","order_by":1,"name":"Xuelian Zheng","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"prefix":"","firstName":"Xuelian","middleName":"","lastName":"Zheng","suffix":""},{"id":449923313,"identity":"eb406ecf-0925-4515-b201-bcd2c77b32ab","order_by":2,"name":"Yuanyuan Ren","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYNCCCjYZECVBgpYzbDwkamFsYyBBi3l77zFp3nl8PAYHmA/e5mGwyyOoRebMuTRp3m1sQC1sydY8DMnFBLVISOSYQbXwmEnzMBxIbCCoRf4NUMsckBb+b0RqkQAaztsAtoWNSC08OcaWc46x8UgeZgMyDJKJ0MJ+xvDGm5pjcnzHmx/eeFNhR1gLELBI8TAcY2BgBrENiFAPBMwffzDUEKd0FIyCUTAKRiYAAGoCL9n4je2IAAAAAElFTkSuQmCC","orcid":"","institution":"Jilin University","correspondingAuthor":true,"prefix":"","firstName":"Yuanyuan","middleName":"","lastName":"Ren","suffix":""},{"id":449923314,"identity":"d6d1757c-af0a-47c0-bb13-4c8f19e23c60","order_by":3,"name":"Xiansheng Li","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"prefix":"","firstName":"Xiansheng","middleName":"","lastName":"Li","suffix":""},{"id":449923315,"identity":"2753d175-c1b6-43f6-95b2-4c260981bd53","order_by":4,"name":"Biao Liang","email":"","orcid":"","institution":"Nanjing Sample Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Biao","middleName":"","lastName":"Liang","suffix":""},{"id":449923316,"identity":"4d557319-0b89-48dc-989a-1376656664b2","order_by":5,"name":"Jianfeng Xi","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"prefix":"","firstName":"Jianfeng","middleName":"","lastName":"Xi","suffix":""}],"badges":[],"createdAt":"2025-03-25 03:23:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6299556/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6299556/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87459051,"identity":"c05e77b9-b3a4-4d33-a78b-7d30dd14e7fe","added_by":"auto","created_at":"2025-07-24 05:32:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1231478,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6299556/v1_covered_5ce5f666-cbc9-4d66-94ed-eb16891282fd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Unsupervised inference of driving behavior primitives considering feature correlations and temporal dynamics","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":"Driving behavior primitive, Data segmentation, Segments clustering, H-BMASS, IDT-LDA","lastPublishedDoi":"10.21203/rs.3.rs-6299556/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6299556/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"As the smallest units of driving behavior, driving behavior primitive plays a crucial role in understanding driving dynamics. To better align the inferred driving behavior primitives with real-world driving scenarios, this paper proposes an unsupervised method consisting of two key stages: data segmentation and segments clustering. In data segmentation, a Hierarchical Bayesian Model-based Agglomerative Sequence Segmentation (H-BMASS) model is introduced to accurately capture the change points of variables across different dimensions, thereby avoiding under-segmentation issue that occurs when BMASS is applied to multivariate time series. In segments clustering, to address the limitation of LDA in capturing temporal dynamics in time series data, an Integrating Distribution- and Trend-based Latent Dirichlet Allocation (IDT-LDA) model is proposed. This model incorporates the change trend of data points to capture the temporal dynamics, determined by the derivatives and fluctuations. Compared to conventional BMASS, H-BMASS effectively identifies the change points of driving behavior, with clear structural differences between adjacent segments. Compared to the primitives obtained using Distribution-based LDA, the primitives clustered using IDT-LDA exhibit improved inter-class separability and enhanced interpretability. This unsupervised framework offers an effective method for inferring driving behavior primitives, which will benefit the development of AVs and ADASs.","manuscriptTitle":"Unsupervised inference of driving behavior primitives considering feature correlations and temporal dynamics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-30 09:31:49","doi":"10.21203/rs.3.rs-6299556/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":"0a17bdbe-3749-42ff-8e91-9c97de97b105","owner":[],"postedDate":"April 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47877468,"name":"Physical sciences/Mathematics and computing/Applied mathematics"},{"id":47877469,"name":"Physical sciences/Mathematics and computing/Computational science"}],"tags":[],"updatedAt":"2025-07-24T05:08:39+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-30 09:31:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6299556","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6299556","identity":"rs-6299556","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}