Adaptive Dimensionality Reduction for Efficient Deep Learning on Temporal Datasets

Adaptive Dimensionality Reduction for Efficient Deep Learning on Temporal Datasets | 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 Adaptive Dimensionality Reduction for Efficient Deep Learning on Temporal Datasets Yaseen Yaseen, Oh-Jin Kwon, Jaeho Kim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6732901/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 16 You are reading this latest preprint version Abstract In the domain of computer vision and its related research fields, especially in temporal data handling, the analysis and processing of high dimensional data is a huge problem. Challenges in deep learning-based high dimension data processing often arise from their variable length sequences and their complex data patterns. As the use of high dimensional data continues to grow, the demand for dimension reduction of complex data is growing rapidly. Dimensionality reduction is the process of reducing a high-dimensional matrix of a dataset into a lower dimension. Standard approaches based on principal component analysis, independent component analysis and others, including simple padding and truncation, can lead to data loss or unwanted computational overhead. To address this issue, we introduce a VidSqeOpt method for dimensionality reduction based on feature extraction which exploits statistical approaches with reduced dimension and optimal length finding. Our method is validated on several benchmark datasets that are based on temporal data with complex dimensionality. Cross comparison with the baseline methods shows that our proposed approach adapts to diverse tasks, achieving up to 2.0% higher accuracy while reducing per-frame processing time by at least 23.7%, down to ≤0.45 seconds. Dimensionality reduction spatiotemporal features processing input sequence standardization fixed length feature representation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 02 Dec, 2025 Reviews received at journal 31 Oct, 2025 Reviewers agreed at journal 29 Oct, 2025 Reviewers agreed at journal 27 Oct, 2025 Reviewers agreed at journal 27 Oct, 2025 Reviewers agreed at journal 06 Oct, 2025 Reviewers agreed at journal 16 Sep, 2025 Reviewers agreed at journal 08 Aug, 2025 Reviewers agreed at journal 05 Aug, 2025 Reviews received at journal 04 Aug, 2025 Reviewers agreed at journal 01 Aug, 2025 Reviewers agreed at journal 30 Jul, 2025 Reviewers invited by journal 30 Jul, 2025 Editor assigned by journal 31 May, 2025 Submission checks completed at journal 24 May, 2025 First submitted to journal 23 May, 2025 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-6732901","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":494284611,"identity":"2631dde6-dca5-465e-a8cb-db3de9a94702","order_by":0,"name":"Yaseen Yaseen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYPACGwbGBjAjgWgtaaRrOQxjEKHF4Pjxhw8+7jhvzzwjgfHDD4a0fMJazuQYG848czuxcUYCs2QPQ45lA0EtB3LYpHnbbicwzkhgkGZgqDAgbMv5589//207Zw/UwvybOC03EsyYGdsOMAIdxga0JYewFskbb4wle9uSExt7HrZZ9hikEdbCdz794YefbXb2hu3Jh2/8qEgmrEXhAJRh2ACKTMIaGBjkG2AMIhSPglEwCkbBCAUA0A09EPj9x40AAAAASUVORK5CYII=","orcid":"","institution":"Sejong University","correspondingAuthor":true,"prefix":"","firstName":"Yaseen","middleName":"","lastName":"Yaseen","suffix":""},{"id":494284612,"identity":"29341fe1-3bd6-4fc1-980c-b37c593e6fbc","order_by":1,"name":"Oh-Jin Kwon","email":"","orcid":"","institution":"Sejong University","correspondingAuthor":false,"prefix":"","firstName":"Oh-Jin","middleName":"","lastName":"Kwon","suffix":""},{"id":494284613,"identity":"11323dc3-c628-449e-8657-83fb257351c5","order_by":2,"name":"Jaeho Kim","email":"","orcid":"","institution":"Sejong University","correspondingAuthor":false,"prefix":"","firstName":"Jaeho","middleName":"","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2025-05-23 12:38:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6732901/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6732901/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88211608,"identity":"1bdf8922-92f6-4c53-b0e7-bbd270f99b1c","added_by":"auto","created_at":"2025-08-04 05:34:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1331754,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6732901/v1_covered_4c095b03-9cef-4870-8727-8b30aedb98cc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adaptive Dimensionality Reduction for Efficient Deep Learning on Temporal Datasets","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Dimensionality reduction, spatiotemporal features processing, input sequence standardization, fixed length feature representation","lastPublishedDoi":"10.21203/rs.3.rs-6732901/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6732901/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In the domain of computer vision and its related research fields, especially in temporal data handling, the analysis and processing of high dimensional data is a huge problem. Challenges in deep learning-based high dimension data processing often arise from their variable length sequences and their complex data patterns. As the use of high dimensional data continues to grow, the demand for dimension reduction of complex data is growing rapidly. Dimensionality reduction is the process of reducing a high-dimensional matrix of a dataset into a lower dimension. Standard approaches based on principal component analysis, independent component analysis and others, including simple padding and truncation, can lead to data loss or unwanted computational overhead. To address this issue, we introduce a VidSqeOpt method for dimensionality reduction based on feature extraction which exploits statistical approaches with reduced dimension and optimal length finding. Our method is validated on several benchmark datasets that are based on temporal data with complex dimensionality. Cross comparison with the baseline methods shows that our proposed approach adapts to diverse tasks, achieving up to 2.0% higher accuracy while reducing per-frame processing time by at least 23.7%, down to ≤0.45 seconds.","manuscriptTitle":"Adaptive Dimensionality Reduction for Efficient Deep Learning on Temporal Datasets","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-04 05:10:28","doi":"10.21203/rs.3.rs-6732901/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-02T12:38:52+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-31T18:08:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"189267066638632017524513414014186625082","date":"2025-10-29T20:36:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"63674819617960128483077359744039547143","date":"2025-10-27T13:06:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"11054544627236364193127445471231552171","date":"2025-10-27T10:16:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"315477541958708207663430602580331607428","date":"2025-10-07T03:27:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"156280408249698376113386934679163843808","date":"2025-09-16T12:34:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"115147835569680059288879425392345008975","date":"2025-08-09T02:26:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"49100542815314807659402444473889053179","date":"2025-08-05T07:43:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-04T09:28:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"254739794279645468289248227958994318459","date":"2025-08-01T11:51:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"12415430163096411307167060179480926943","date":"2025-07-30T15:57:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-30T10:11:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-31T08:57:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-24T05:09:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"Knowledge and Information Systems","date":"2025-05-23T12:22:57+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"282cff7f-437a-4ac5-abc0-1119054b5cf6","owner":[],"postedDate":"August 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T08:55:34+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-04 05:10:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6732901","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6732901","identity":"rs-6732901","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}