Scaled Custom Attention for Enhanced Temporal Dependency Modeling in EEG Classification

Scaled Custom Attention for Enhanced Temporal Dependency Modeling in EEG Classification | 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 Scaled Custom Attention for Enhanced Temporal Dependency Modeling in EEG Classification Swaleh Omar, Michael Kimwele, Akeem Olowolayemo, Dennis Kaburu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6226331/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 Accurate Electroencephalography (EEG) classification is essential for diagnosing brain disorders such as Epilepsy. Whereas Deep Learning models such as Convolution Neural Networks (CNNs) and Long Short Term Memory (LSTM) improved EEG classification performance over traditional methods, existing attention mechanisms such as Additive, Luong and Multi-head struggle to capture EEG’s complex temporal dependencies. This study proposes Scaled Custom Attention (SCA); a mechanism for temporal dependency modeling during EEG classification. Unlike traditional Query-Key-Value (QKV) approaches which rely on semantic weighting schemes, SCA employs direct feature weighting strategy that adapts to the unique temporal dependencies of EEG signals, and introduces a scaling strategy that enhances stability. To validate our approach, experiments were conducted using TUH EEG Epilepsy Corpus (TUEP) where SCA achieved compelling classification accuracy (98.17%), surpassing Additive (96.47%), Multihead (97.65%), and Luong (97.26%) attention mechanisms when integrated to the LConvNet EEG classification model. Additionally, SCA demonstrated strong scalability, parameter efficiency, and generalization abilities, making it a promising enhancement for EEG-based deep learning models. EEG classification Attention mechanism SCA Deep learning Feature Weighting Temporal dependency 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-6226331","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":432578261,"identity":"ae171574-b23c-452d-af25-3def510d0d3a","order_by":0,"name":"Swaleh Omar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYHACxgOMDQwMbAzMB4AcCRmi9EC0sLElgLTwEK+FgY3HAMQhrEV+RvKDAx93METzyfd8fnWjxoKHgf3w0Q34tBjcSDM4OPMMQ24bG+8265xjQIfxpKXdwKtFOsHgMG8bRItxDhtQiwSPGV4t8rPTPxz+C9bC88w45x8RWhhu5xgcZoRoYX6c20aEFoP7bwoO9rZJALWkmTHn9knwsBHyi3zP8Y0PfrbZ5M5vPvz4c863Ojl+9sPH8DsMAiRABBuEJEI5HDB/IEX1KBgFo2AUjBwAAAcsRvIL10v+AAAAAElFTkSuQmCC","orcid":"","institution":"Kenya Industrial Research and Development Institute","correspondingAuthor":true,"prefix":"","firstName":"Swaleh","middleName":"","lastName":"Omar","suffix":""},{"id":432578262,"identity":"4edb8246-c301-43ad-a9d1-9d8261ba2018","order_by":1,"name":"Michael Kimwele","email":"","orcid":"","institution":"Jomo Kenyatta University of Agriculture and Technology","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Kimwele","suffix":""},{"id":432578263,"identity":"3be45d8c-46e0-4784-904a-338a96556ab7","order_by":2,"name":"Akeem Olowolayemo","email":"","orcid":"","institution":"International Islamic University Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Akeem","middleName":"","lastName":"Olowolayemo","suffix":""},{"id":432578264,"identity":"89766fdb-41c7-42e6-a2ae-15d444c4053f","order_by":3,"name":"Dennis Kaburu","email":"","orcid":"","institution":"Jomo Kenyatta University of Agriculture and Technology","correspondingAuthor":false,"prefix":"","firstName":"Dennis","middleName":"","lastName":"Kaburu","suffix":""}],"badges":[],"createdAt":"2025-03-14 12:38:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6226331/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6226331/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":81330919,"identity":"dfb0461e-82bc-499a-affd-74d78b1caa6f","added_by":"auto","created_at":"2025-04-24 21:31:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4824083,"visible":true,"origin":"","legend":"","description":"","filename":"ScaledCustomAttentionforEnhancedTemporalDependencyModelinginEEGClassification.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6226331/v1_covered_a726dee3-510a-4df2-b027-78f3c37f137d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Scaled Custom Attention for Enhanced Temporal Dependency Modeling in EEG Classification","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":"EEG classification, Attention mechanism, SCA, Deep learning, Feature Weighting, Temporal dependency","lastPublishedDoi":"10.21203/rs.3.rs-6226331/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6226331/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate Electroencephalography (EEG) classification is essential for diagnosing brain disorders such as Epilepsy. Whereas Deep Learning models such as Convolution Neural Networks (CNNs) and Long Short Term Memory (LSTM) improved EEG classification performance over traditional methods, existing attention mechanisms such as Additive, Luong and Multi-head struggle to capture EEG’s complex temporal dependencies. This study proposes Scaled Custom Attention (SCA); a mechanism for temporal dependency modeling during EEG classification. Unlike traditional Query-Key-Value (QKV) approaches which rely on semantic weighting schemes, SCA employs direct feature weighting strategy that adapts to the unique temporal dependencies of EEG signals, and introduces a scaling strategy that enhances stability. To validate our approach, experiments were conducted using TUH EEG Epilepsy Corpus (TUEP) where SCA achieved compelling classification accuracy (98.17%), surpassing Additive (96.47%), Multihead (97.65%), and Luong (97.26%) attention mechanisms when integrated to the LConvNet EEG classification model. Additionally, SCA demonstrated strong scalability, parameter efficiency, and generalization abilities, making it a promising enhancement for EEG-based deep learning models.\u003c/p\u003e","manuscriptTitle":"Scaled Custom Attention for Enhanced Temporal Dependency Modeling in EEG Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-02 02:39:37","doi":"10.21203/rs.3.rs-6226331/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":"7e0f3c80-606a-4536-aac0-9bac16ebba4c","owner":[],"postedDate":"April 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-04-24T21:23:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-02 02:39:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6226331","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6226331","identity":"rs-6226331","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}