Deep Learning and Dynamical Modeling Frameworkfor EEG-Based Cognitive State Evolution inBrain-Computer Interfaces

Deep Learning and Dynamical Modeling Frameworkfor EEG-Based Cognitive State Evolution inBrain-Computer Interfaces | 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 Deep Learning and Dynamical Modeling Frameworkfor EEG-Based Cognitive State Evolution inBrain-Computer Interfaces Muhammad Khurram Umair, Ayesha Arif Khawaja, Muhammad Faisal Abrar, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9208513/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 11 You are reading this latest preprint version Abstract Brain-computer interfaces (BCIs) require reliable cognitive state monitoring to ensure safe and effective operation. While deeplearning approaches have shown promise for EEG-based state detection, they lack temporal consistency and mechanisticinterpretability, limiting clinical applicability. We present a novel unified framework integrating Long Short-Term Memory (LSTM)networks with a three-state compartmental Ordinary Differential Equation (ODE) model for interpretable cognitive state evolutionin BCIs. The framework employs a probabilistic coupling mechanism where LSTM classification probabilities dynamicallymodulate ODE transition rates between Active, Passive, and Fatigued cognitive states. We evaluated the framework on theOpenNeuro ds004148 dataset (60 participants, 61 channels, 500 Hz) using stratified temporal cross-validation. The integratedLSTM-ODE framework achieved 85.57% accuracy (95% CI: 85.19–85.93%) with F1-score of 0.854, outperforming traditionalmachine learning baselines including Random Forest (82.29%) and XGBoost (80.92%). Explainability analysis revealedanterior frontal EEG channels (AF7, AF3, Fp1) as primary contributors with gradient-based, permutation, and SHAP importancemethods. Learned ODE parameters showed physiologically meaningful dynamics: the Passive-to-Fatigued transition ratedominated (time constant 3.33 seconds), indicating rapid vigilance decrement, while full recovery was substantially slower (timeconstant 100 seconds). The fatigue accumulation ratio of 0.91 indicates strongly asymmetric dynamics where fatigue-directedtransitions dominate over recovery. This framework establishes a principled approach to combining deep learning patternrecognition with mechanistic dynamical modeling, providing clinically meaningful transition rate interpretations for proactive BCIsafety interventions Biological sciences/Computational biology and bioinformatics Physical sciences/Mathematics and computing Biological sciences/Neuroscience Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 12 May, 2026 Reviews received at journal 09 May, 2026 Reviewers agreed at journal 07 May, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviews received at journal 19 Apr, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviewers invited by journal 06 Apr, 2026 Editor invited by journal 31 Mar, 2026 Editor assigned by journal 25 Mar, 2026 Submission checks completed at journal 25 Mar, 2026 First submitted to journal 24 Mar, 2026 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-9208513","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":618246795,"identity":"abdf7bf9-b1f4-4f51-847b-b2ce97b30b04","order_by":0,"name":"Muhammad Khurram Umair","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYJCCAwwGNnIGYKaBBbFaCtKMDRiYQVokiLXnw+HEDWAtDERoMbh2+OHhCoPD6dvZ+49u+FEgwcDf3p2AX8vtNIODZwzSc3f2HGa72QN0mMSZsxsIaEkwONhgYJ274UYy2w0eoBYDiVxCWtI/ALUwpxsAtdz8Q5yWHJAtzgkgLbeJskXydk4BUEua4YYzh81uyxhI8BD0C9/t9M0fG/7YyBscb3x2880fGzn+9l78WjAAD2nKR8EoGAWjYBRgBQDe7UuYzuCt2AAAAABJRU5ErkJggg==","orcid":"","institution":"University of Engineering and Technology","correspondingAuthor":true,"prefix":"","firstName":"Muhammad","middleName":"Khurram","lastName":"Umair","suffix":""},{"id":618246796,"identity":"7f4fe094-6f61-437c-bfb9-b33c032be921","order_by":1,"name":"Ayesha Arif Khawaja","email":"","orcid":"","institution":"National University of Sciences and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ayesha","middleName":"Arif","lastName":"Khawaja","suffix":""},{"id":618246797,"identity":"917bd02b-31cf-4173-9ead-3072da9158d7","order_by":2,"name":"Muhammad Faisal Abrar","email":"","orcid":"","institution":"University of Ha'il","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"Faisal","lastName":"Abrar","suffix":""},{"id":618246798,"identity":"fc9eceff-200e-45cf-8be3-4ef48ba51980","order_by":3,"name":"Sikandar Ali","email":"","orcid":"","institution":"University of the West of Scotland","correspondingAuthor":false,"prefix":"","firstName":"Sikandar","middleName":"","lastName":"Ali","suffix":""},{"id":618246799,"identity":"464caa26-bdb9-484a-8986-48a169953728","order_by":4,"name":"It Ee Lee","email":"","orcid":"","institution":"Multimedia University","correspondingAuthor":false,"prefix":"","firstName":"It","middleName":"Ee","lastName":"Lee","suffix":""},{"id":618246800,"identity":"51a8a546-d60e-40bf-b341-c95bfa0c1d2a","order_by":5,"name":"Salman Jan","email":"","orcid":"","institution":"Arab Open University","correspondingAuthor":false,"prefix":"","firstName":"Salman","middleName":"","lastName":"Jan","suffix":""}],"badges":[],"createdAt":"2026-03-24 07:54:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9208513/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9208513/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106725436,"identity":"51774c08-ed8a-4456-aa0d-fb2d44fe5dc9","added_by":"auto","created_at":"2026-04-12 18:32:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3275978,"visible":true,"origin":"","legend":"","description":"","filename":"DeepLearningandDynamicalModelingFrameworkforEEGBasedCognitiveStateEvolutioninBrainComputerInterfacessubmission1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9208513/v1_covered_1cb70822-5d55-446c-9279-46bd99314bd2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Learning and Dynamical Modeling Frameworkfor EEG-Based Cognitive State Evolution inBrain-Computer Interfaces","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9208513/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9208513/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Brain-computer interfaces (BCIs) require reliable cognitive state monitoring to ensure safe and effective operation. While deeplearning approaches have shown promise for EEG-based state detection, they lack temporal consistency and mechanisticinterpretability, limiting clinical applicability. We present a novel unified framework integrating Long Short-Term Memory (LSTM)networks with a three-state compartmental Ordinary Differential Equation (ODE) model for interpretable cognitive state evolutionin BCIs. The framework employs a probabilistic coupling mechanism where LSTM classification probabilities dynamicallymodulate ODE transition rates between Active, Passive, and Fatigued cognitive states. We evaluated the framework on theOpenNeuro ds004148 dataset (60 participants, 61 channels, 500 Hz) using stratified temporal cross-validation. The integratedLSTM-ODE framework achieved 85.57% accuracy (95% CI: 85.19–85.93%) with F1-score of 0.854, outperforming traditionalmachine learning baselines including Random Forest (82.29%) and XGBoost (80.92%). Explainability analysis revealedanterior frontal EEG channels (AF7, AF3, Fp1) as primary contributors with gradient-based, permutation, and SHAP importancemethods. Learned ODE parameters showed physiologically meaningful dynamics: the Passive-to-Fatigued transition ratedominated (time constant 3.33 seconds), indicating rapid vigilance decrement, while full recovery was substantially slower (timeconstant 100 seconds). The fatigue accumulation ratio of 0.91 indicates strongly asymmetric dynamics where fatigue-directedtransitions dominate over recovery. This framework establishes a principled approach to combining deep learning patternrecognition with mechanistic dynamical modeling, providing clinically meaningful transition rate interpretations for proactive BCIsafety interventions","manuscriptTitle":"Deep Learning and Dynamical Modeling Frameworkfor EEG-Based Cognitive State Evolution inBrain-Computer Interfaces","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-10 06:45:07","doi":"10.21203/rs.3.rs-9208513/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-12T13:04:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T07:00:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"168553835869938899995783296532691842861","date":"2026-05-07T06:03:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"283046426382844335971806321924793876925","date":"2026-04-22T00:58:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-19T05:26:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"8423469497174930254536271812754729219","date":"2026-04-19T03:26:06+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-06T10:32:22+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-31T07:25:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-25T13:52:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-25T13:51:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-24T07:51:11+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f3cda2ba-0326-4a51-aaee-13007ea5ed29","owner":[],"postedDate":"April 10th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-12T13:04:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T07:00:35+00:00","index":51,"fulltext":""},{"type":"reviewerAgreed","content":"168553835869938899995783296532691842861","date":"2026-05-07T06:03:35+00:00","index":50,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":65787787,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":65787788,"name":"Physical sciences/Mathematics and computing"},{"id":65787789,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-05-12T13:35:00+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-10 06:45:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9208513","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9208513","identity":"rs-9208513","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}