Dual-Stage Prototype Representation for Robust Cross-Subject Motor Imagery EEG Decoding

Dual-Stage Prototype Representation for Robust Cross-Subject Motor Imagery EEG Decoding | 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 Dual-Stage Prototype Representation for Robust Cross-Subject Motor Imagery EEG Decoding YuanZheng SHAN, Hua BO This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8952124/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Motor imagery (MI) electroencephalography (EEG) decoding remains challenging due to severe cross-subject variability and signal non-stationarity, which significantly degrade model generalization to unseen subjects. Existing prototype-based and domain adaptation approaches typically model EEG representations at a single semantic level, limiting their ability to simultaneously capture spatial channel characteristics and high-level discriminative structures. To address this limitation, we propose a dual-stage prototype representation framework for cross-subject MI-EEG decoding. Specifically, electrode channel prototypes and feature prototypes are jointly constructed to enable hierarchical representation learning at both spatial and semantic levels. On this basis, a prototype-guided pairwise similarity learning mechanism is developed, where label supervision in the source domain and a pseudo-supervised structure in the target domain explicitly regularize inter-sample semantic relationships, improving intra-class compactness and inter-class separability. Furthermore, a StyleMix-based feature perturbation strategy and a Wasserstein distance–driven domain alignment module are incorporated to mitigate cross-subject distribution discrepancies and enhance feature robustness. Extensive cross-subject experiments on public brain–computer interface (BCI) competition datasets demonstrate the effectiveness of the proposed method. On the BCI Competition IV dataset 2a, our approach achieves an average classification accuracy improvement of 2.99% over state-of-the-art methods, and on dataset 2b, the improvement reaches 2.83%. These results consistently validate the superiority of our method across multiple evaluation metrics. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Biological sciences/Neuroscience Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 14 Apr, 2026 Editor invited by journal 27 Feb, 2026 Editor assigned by journal 25 Feb, 2026 Submission checks completed at journal 25 Feb, 2026 First submitted to journal 23 Feb, 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-8952124","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":622824369,"identity":"d1676f8e-da55-4961-b681-04c08f107729","order_by":0,"name":"YuanZheng SHAN","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIie3RLQ+CQBzH8dvYzoIy2zEYvoXb2Ei+BF/E/cdG0s1IMLDpIPhUDb4IoxFlO8vZCQau2GkGg5J1gM1wn3zf7X53CCnKH8KD7FTAc+gYna0sWDhrTnoE+1RGgWuuhEYLwZsTh+heX0ZnOOQjbMqF1uJiVuQhOKauuevyECKMjGTJ6hM7DQoQN8ewNkEORxsRcT3UJ4hdKMN319ynXg4CI0omTQnEhOHsvYV5U4i1FgnxMYG4SsbvUa0SnWuUieqRuU+Y4HrjlkGyLeUjrL5yfiof4cwxknV98kH/7biiKIry1QvDtVD0GbY6MAAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"YuanZheng","middleName":"","lastName":"SHAN","suffix":""},{"id":622824370,"identity":"50f4ba9b-ff04-4344-a0b2-d118950b8560","order_by":1,"name":"Hua BO","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Hua","middleName":"","lastName":"BO","suffix":""}],"badges":[],"createdAt":"2026-02-24 03:23:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8952124/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8952124/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107704423,"identity":"8da34628-6fb1-49c5-84f1-686175005c1e","added_by":"auto","created_at":"2026-04-24 08:45:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2253249,"visible":true,"origin":"","legend":"","description":"","filename":"TemplateforsubmissionstoScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8952124/v1_covered_de1d2086-de97-4d4f-912d-55067d8210af.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dual-Stage Prototype Representation for Robust Cross-Subject Motor Imagery EEG Decoding","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-8952124/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8952124/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Motor imagery (MI) electroencephalography (EEG) decoding remains challenging due to severe cross-subject variability and signal non-stationarity, which significantly degrade model generalization to unseen subjects. Existing prototype-based and domain adaptation approaches typically model EEG representations at a single semantic level, limiting their ability to simultaneously capture spatial channel characteristics and high-level discriminative structures. To address this limitation, we propose a dual-stage prototype representation framework for cross-subject MI-EEG decoding. Specifically, electrode channel prototypes and feature prototypes are jointly constructed to enable hierarchical representation learning at both spatial and semantic levels. On this basis, a prototype-guided pairwise similarity learning mechanism is developed, where label supervision in the source domain and a pseudo-supervised structure in the target domain explicitly regularize inter-sample semantic relationships, improving intra-class compactness and inter-class separability. Furthermore, a StyleMix-based feature perturbation strategy and a Wasserstein distance–driven domain alignment module are incorporated to mitigate cross-subject distribution discrepancies and enhance feature robustness. Extensive cross-subject experiments on public brain–computer interface (BCI) competition datasets demonstrate the effectiveness of the proposed method. On the BCI Competition IV dataset 2a, our approach achieves an average classification accuracy improvement of 2.99% over state-of-the-art methods, and on dataset 2b, the improvement reaches 2.83%. These results consistently validate the superiority of our method across multiple evaluation metrics.","manuscriptTitle":"Dual-Stage Prototype Representation for Robust Cross-Subject Motor Imagery EEG Decoding","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 10:51:00","doi":"10.21203/rs.3.rs-8952124/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-04-14T06:24:09+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-27T11:11:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-25T12:20:56+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-25T12:16:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-02-24T03:12:58+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":"0bae0647-fac3-4e7f-ba75-09f7b58056d4","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66276549,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":66276550,"name":"Physical sciences/Engineering"},{"id":66276551,"name":"Physical sciences/Mathematics and computing"},{"id":66276552,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-04-21T10:51:00+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 10:51:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8952124","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8952124","identity":"rs-8952124","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}