EEG Emotion Recognition Based on Masked Generative Adversarial Networks and Neural Architecture Search

EEG Emotion Recognition Based on Masked Generative Adversarial Networks and Neural Architecture Search | 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 EEG Emotion Recognition Based on Masked Generative Adversarial Networks and Neural Architecture Search Kexuan Zhu, Qian Zhao, Huadi Wang, Yang Zhao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9400088/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 6 You are reading this latest preprint version Abstract EEG signals face challenges such as a scarcity of training data, significant individual variability, and difficulties in designing neural network architectures, which severely limit the performance and generalization capabilities of emotion recognition models. This paper proposes an EEG-based emotion recognition method that integrates masked generative adversarial data augmentation with personalized neural architecture search. We designed a data augmentation strategy using a frequency-domain feature-based stochastic electrode mask generative adversarial network, which effectively expands the training dataset and enhances the model’s generalization ability. Subsequently, we constructed a neural architecture search space tailored for EEG signals and employed a differentiable architecture search method to automatically discover the optimal network topology. Finally, a personalized architecture search strategy is employed to independently identify the classification network best suited to each subject’s unique EEG signal characteristics. Experimental validation on the public EEG emotion dataset DEAP achieved a classification accuracy of 98.64% on the Arousal dimension and 98.59% on the Valence dimension, significantly outperforming traditional machine learning methods and deep learning models with fixed architectures. EEG emotion recognition generative adversarial network data augmentation neural architecture search Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 18 May, 2026 Reviewers agreed at journal 13 Apr, 2026 Reviewers invited by journal 13 Apr, 2026 Editor assigned by journal 13 Apr, 2026 Submission checks completed at journal 13 Apr, 2026 First submitted to journal 13 Apr, 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-9400088","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":622881158,"identity":"99d7f465-2c3c-4c05-9f21-1e1e93464ad0","order_by":0,"name":"Kexuan Zhu","email":"","orcid":"","institution":"Qufu Normal University","correspondingAuthor":false,"prefix":"","firstName":"Kexuan","middleName":"","lastName":"Zhu","suffix":""},{"id":622881159,"identity":"a14d5b92-6176-476f-b93e-5334b6906faa","order_by":1,"name":"Qian Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYDACCRBhYCPHxt7Y+OAD8Voq0oz5eQ43G84gXsuZQ4kzZ6S3SXMQo0N+dvPDB2/bDjBuuPmwQZqBwU5Ot4GAFsY5x4wN57bdYTa4ndhgXMCQbGx2gIAWZokEM2netmdsIC3JMxgOJG4jpIVNIv0bUMthHoObBxsO8xCjhUcix0ya58xhCckZjI3NRGmRkMgpNpxTkWbAz5PYzDjDgAi/yM9I3/jgjYFNfRv78ec/PlTYyRHUAnEdnGVAjHJULaNgFIyCUTAKsAAAUFxEmG3yC/gAAAAASUVORK5CYII=","orcid":"","institution":"Qufu Normal University","correspondingAuthor":true,"prefix":"","firstName":"Qian","middleName":"","lastName":"Zhao","suffix":""},{"id":622881160,"identity":"1d3ca504-57d9-475f-b587-ea947a98edda","order_by":2,"name":"Huadi Wang","email":"","orcid":"","institution":"Qufu Normal University","correspondingAuthor":false,"prefix":"","firstName":"Huadi","middleName":"","lastName":"Wang","suffix":""},{"id":622881161,"identity":"978d6e8f-3176-446b-8494-326c1131ceb5","order_by":3,"name":"Yang Zhao","email":"","orcid":"","institution":"Shanxian Vocational Secondary School of Shandong","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2026-04-13 07:23:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9400088/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9400088/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107488226,"identity":"6fd93dc9-a581-4462-8b3f-01167bca207b","added_by":"auto","created_at":"2026-04-22 02:43:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":738986,"visible":true,"origin":"","legend":"","description":"","filename":"EEGEmotionRecognitionBasedonMaskedGANandNAS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9400088/v1_covered_c6b0e7ae-3ddf-4f6f-b262-74544c10b809.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"EEG Emotion Recognition Based on Masked Generative Adversarial Networks and Neural Architecture Search","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":"user-modeling-and-user-adapted-interaction","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"umui","sideBox":"Learn more about [User Modeling and User-Adapted Interaction](http://link.springer.com/journal/11257)","snPcode":"11257","submissionUrl":"https://submission.nature.com/new-submission/11257/3","title":"User Modeling and User-Adapted Interaction","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"EEG, emotion recognition, generative adversarial network, data augmentation, neural architecture search","lastPublishedDoi":"10.21203/rs.3.rs-9400088/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9400088/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEEG signals face challenges such as a scarcity of training data, significant individual variability, and difficulties in designing neural network architectures, which severely limit the performance and generalization capabilities of emotion recognition models. This paper proposes an EEG-based emotion recognition method that integrates masked generative adversarial data augmentation with personalized neural architecture search. We designed a data augmentation strategy using a frequency-domain feature-based stochastic electrode mask generative adversarial network, which effectively expands the training dataset and enhances the model\u0026rsquo;s generalization ability. Subsequently, we constructed a neural architecture search space tailored for EEG signals and employed a differentiable architecture search method to automatically discover the optimal network topology. Finally, a personalized architecture search strategy is employed to independently identify the classification network best suited to each subject\u0026rsquo;s unique EEG signal characteristics. Experimental validation on the public EEG emotion dataset DEAP achieved a classification accuracy of 98.64% on the Arousal dimension and 98.59% on the Valence dimension, significantly outperforming traditional machine learning methods and deep learning models with fixed architectures.\u003c/p\u003e","manuscriptTitle":"EEG Emotion Recognition Based on Masked Generative Adversarial Networks and Neural Architecture Search","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 05:00:19","doi":"10.21203/rs.3.rs-9400088/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"301286845974524112447932110923985965794","date":"2026-05-18T17:51:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"60162635629225235329291047694829044790","date":"2026-04-14T02:14:26+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-13T18:09:06+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-13T14:25:41+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-13T14:25:07+00:00","index":"","fulltext":""},{"type":"submitted","content":"User Modeling and User-Adapted Interaction","date":"2026-04-13T07:09:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"user-modeling-and-user-adapted-interaction","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"umui","sideBox":"Learn more about [User Modeling and User-Adapted Interaction](http://link.springer.com/journal/11257)","snPcode":"11257","submissionUrl":"https://submission.nature.com/new-submission/11257/3","title":"User Modeling and User-Adapted Interaction","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"80b88ca9-4efa-41b2-81bc-527e76dd7748","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"301286845974524112447932110923985965794","date":"2026-05-18T17:51:38+00:00","index":19,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-21T05:00:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 05:00:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9400088","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9400088","identity":"rs-9400088","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}