Dynamic Multi-Feature Fusion for EEG-Based Emotion Recognition

Dynamic Multi-Feature Fusion for EEG-Based Emotion Recognition | 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 Short Report Dynamic Multi-Feature Fusion for EEG-Based Emotion Recognition Ruihan Zhang, Li Zhang, Yihuan Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9394236/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Electroencephalography (EEG)-based emotion recognition is essential for affective computing and human-computer interaction (HCI). However, current methodologies are constrained by two critical limitations: the poor robustness of handcrafted features and the substantial computational and data overhead inherent in deep learning frameworks. To bridge this gap, this study proposes a lightweight and efficient framework that integrates adaptive dynamic weight multi-feature fusion with a kernel-optimized support vector machine (SVM). Specifically, multi-domain features—including time-frequency (wavelet packet decomposition, WPD), frequency (power spectral density, PSD), and nonlinear dynamics (sample entropy, SampEn)—are extracted to construct a comprehensive representation. An adaptive weight optimization strategy is designed for dynamic feature fusion, while K-means clustering is employed for label denoising to mitigate subjective ambiguity. The proposed framework achieves an average classification accuracy of 90.42% on the public DEAP dataset and 82.32% on a self-collected dataset NeuroVision. SHapley Additive exPlanation (SHAP) analysis reveals that PSD features provide the primary contribution, while WPD and SampEn offer critical complementary information. These results demonstrate that the proposed framework is effective, computationally efficient, and robust, offering a practical solution for potential clinical diagnosis and affective BCI applications. Emotion Recognition EEG Support Vector Machine Feature Fusion Power Spectral Density Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 02 May, 2026 Reviews received at journal 01 May, 2026 Reviewers agreed at journal 23 Apr, 2026 Reviewers invited by journal 19 Apr, 2026 Editor assigned by journal 15 Apr, 2026 Submission checks completed at journal 15 Apr, 2026 First submitted to journal 12 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-9394236","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Short Report","associatedPublications":[],"authors":[{"id":628379731,"identity":"220b7828-e18c-480c-bb2c-b65d2aad8b9b","order_by":0,"name":"Ruihan Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIiWNgGAWjYLCCBAaJejZmxoYDH0jQYpPAx9588OAMEuxJS5DjOZZ8mIcYtfztZ599eFBxOI9NIsfgsE2ZNVCkOwGvFokz6cYzEs4cLgZryTmXDhQ5uwGvFgOGNGaGxLbDjG0gLblthxkMJHIJaOF/BtTyD6rFkigtEiBbGtIS23iOJQA1EqFF4gbQloRjNsZs7M0HDvacS+ch6Bf+/jRmxh81EnLyzYzNH36UWcvxt/fi14IG2JiJihpULaTqGAWjYBSMghEAAGifRqeBXK0lAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Ruihan","middleName":"","lastName":"Zhang","suffix":""},{"id":628379732,"identity":"180df294-d832-4ab0-b99a-988c846cad71","order_by":1,"name":"Li Zhang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"Zhang","suffix":""},{"id":628379733,"identity":"0f5c7460-9f88-420a-b288-2c7871d6956d","order_by":2,"name":"Yihuan Yang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yihuan","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2026-04-12 12:39:43","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9394236/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9394236/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107870372,"identity":"7d263b08-83f5-4bfb-b809-752981b21f8e","added_by":"auto","created_at":"2026-04-27 07:39:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":547052,"visible":true,"origin":"","legend":"","description":"","filename":"renamed0a784.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9394236/v1_covered_c8177789-ca05-481f-b33c-276b013e0b09.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dynamic Multi-Feature Fusion for EEG-Based Emotion Recognition","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":"cognitive-neurodynamics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"cody","sideBox":"Learn more about [Cognitive Neurodynamics](http://link.springer.com/journal/11571)","snPcode":"11571","submissionUrl":"https://submission.nature.com/new-submission/11571/3","title":"Cognitive Neurodynamics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Emotion Recognition, EEG, Support Vector Machine, Feature Fusion, Power Spectral Density","lastPublishedDoi":"10.21203/rs.3.rs-9394236/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9394236/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eElectroencephalography (EEG)-based emotion recognition is essential for affective computing and human-computer interaction (HCI). However, current methodologies are constrained by two critical limitations: the poor robustness of handcrafted features and the substantial computational and data overhead inherent in deep learning frameworks. To bridge this gap, this study proposes a lightweight and efficient framework that integrates adaptive dynamic weight multi-feature fusion with a kernel-optimized support vector machine (SVM). Specifically, multi-domain features\u0026mdash;including time-frequency (wavelet packet decomposition, WPD), frequency (power spectral density, PSD), and nonlinear dynamics (sample entropy, SampEn)\u0026mdash;are extracted to construct a comprehensive representation. An adaptive weight optimization strategy is designed for dynamic feature fusion, while K-means clustering is employed for label denoising to mitigate subjective ambiguity. The proposed framework achieves an average classification accuracy of 90.42% on the public DEAP dataset and 82.32% on a self-collected dataset NeuroVision. SHapley Additive exPlanation (SHAP) analysis reveals that PSD features provide the primary contribution, while WPD and SampEn offer critical complementary information. These results demonstrate that the proposed framework is effective, computationally efficient, and robust, offering a practical solution for potential clinical diagnosis and affective BCI applications.\u003c/p\u003e","manuscriptTitle":"Dynamic Multi-Feature Fusion for EEG-Based Emotion Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-27 03:21:32","doi":"10.21203/rs.3.rs-9394236/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"170915006344417132953371180643545616950","date":"2026-05-02T08:46:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-01T09:26:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307162832528405967024139532683628303646","date":"2026-04-23T12:32:34+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-19T06:22:10+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-15T13:59:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-15T13:59:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cognitive Neurodynamics","date":"2026-04-12T12:24:53+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cognitive-neurodynamics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"cody","sideBox":"Learn more about [Cognitive Neurodynamics](http://link.springer.com/journal/11571)","snPcode":"11571","submissionUrl":"https://submission.nature.com/new-submission/11571/3","title":"Cognitive Neurodynamics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a265fbda-f0f5-422b-888f-62a827814d9f","owner":[],"postedDate":"April 27th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"170915006344417132953371180643545616950","date":"2026-05-02T08:46:29+00:00","index":17,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-01T09:26:49+00:00","index":16,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-27T03:21:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-27 03:21:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9394236","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9394236","identity":"rs-9394236","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}