{"paper_id":"4938fc44-ddc7-40c7-bb4a-9331eec0d551","body_text":"EEG-based Emotion Recognition in Resource-Constrained Environments: Reproducibility and Lightweighting of a Gompertz Fuzzy Ensemble Model on TorchEEG | 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-based Emotion Recognition in Resource-Constrained Environments: Reproducibility and Lightweighting of a Gompertz Fuzzy Ensemble Model on TorchEEG Guozhu Zhao, Zehua Wang, Zijing Feng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9100285/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 EEG-based emotion recognition for resource-constrained devices is often challenged by irreproducible evaluation pipelines and oversized deep models. This study establishes a TorchEEG-based reproducible workflow on DEAP, employing trial-wise grouped 5-fold cross-validation to prevent trial-level information leakage and ensure consistent benchmarking. Building on this pipeline, we propose a lightweight multi-branch ensemble featuring a shared depthwise-separable 1D-CNN backbone with three shallow complementary branches (LSTM, GRU, and convolutional pooling), enabling parameter reuse with minimal overhead. For decision fusion, a Gompertz-function-based sample-wise adaptive fuzzy weighting is introduced to nonlinearly map branch confidence into normalized weights, improving robustness without additional heavy computation. On valence binary classification, the proposed model achieves 82.28% ± 0.58% accuracy with loss 0.588 ± 0.023 using only \\((4.9\\times10^4)\\) parameters, delivering an approximately 33× parameter reduction versus commonly used million-parameter CNN baselines while maintaining comparable accuracy. Fusion ablations further indicate that the proposed weighting mitigates the large and unstable test loss observed with max-confidence selection. All experiments are conducted under CPU-only inference and evaluation settings to reflect practical deployment constraints. DEAP Depthwise-separable CNN EEG-based emotion recognition Lightweight TorchEEG 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-9100285\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":608208693,\"identity\":\"7561f33d-87c1-4453-8d69-44e2dc21052a\",\"order_by\":0,\"name\":\"Guozhu Zhao\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Civil Aviation Flight University of China\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Guozhu\",\"middleName\":\"\",\"lastName\":\"Zhao\",\"suffix\":\"\"},{\"id\":608208694,\"identity\":\"556e7e82-c512-4ea6-bdb1-56780a11a2e5\",\"order_by\":1,\"name\":\"Zehua Wang\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIie3RMQrCMBSA4VcKuhRdK17iQaFWKPUqQiFdgvQG9gCCa48heIHWh7oorh0cnMShQ0aHgr4ujm3dBPNDhsD7CEkAdLpfDnllCv3gK2LkaSzCr4hJltoZSevk8UwPqHyY2OGNfMxM6NN+00hOC+GBJWCaCiSJ1wFvRNFE3Ey6CDYBFvOa3E2wLbeZXEom+GISKfKQjKSVFNK5wTxjIpHP6kBmRenyh4R8qTLOVyjCXttdRmvpKKgCfrpoq56VHwz7dGgkXG9cASyTz7ZlvM5UHYZ0Op3un3sD9ixM2H+VXocAAAAASUVORK5CYII=\",\"orcid\":\"\",\"institution\":\"Civil Aviation Flight University of China\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Zehua\",\"middleName\":\"\",\"lastName\":\"Wang\",\"suffix\":\"\"},{\"id\":608208695,\"identity\":\"b3d3fcb4-c662-4f97-863e-27f6b569c7d1\",\"order_by\":2,\"name\":\"Zijing Feng\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Civil Aviation Flight University of China\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Zijing\",\"middleName\":\"\",\"lastName\":\"Feng\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2026-03-12 05:23:13\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-9100285/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-9100285/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":108330385,\"identity\":\"b098eb6b-ac32-4d87-943e-3fdb67aa8a42\",\"added_by\":\"auto\",\"created_at\":\"2026-05-02 17:09:32\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":705987,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"wangNPL2026.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-9100285/v1_covered_66e2eee8-0b3b-4886-aabe-5ae0f002f6a4.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"EEG-based Emotion Recognition in Resource-Constrained Environments: Reproducibility and Lightweighting of a Gompertz Fuzzy Ensemble Model on TorchEEG\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":false,\"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\":\"info@researchsquare.com\",\"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\":\"DEAP, Depthwise-separable CNN, EEG-based emotion recognition, Lightweight, TorchEEG\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-9100285/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-9100285/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eEEG-based emotion recognition for resource-constrained devices is often challenged by irreproducible evaluation pipelines and oversized deep models. This study establishes a TorchEEG-based reproducible workflow on DEAP, employing trial-wise grouped 5-fold cross-validation to prevent trial-level information leakage and ensure consistent benchmarking. Building on this pipeline, we propose a lightweight multi-branch ensemble featuring a shared depthwise-separable 1D-CNN backbone with three shallow complementary branches (LSTM, GRU, and convolutional pooling), enabling parameter reuse with minimal overhead. For decision fusion, a Gompertz-function-based sample-wise adaptive fuzzy weighting is introduced to nonlinearly map branch confidence into normalized weights, improving robustness without additional heavy computation. On valence binary classification, the proposed model achieves 82.28% \\u0026plusmn; 0.58% accuracy with loss 0.588 \\u0026plusmn; 0.023 using only \\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\((4.9\\\\times10^4)\\\\)\\u003c/span\\u003e\\u003c/span\\u003e parameters, delivering an approximately 33\\u0026times; parameter reduction versus commonly used million-parameter CNN baselines while maintaining comparable accuracy. Fusion ablations further indicate that the proposed weighting mitigates the large and unstable test loss observed with max-confidence selection. All experiments are conducted under CPU-only inference and evaluation settings to reflect practical deployment constraints.\\u003c/p\\u003e\",\"manuscriptTitle\":\"EEG-based Emotion Recognition in Resource-Constrained Environments: Reproducibility and Lightweighting of a Gompertz Fuzzy Ensemble Model on TorchEEG\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2026-03-19 16:57:30\",\"doi\":\"10.21203/rs.3.rs-9100285/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"8c782b29-52ed-4875-87b1-9a95017ead4a\",\"owner\":[],\"postedDate\":\"March 19th, 2026\",\"published\":true,\"recentEditorialEvents\":[{\"type\":\"decision\",\"content\":\"Rejected\",\"date\":\"2026-05-02T17:05:06+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2026-05-02T17:09:02+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2026-03-19 16:57:30\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-9100285\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-9100285\",\"identity\":\"rs-9100285\",\"version\":[\"v1\"]},\"buildId\":\"XKTyCvWXoU3ODBz1xrDgd\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}