DSTA-Net: Dynamic Spatio-Temporal Feature Augmentation Network for Motor Imagery Classification

DSTA-Net: Dynamic Spatio-Temporal Feature Augmentation Network for Motor Imagery Classification | 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 DSTA-Net: Dynamic Spatio-Temporal Feature Augmentation Network for Motor Imagery Classification liang Chang, banghua Yang, jiayang Zhang, tie Li, juntao Feng, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6208691/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Jul, 2025 Read the published version in Cognitive Neurodynamics → Version 1 posted 7 You are reading this latest preprint version Abstract Accurate decoding and strong feature interpretability of Motor Imagery (MI) are expected to drive MI applications in stroke rehabilitation. However, the inherent nonstationarity and high intra-class variability of MI-EEG pose significant challenges in extracting reliable spatio-temporal features. We proposed the Dynamic Spatio-Temporal Feature Augmentation Network (DSTA-Net), which combines DSTA and the Spatio-Temporal Convolution (STC) modules. In DSTA module, multi-scale temporal convolutional kernels tailored to the α and β frequency bands of MI neurophysiological characteristics, while raw EEG serve as a baseline feature layer to retain original information. Next, Grouped Spatial Convolutions extract multi-level spatial features, combined with weight constraints to prevent overfitting. Spatial convolution kernels map EEG channel information into a new spatial domain, enabling further feature extraction through dimensional transformation. And STC module further extracts features and conducts classification. We evaluated DSTA-Net on three public datasets and applied it to a self-collected stroke dataset. In 10-fold cross-validation, DSTA-Net achieved average accuracy improvements of 6.29% (p<0.01), 3.05% (p<0.01), 5.26%(p<0.01), and 2.25% over the ShallowConvNet on the BCI-IV-2a, OpenBMI, CASIA, and stroke dataset, respectively. In hold-out validation, DSTA-Net achieved average accuracy improvements of 3.99% (p<0.01) and 4.2% (p<0.01) over the ShallowConvNet on the OpenBMI and CASIA datasets, respectively. Finally, we applied DeepLIFT, Common Spatial Pattern, and t-SNE to analyze the contributions of individual EEG channels, extract spatial patterns, and visualize features. The superiority of DSTA-Net offers new insights for further research and application in MI. The code is available in https://github.com/CL-Cloud-BCI/DSTANet-code . Motor Imagery Stroke rehabilitation Dynamic Spatio-Temporal Feature Augmentation Network (DSTA-Net) Constrained Grouped Spatial Convolution Multi-level Spatial Features Full Text Additional Declarations No competing interests reported. The Supplementary materials file is not available with this version. Cite Share Download PDF Status: Published Journal Publication published 23 Jul, 2025 Read the published version in Cognitive Neurodynamics → Version 1 posted Editorial decision: Revision requested 04 May, 2025 Reviews received at journal 26 Mar, 2025 Reviewers agreed at journal 26 Mar, 2025 Reviewers invited by journal 26 Mar, 2025 Editor assigned by journal 12 Mar, 2025 Submission checks completed at journal 12 Mar, 2025 First submitted to journal 12 Mar, 2025 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-6208691","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":428255775,"identity":"25469618-d8cb-4775-8a99-8c86ffc91b49","order_by":0,"name":"liang Chang","email":"","orcid":"","institution":"Shanghai University","correspondingAuthor":false,"prefix":"","firstName":"liang","middleName":"","lastName":"Chang","suffix":""},{"id":428255777,"identity":"06104540-d8d3-41e4-a1d9-e5686e412aaa","order_by":1,"name":"banghua Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYJACZhBhwMDA+ICxAcRMIF4LswHJWtgkiNJicPzs4dcFNXfstkskP6v8ueMwAz97jgHDzx14tJzJS7OecexZ8s4ZaWa3ec8cZpDseWPA2HsGj5YDOWbGPGyHkw1uJJjdZmw7zGBwI8eAmbENj5bzb4Ba/oG0pH8r/AnUYk9Qy40c48e8bYftgAwzBl6QLRIEtEjeeGPGPLPvcILBmTfF0rxt6TwSZ54VHOzFo4XvfI7x54Jvh+0Njqdv/PizzVqOvz1544OfeLQoHABGB5BObIAK8ICIA7g1MDDINzAwfwDS9vgUjYJRMApGwQgHABEyWPE6JPrrAAAAAElFTkSuQmCC","orcid":"","institution":"Shanghai University","correspondingAuthor":true,"prefix":"","firstName":"banghua","middleName":"","lastName":"Yang","suffix":""},{"id":428255779,"identity":"88eda9a8-230e-4153-aae7-5c79f6dd2583","order_by":2,"name":"jiayang Zhang","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"jiayang","middleName":"","lastName":"Zhang","suffix":""},{"id":428255780,"identity":"adb3cf74-7732-4772-bca6-88eaee840a83","order_by":3,"name":"tie Li","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"tie","middleName":"","lastName":"Li","suffix":""},{"id":428255781,"identity":"698d64bb-9118-4d67-875b-9af110b04e5c","order_by":4,"name":"juntao Feng","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"juntao","middleName":"","lastName":"Feng","suffix":""},{"id":428255782,"identity":"de9e1c47-cd07-49c9-8e23-7f3534fee45b","order_by":5,"name":"wendong Xu","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"wendong","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2025-03-12 05:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6208691/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6208691/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11571-025-10296-0","type":"published","date":"2025-07-23T15:58:06+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":87756870,"identity":"27bbcbca-28ad-49c2-adc5-57afc009f73a","added_by":"auto","created_at":"2025-07-28 16:09:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1149160,"visible":true,"origin":"","legend":"","description":"","filename":"20250312DSTANet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6208691/v1_covered_e43d66bb-f7a3-4a47-8713-b41112bb92f0.pdf"}],"financialInterests":"\u003cp\u003eNo competing interests reported.\u003c/p\u003e\n\u003cp\u003eThe Supplementary materials file is not available with this version.\u0026nbsp;\u003c/p\u003e","formattedTitle":"DSTA-Net: Dynamic Spatio-Temporal Feature Augmentation Network for Motor Imagery Classification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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":"Motor Imagery, Stroke rehabilitation, Dynamic Spatio-Temporal Feature Augmentation Network (DSTA-Net), Constrained Grouped Spatial Convolution, Multi-level Spatial Features","lastPublishedDoi":"10.21203/rs.3.rs-6208691/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6208691/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate decoding and strong feature interpretability of Motor Imagery (MI) are expected to drive MI applications in stroke rehabilitation. However, the inherent nonstationarity and high intra-class variability of MI-EEG pose significant challenges in extracting reliable spatio-temporal features. We proposed the Dynamic Spatio-Temporal Feature Augmentation Network (DSTA-Net), which combines DSTA and the Spatio-Temporal Convolution (STC) modules. In DSTA module, multi-scale temporal convolutional kernels tailored to the α and β frequency bands of MI neurophysiological characteristics, while raw EEG serve as a baseline feature layer to retain original information. Next, Grouped Spatial Convolutions extract multi-level spatial features, combined with weight constraints to prevent overfitting. Spatial convolution kernels map EEG channel information into a new spatial domain, enabling further feature extraction through dimensional transformation. And STC module further extracts features and conducts classification. We evaluated DSTA-Net on three public datasets and applied it to a self-collected stroke dataset. In 10-fold cross-validation, DSTA-Net achieved average accuracy improvements of 6.29% (p\u0026lt;0.01), 3.05% (p\u0026lt;0.01), 5.26%(p\u0026lt;0.01), and 2.25% over the ShallowConvNet on the BCI-IV-2a, OpenBMI, CASIA, and stroke dataset, respectively. In hold-out validation, DSTA-Net achieved average accuracy improvements of 3.99% (p\u0026lt;0.01) and 4.2% (p\u0026lt;0.01) over the ShallowConvNet on the OpenBMI and CASIA datasets, respectively. Finally, we applied DeepLIFT, Common Spatial Pattern, and t-SNE to analyze the contributions of individual EEG channels, extract spatial patterns, and visualize features. The superiority of DSTA-Net offers new insights for further research and application in MI. The code is available in \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/CL-Cloud-BCI/DSTANet-code\u003c/span\u003e\u003cspan address=\"https://github.com/CL-Cloud-BCI/DSTANet-code\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"DSTA-Net: Dynamic Spatio-Temporal Feature Augmentation Network for Motor Imagery Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-18 05:37:15","doi":"10.21203/rs.3.rs-6208691/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-05T02:55:24+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-27T02:15:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"197061949301056214841178605037074099992","date":"2025-03-26T12:06:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-26T10:47:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-13T00:40:37+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-13T00:39:34+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cognitive Neurodynamics","date":"2025-03-12T05:09:26+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":"2f4f4007-54ef-41c0-b769-7507b339b193","owner":[],"postedDate":"March 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-07-28T16:06:43+00:00","versionOfRecord":{"articleIdentity":"rs-6208691","link":"https://doi.org/10.1007/s11571-025-10296-0","journal":{"identity":"cognitive-neurodynamics","isVorOnly":false,"title":"Cognitive Neurodynamics"},"publishedOn":"2025-07-23 15:58:06","publishedOnDateReadable":"July 23rd, 2025"},"versionCreatedAt":"2025-03-18 05:37:15","video":"","vorDoi":"10.1007/s11571-025-10296-0","vorDoiUrl":"https://doi.org/10.1007/s11571-025-10296-0","workflowStages":[]},"version":"v1","identity":"rs-6208691","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6208691","identity":"rs-6208691","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}