Massive MIMO-FDD Self-Attention CSI Feedback Networkfor Outdoor Environments

Massive MIMO-FDD Self-Attention CSI Feedback Networkfor Outdoor Environments | 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 Massive MIMO-FDD Self-Attention CSI Feedback Networkfor Outdoor Environments Linyu Wang, Yi Cao, Jianhong Xiang, Hanyu Jiang, Yu Zhong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4212445/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 In situations where traditional feedback methods face high complexity and rely on channel sparsity,many deep learning-based CSI compression feedback methods have shown the potential to fullycapture the diversity and multiplexing gains of Massive MIMO technology in Frequency DivisionDuplex (FDD) mode. In order to further enhance the accuracy of obtaining downlink channel stateinformation at the base station side, this paper proposes a novel neural network, SfNet. Basedon visual analysis, the convolutional layers in the encoder are designed to extract long-distancetime-delay correlations of the same antenna across different subcarriers. The SimAM module isintroduced to mitigate clustering effects. In the decoder, a spatial-temporal joint modeling approachis presented, utilizing the CBAM module to preserve the original spatial structure features lostduring the dimension reduction of the CSI matrix to sequence data. Subsequently, two layers ofTransformer multi-head attention are employed to achieve more global time-series modeling.Theexperimental results indicate that, compared to CLNet, the average complexity of SfNet’s encoder isreduced by 3.4%. It meets the demand for lightweight devices on the user side. In terms of accuracy,SfNet exhibits an average improvement of 30.17% compared to TransNet in outdoor environments. Massive MIMO CSI Feedback Deep Learning CNN Transformer Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 13 Apr, 2024 Reviews received at journal 13 Apr, 2024 Reviewers agreed at journal 04 Apr, 2024 Reviewers invited by journal 03 Apr, 2024 Submission checks completed at journal 03 Apr, 2024 Editor assigned by journal 03 Apr, 2024 First submitted to journal 03 Apr, 2024 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-4212445","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":288129376,"identity":"a7db6706-2cea-4c99-acf3-b3ed16fb2e4c","order_by":0,"name":"Linyu Wang","email":"","orcid":"","institution":"Harbin Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Linyu","middleName":"","lastName":"Wang","suffix":""},{"id":288129377,"identity":"b96adb25-acf9-4b5e-8124-f9726df06cb2","order_by":1,"name":"Yi Cao","email":"","orcid":"","institution":"Harbin Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Cao","suffix":""},{"id":288129378,"identity":"ef96a2c7-80cf-43f8-9f2d-81128c111d26","order_by":2,"name":"Jianhong Xiang","email":"data:image/png;base64,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","orcid":"","institution":"Harbin Engineering University","correspondingAuthor":true,"prefix":"","firstName":"Jianhong","middleName":"","lastName":"Xiang","suffix":""},{"id":288129379,"identity":"85e017ed-6382-454e-a6ac-5568b3c215d5","order_by":3,"name":"Hanyu Jiang","email":"","orcid":"","institution":"Harbin Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Hanyu","middleName":"","lastName":"Jiang","suffix":""},{"id":288129380,"identity":"c8eb3074-b9c0-40c0-a4b7-a10372a9ae9c","order_by":4,"name":"Yu Zhong","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Zhong","suffix":""}],"badges":[],"createdAt":"2024-04-03 11:40:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4212445/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4212445/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54339747,"identity":"d03f0318-93c1-41f5-b2aa-75fe512fbdc5","added_by":"auto","created_at":"2024-04-09 04:33:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":395445,"visible":true,"origin":"","legend":"","description":"","filename":"SfNet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4212445/v1_covered_0a468d72-6cbe-44ca-8c54-d667e3ed18f3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eMassive MIMO-FDD Self-Attention CSI Feedback Networkfor Outdoor Environments\u003c/p\u003e","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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Massive MIMO,CSI Feedback, Deep Learning, CNN, Transformer","lastPublishedDoi":"10.21203/rs.3.rs-4212445/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4212445/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In situations where traditional feedback methods face high complexity and rely on channel sparsity,many deep learning-based CSI compression feedback methods have shown the potential to fullycapture the diversity and multiplexing gains of Massive MIMO technology in Frequency DivisionDuplex (FDD) mode. In order to further enhance the accuracy of obtaining downlink channel stateinformation at the base station side, this paper proposes a novel neural network, SfNet. Basedon visual analysis, the convolutional layers in the encoder are designed to extract long-distancetime-delay correlations of the same antenna across different subcarriers. The SimAM module isintroduced to mitigate clustering effects. In the decoder, a spatial-temporal joint modeling approachis presented, utilizing the CBAM module to preserve the original spatial structure features lostduring the dimension reduction of the CSI matrix to sequence data. Subsequently, two layers ofTransformer multi-head attention are employed to achieve more global time-series modeling.Theexperimental results indicate that, compared to CLNet, the average complexity of SfNet’s encoder isreduced by 3.4%. It meets the demand for lightweight devices on the user side. In terms of accuracy,SfNet exhibits an average improvement of 30.17% compared to TransNet in outdoor environments.","manuscriptTitle":"Massive MIMO-FDD Self-Attention CSI Feedback Networkfor Outdoor Environments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-09 04:25:26","doi":"10.21203/rs.3.rs-4212445/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-04-14T00:19:20+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-13T11:29:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"2fbb13ba-54f4-449c-93ac-c95a67a64a10","date":"2024-04-05T03:53:23+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-04-04T03:57:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-03T13:02:20+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-03T13:02:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2024-04-03T11:38:50+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"c36738b9-a158-4a05-973d-7921d4534698","owner":[],"postedDate":"April 9th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-04-28T00:41:41+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-09 04:25:26","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4212445","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4212445","identity":"rs-4212445","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}