SEGMTM: A Spectrum Prediction Method Based on Enhanced Graph Convolution and Multi-scale Time Decomposition

SEGMTM: A Spectrum Prediction Method Based on Enhanced Graph Convolution and Multi-scale Time Decomposition | 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 SEGMTM: A Spectrum Prediction Method Based on Enhanced Graph Convolution and Multi-scale Time Decomposition Yong Meng, Suting Chen, Xinyu Lu, Wenliang Xu, Zhenxing Shi, Xuefen Zhou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5297237/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 May, 2025 Read the published version in Multimedia Systems → Version 1 posted 9 You are reading this latest preprint version Abstract The development of wireless communication technology has led to increasing pressure on spectrum resources, making the rational allocation and utilization of these resources a significant challenge both now and in the future. Although spectrum data is a complex nonlinear time series, it exhibits a high degree of temporal and spatial correlation, providing new directions for addressing the issue of spectrum resource scarcity. In response to this situation, this study constructs a multi-scale spatio-temporal spectrum prediction method based on deep learning. First, we analyze the correlations present in different channels of spectrum data and utilize singular spectrum analysis (SSA) to decompose the complex spectrum data into a series of frequency components with underlying structures and patterns. Subsequently, we propose a spectrum prediction model (SEGMTM) that includes an attention-based enhanced graph convolutional network module (A-EGCN) and a multi-scale temporal module (MTM) to model the spatial and temporal correlations of the spectrum data, respectively. Furthermore, to reduce model complexity, we design a D-Regression module for auxiliary predictions. We validate the effectiveness of the proposed method through spectrum quality prediction and spectrum state prediction on two real measured spectrum datasets. Experimental results demonstrate that the proposed method achieves outstanding performance in both prediction tasks, with particularly notable advantages in long-term prediction tasks. In the spectrum quality prediction task, evaluation metrics show an improvement of 1.72% to 21.19%, while in the spectrum state prediction task, the accuracy improves by 1.28% to 3.51%. Spectrum prediction Bidirectional equidistant convolution Singular spectrum analysis GCN Attention Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 12 May, 2025 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 12 Feb, 2025 Reviews received at journal 11 Feb, 2025 Reviewers agreed at journal 08 Feb, 2025 Reviews received at journal 04 Jan, 2025 Reviewers agreed at journal 13 Dec, 2024 Reviewers invited by journal 01 Dec, 2024 Editor assigned by journal 01 Dec, 2024 Submission checks completed at journal 21 Oct, 2024 First submitted to journal 20 Oct, 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-5297237","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":368656860,"identity":"6f1b2ab5-81b3-4cda-8590-8ba835d8eb02","order_by":0,"name":"Yong Meng","email":"","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yong","middleName":"","lastName":"Meng","suffix":""},{"id":368656861,"identity":"3673f457-2930-4f61-bae4-334d568e6ab1","order_by":1,"name":"Suting Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+klEQVRIiWNgGAWjYJCCA0CcwMDADKQNwAIGBDQww7SwJYAUSxClhQGihQeskrAW+Rn5Bw8X/LLL45fu+faYp6CujoG9eZsEQ80dnFoMbiQzHJ7Zl1wsOefsdmMeg8MSDDzHyiQYjj3DrUUCqIW350Dihhu526R5DA5IMEjkmEkwNhzG4zColv03cp4BtdRJMMi/wa+FAeQwnh9AWyRy2IBamIG28ODXYnDmscFh3obkxBk30swk5xgclmzjSSu2SDiGx2HtiY8/8/yxS+yfkfxM4s2fOn5+9sMbb3yoweMwEGBsQ+KwgYgE/BqA4A9BFaNgFIyCUTCSAQARk1F7nuI4fgAAAABJRU5ErkJggg==","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Suting","middleName":"","lastName":"Chen","suffix":""},{"id":368656862,"identity":"a6e921ee-7622-4827-bdba-ca7b7615bfa3","order_by":2,"name":"Xinyu Lu","email":"","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Lu","suffix":""},{"id":368656863,"identity":"a2506835-d24c-446b-8e69-671c667b9be2","order_by":3,"name":"Wenliang Xu","email":"","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Wenliang","middleName":"","lastName":"Xu","suffix":""},{"id":368656864,"identity":"42e2eb36-b93e-414b-8919-6a2a70a92f15","order_by":4,"name":"Zhenxing Shi","email":"","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhenxing","middleName":"","lastName":"Shi","suffix":""},{"id":368656865,"identity":"5d8f8819-738e-4ad5-9ec4-b4580a4b6943","order_by":5,"name":"Xuefen Zhou","email":"","orcid":"","institution":"Nanjing University of Information Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xuefen","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2024-10-20 07:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5297237/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5297237/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-025-01828-z","type":"published","date":"2025-05-12T15:57:46+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":83067813,"identity":"8ba4cebe-275c-46d2-b0d2-7f8c49eb6154","added_by":"auto","created_at":"2025-05-19 16:06:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7317869,"visible":true,"origin":"","legend":"","description":"","filename":"SEGMTMASpectrumPredictionMethodBasedonEnhancedGraphConvolutionandMultiscaleTimeDecomposition.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5297237/v1_covered_a88c01a5-b408-4cd7-9f54-1766de033f09.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SEGMTM: A Spectrum Prediction Method Based on Enhanced Graph Convolution and Multi-scale Time Decomposition","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":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Spectrum prediction, Bidirectional equidistant convolution, Singular spectrum analysis, GCN, Attention","lastPublishedDoi":"10.21203/rs.3.rs-5297237/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5297237/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe development of wireless communication technology has led to increasing pressure on spectrum resources, making the rational allocation and utilization of these resources a significant challenge both now and in the future. Although spectrum data is a complex nonlinear time series, it exhibits a high degree of temporal and spatial correlation, providing new directions for addressing the issue of spectrum resource scarcity. In response to this situation, this study constructs a multi-scale spatio-temporal spectrum prediction method based on deep learning. First, we analyze the correlations present in different channels of spectrum data and utilize singular spectrum analysis (SSA) to decompose the complex spectrum data into a series of frequency components with underlying structures and patterns. Subsequently, we propose a spectrum prediction model (SEGMTM) that includes an attention-based enhanced graph convolutional network module (A-EGCN) and a multi-scale temporal module (MTM) to model the spatial and temporal correlations of the spectrum data, respectively. Furthermore, to reduce model complexity, we design a D-Regression module for auxiliary predictions. We validate the effectiveness of the proposed method through spectrum quality prediction and spectrum state prediction on two real measured spectrum datasets. Experimental results demonstrate that the proposed method achieves outstanding performance in both prediction tasks, with particularly notable advantages in long-term prediction tasks. In the spectrum quality prediction task, evaluation metrics show an improvement of 1.72% to 21.19%, while in the spectrum state prediction task, the accuracy improves by 1.28% to 3.51%.\u003c/p\u003e","manuscriptTitle":"SEGMTM: A Spectrum Prediction Method Based on Enhanced Graph Convolution and Multi-scale Time Decomposition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-04 05:59:14","doi":"10.21203/rs.3.rs-5297237/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-02-13T02:34:19+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-11T07:12:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"257564425266844291612521228216653337214","date":"2025-02-08T08:58:32+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-04T08:25:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"319094540102443716849928496464647712818","date":"2024-12-14T04:05:42+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-12-02T01:46:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-12-01T09:37:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-10-21T15:23:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2024-10-20T07:27:32+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"03a597a4-abf1-4641-abd5-6f41694f073d","owner":[],"postedDate":"November 4th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-05-19T16:01:39+00:00","versionOfRecord":{"articleIdentity":"rs-5297237","link":"https://doi.org/10.1007/s00530-025-01828-z","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2025-05-12 15:57:46","publishedOnDateReadable":"May 12th, 2025"},"versionCreatedAt":"2024-11-04 05:59:14","video":"","vorDoi":"10.1007/s00530-025-01828-z","vorDoiUrl":"https://doi.org/10.1007/s00530-025-01828-z","workflowStages":[]},"version":"v1","identity":"rs-5297237","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5297237","identity":"rs-5297237","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}