RAGMCL: A Correlation-Feature-Incorporated Multichannel Network for Signal Modulation Recognition

RAGMCL: A Correlation-Feature-Incorporated Multichannel Network for Signal Modulation 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 Article RAGMCL: A Correlation-Feature-Incorporated Multichannel Network for Signal Modulation Recognition Yangyang Wang, Fei Cao, Xiaolong Wang, Shunhu Hou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3842028/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 Signal modulation recognition (SMR) is crucial in wireless communication systems. In recent years, various modulation recognition algorithms based on deep learning have emerged. However, the problems of low recognition accuracy and a large number of network parameters have not been well solved. To overcome these challenges, this article presents an improved spatiotemporal multi-channel network (MCLDNN) called RAGMCL network by combining the signal correlation feature, attention mechanism module, and random Gaussian noise. The proposed approach introduces a four-channel convolutional network by augmenting the input of the original MCLDNN network with an additional channel. This channel utilizes the IQCLNet technique to extract relevant features from IQ signals, thereby enhancing the feature set used for network training. Moreover, an attention mechanism module is incorporated into the convolutional layer to assign training weights, emphasizing significant features during the learning process. Replacing the LSTM layer with BiGRU to exploit the IQ signal features fully. Additionally, introducing random Gaussian noise after the fully connected layer to discard irrelevant output features randomly, enhances the model's robustness and recognition accuracy. The RAGMCL network is evaluated using four publicly available datasets: RML2016.10a, RML2016.10b, RML2016.04c, and RML2018.01a. Experimental results demonstrate that the RAGMCL network achieves higher recognition accuracy across all four datasets while reducing the model parameters by 19.85%, combining the advantages of low number of parameters and high recognition accuracy. The RAGMCL network designed in this thesis holds potential for satellite communication applications. Physical sciences/Mathematics and computing/Computer science Physical sciences/Engineering/Aerospace engineering Physical sciences/Engineering/Electrical and electronic engineering 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-3842028","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":266860514,"identity":"3a5fec12-4f7d-4d2d-832b-d536a7d534c7","order_by":0,"name":"Yangyang Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIie3PsUvDQBTH8Scn53Jt1jvU9l84ELL4z7wjkE10zBBrB3kZSvf2v+jY8ULhspx73OKik2A3OwgSCo5JxoL3HX5w8D7DAYRCJxmz7U74RVE2mOVDCMd2byLhE914N4QI3a5ZrzBWb8+sH4wrjOVh+3i2sZhmZs4hKhbYSZRvUrX0FdO2dLXZXoH0L5tOomt0ckSO63Ke1sZz0PKujxhSP+SE3kH8YIgNIQm/HFEuFUEMg4jy7+z2mqyOhEgkeid6/zKu7vevnzR7oulHuf/O8klULLsJWDyXALu/t+g+PxL2BTDrPwyFQqH/2y9QJ1HDPz2okQAAAABJRU5ErkJggg==","orcid":"","institution":"Rocket Force University of Engineering","correspondingAuthor":true,"prefix":"","firstName":"Yangyang","middleName":"","lastName":"Wang","suffix":""},{"id":266860515,"identity":"ed4f9448-7d18-45a5-ae65-d7319bddd6c0","order_by":1,"name":"Fei Cao","email":"","orcid":"","institution":"Rocket Force University of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Fei","middleName":"","lastName":"Cao","suffix":""},{"id":266860516,"identity":"de4fa602-b8e7-4780-91a9-6b0eb58c2013","order_by":2,"name":"Xiaolong Wang","email":"","orcid":"","institution":"Rocket Force University of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Xiaolong","middleName":"","lastName":"Wang","suffix":""},{"id":266860517,"identity":"ab30839d-26b4-4778-8b18-550037fd61ca","order_by":3,"name":"Shunhu Hou","email":"","orcid":"","institution":"Space Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Shunhu","middleName":"","lastName":"Hou","suffix":""}],"badges":[],"createdAt":"2024-01-07 09:14:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3842028/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3842028/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57331725,"identity":"5c6f301f-8519-4f76-837c-3ae2bcdbb9d5","added_by":"auto","created_at":"2024-05-29 08:37:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3073850,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3842028/v1_covered_2e57381b-4881-44f7-a86f-1c6feef0709b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"RAGMCL: A Correlation-Feature-Incorporated Multichannel Network for Signal Modulation Recognition","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":"[email protected]","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":"","lastPublishedDoi":"10.21203/rs.3.rs-3842028/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3842028/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSignal modulation recognition (SMR) is crucial in wireless communication systems. In recent years, various modulation recognition algorithms based on deep learning have emerged. However, the problems of low recognition accuracy and a large number of network parameters have not been well solved. To overcome these challenges, this article presents an improved spatiotemporal multi-channel network (MCLDNN) called RAGMCL network by combining the signal correlation feature, attention mechanism module, and random Gaussian noise. The proposed approach introduces a four-channel convolutional network by augmenting the input of the original MCLDNN network with an additional channel. This channel utilizes the IQCLNet technique to extract relevant features from IQ signals, thereby enhancing the feature set used for network training. Moreover, an attention mechanism module is incorporated into the convolutional layer to assign training weights, emphasizing significant features during the learning process. Replacing the LSTM layer with BiGRU to exploit the IQ signal features fully. Additionally, introducing random Gaussian noise after the fully connected layer to discard irrelevant output features randomly, enhances the model's robustness and recognition accuracy. The RAGMCL network is evaluated using four publicly available datasets: RML2016.10a, RML2016.10b, RML2016.04c, and RML2018.01a. Experimental results demonstrate that the RAGMCL network achieves higher recognition accuracy across all four datasets while reducing the model parameters by 19.85%, combining the advantages of low number of parameters and high recognition accuracy. The RAGMCL network designed in this thesis holds potential for satellite communication applications.\u003c/p\u003e","manuscriptTitle":"RAGMCL: A Correlation-Feature-Incorporated Multichannel Network for Signal Modulation Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-16 08:12:52","doi":"10.21203/rs.3.rs-3842028/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","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":"055fbb06-608e-4503-8c69-0477aa32ff6c","owner":[],"postedDate":"January 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":28122897,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":28122898,"name":"Physical sciences/Engineering/Aerospace engineering"},{"id":28122899,"name":"Physical sciences/Engineering/Electrical and electronic engineering"}],"tags":[],"updatedAt":"2024-05-29T08:29:17+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-16 08:12:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3842028","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3842028","identity":"rs-3842028","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}