An Interpretable Classification Model for UAV and Non-UAV based on LightGBM and SHAP with Radar Data Feature Fusion

An Interpretable Classification Model for UAV and Non-UAV based on LightGBM and SHAP with Radar Data Feature Fusion | 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 An Interpretable Classification Model for UAV and Non-UAV based on LightGBM and SHAP with Radar Data Feature Fusion Kaiqian Li, Shengbo Hu, Xu Wei This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6202423/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 The rapid development of UAV technology has raised concerns about low-altitude safety, with UAVs often being mistaken for birds and balloons. This paper proposes an interpretable LightGBM classification method that integrates radar data features to classify UAVs and Non-UAVs. In this paper, a fusion feature set of motion, radar cross-section (RCS), and track is constructed. The Light-GBM model’s hyperparameters are then optimized through a grid search, and the model’s classification capability is assessed using a 5-fold cross-validation approach. Furthermore, SHAP values are used to quantify the contribution of each feature. In the validation experiments, the results show that the proposed method can effectively separate UAV and non-UAV trajectories. The classification accuracies for UAVs, non-UAVs, and overall classification are 91%, 94%, and 92.55%, respectively. These results outperform those obtained with SVM, random forest, and BPNN algorithms, as well as those using two-feature fusions. This highlights the effectiveness and practicality of the proposed method. Furthermore, the interpretable framework enhances the transparency of the model, making it easier to analyze the reliability of the classification results. UAV classification Feature fusion LightGBM Model interpretation 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-6202423","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":452321012,"identity":"ab7aac0e-6225-4dbb-8acf-a580d683f79d","order_by":0,"name":"Kaiqian Li","email":"","orcid":"","institution":"Guizhou Normal University","correspondingAuthor":false,"prefix":"","firstName":"Kaiqian","middleName":"","lastName":"Li","suffix":""},{"id":452321013,"identity":"1990acd6-30ed-4fc3-853b-0fd8bbc63076","order_by":1,"name":"Shengbo Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtUlEQVRIiWNgGAWjYBACAwYexgdwNrFamA3gbGK1sEmQpsWc/+yxyi9/7iQ2sDdvk2CouUNYi+WMvLTbMjzPEht4jpVJMBx7RoTDbvCY3ZaQOJzYIJFjJsHYcJgILefPmBVLGAC1yL8hVsuBHDPGDwkgW3iI1XIjL1ma4cBh4zaetGKLhGNEOezswY8//hyW7Wc/vPHGhxoitIAAMw+QYAOxEojTwMDA+INYlaNgFIyCUTAyAQBu0jnxQMvNmAAAAABJRU5ErkJggg==","orcid":"","institution":"Guizhou Normal University","correspondingAuthor":true,"prefix":"","firstName":"Shengbo","middleName":"","lastName":"Hu","suffix":""},{"id":452321014,"identity":"a332966f-ac38-4311-b0c0-9350ee7a2b73","order_by":2,"name":"Xu Wei","email":"","orcid":"","institution":"Guizhou Aerospace Nanhai Science \u0026 Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Wei","suffix":""}],"badges":[],"createdAt":"2025-03-11 11:23:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6202423/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6202423/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87098681,"identity":"00512114-dd81-407a-a8c0-31cf047cc893","added_by":"auto","created_at":"2025-07-19 11:47:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":10390044,"visible":true,"origin":"","legend":"","description":"","filename":"AnInterpretableClassificationModelforUAVandNonUAVbasedonLightGBMandSHAPwithRadarDataFeatureFusion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6202423/v1_covered_8a1e3886-88be-4712-8112-1fb8fd1a2558.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Interpretable Classification Model for UAV and Non-UAV based on LightGBM and SHAP with Radar Data Feature Fusion","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":"UAV classification, Feature fusion, LightGBM, Model interpretation","lastPublishedDoi":"10.21203/rs.3.rs-6202423/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6202423/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe rapid development of UAV technology has raised concerns about low-altitude safety, with UAVs often being mistaken for birds and balloons. This paper proposes an interpretable LightGBM classification method that integrates radar data features to classify UAVs and Non-UAVs. In this paper, a fusion feature set of motion, radar cross-section (RCS), and track is constructed. The Light-GBM model’s hyperparameters are then optimized through a grid search, and the model’s classification capability is assessed using a 5-fold cross-validation approach. Furthermore, SHAP values are used to quantify the contribution of each feature. In the validation experiments, the results show that the proposed method can effectively separate UAV and non-UAV trajectories. The classification accuracies for UAVs, non-UAVs, and overall classification are 91%, 94%, and 92.55%, respectively. These results outperform those obtained with SVM, random forest, and BPNN algorithms, as well as those using two-feature fusions. This highlights the effectiveness and practicality of the proposed method. Furthermore, the interpretable framework enhances the transparency of the model, making it easier to analyze the reliability of the classification results.\u003c/p\u003e","manuscriptTitle":"An Interpretable Classification Model for UAV and Non-UAV based on LightGBM and SHAP with Radar Data Feature Fusion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-06 07:09:12","doi":"10.21203/rs.3.rs-6202423/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":"05671ef8-75a2-479e-9925-52aa444173c6","owner":[],"postedDate":"May 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-07-19T11:38:45+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-06 07:09:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6202423","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6202423","identity":"rs-6202423","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}