A pre-averaged pseudo nearest neighbor classifier

A pre-averaged pseudo nearest neighbor classifier | 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Download PDF Research Article A pre-averaged pseudo nearest neighbor classifier Dapeng Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3845132/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 K nearest neighbor rule is a powerful classification method. However, its classification performance will be affected in the situation of small-size samples with existing outliers. To address this issue, a pre-averaged pseudo nearest neighbor classifier (PAPNN) is proposed to improve classification performance. In the PAPNN rule, pre-averaged categorical vectors are calculated by taking the average of any two points of the training sets in each class, and then k pseudo nearest neighbors are chosen from the preprocessed vectors of every class to determine the category of a query point. The pre-averaged vectors can reduce the negative impact of outliers in some degree. Extensive experiments are carried out on nineteen numerical real data sets and three artificial data sets by comparing PAPNN to other five KNN-based methods. The experimental results demonstrate that the proposed PAPNN rule is effective for classification task in the case of small-size samples with existing outliers. pre-averaged pseudo nearest neighbors small-size samples nearest neighbors 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-3845132","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":266596387,"identity":"8e8cecc2-b26f-46d8-b718-657a54d121c0","order_by":0,"name":"Dapeng Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtElEQVRIiWNgGAWjYBACPmYGAwYJAwk5Nvb2A8RpYQNpsaiwMObjOZNApBYGoJaKMxWJ8yQcDIjUws687cHNNon0NgmGBIYfFduIcRhbueHMNoncNunGA4w9Z24To4XHTFoSpEXmQAIzYxuxWv4CHcYmkWBAvBYJiTMSCaRoYSs3kKiQMGwDBvJBovzCz3942wMJgzp5+fb2gw9+VBChhQEcNVBwgCj1KFpGwSgYBaNgFGAFAG6OMcBYAn91AAAAAElFTkSuQmCC","orcid":"","institution":"Jinling Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Dapeng","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-01-08 10:29:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3845132/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3845132/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":50061638,"identity":"7716217a-a324-4ee4-b32a-57dbdcbb287b","added_by":"auto","created_at":"2024-01-23 20:08:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":413761,"visible":true,"origin":"","legend":"","description":"","filename":"snarticletemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3845132/v1_covered_51977d43-1a64-4301-af73-60ca60083f8c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A pre-averaged pseudo nearest neighbor classifier","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":"pre-averaged, pseudo nearest neighbors, small-size samples, nearest neighbors","lastPublishedDoi":"10.21203/rs.3.rs-3845132/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3845132/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"K nearest neighbor rule is a powerful classification method. However, its classification performance will be affected in the situation of small-size samples with existing outliers. To address this issue, a pre-averaged pseudo nearest neighbor classifier (PAPNN) is proposed to improve classification performance. In the PAPNN rule, pre-averaged categorical vectors are calculated by taking the average of any two points of the training sets in each class, and then k pseudo nearest neighbors are chosen from the preprocessed vectors of every class to determine the category of a query point. The pre-averaged vectors can reduce the negative impact of outliers in some degree. Extensive experiments are carried out on nineteen numerical real data sets and three artificial data sets by comparing PAPNN to other five KNN-based methods. The experimental results demonstrate that the proposed PAPNN rule is effective for classification task in the case of small-size samples with existing outliers.","manuscriptTitle":"A pre-averaged pseudo nearest neighbor classifier","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-15 02:43:35","doi":"10.21203/rs.3.rs-3845132/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":"a7c6b87c-958a-41f4-bcee-3b189df50608","owner":[],"postedDate":"January 15th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-01-23T20:00:01+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-15 02:43:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3845132","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3845132","identity":"rs-3845132","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}