{"id":"https://openalex.org/W2113540758","doi":"https://doi.org/10.1109/tsmcb.2008.2004559","title":"K-Means Clustering Versus Validation Measures: A Data-Distribution Perspective","display_name":"K-Means Clustering Versus Validation Measures: A Data-Distribution Perspective","publication_year":2008,"publication_date":"2008-12-18","ids":{"openalex":"https://openalex.org/W2113540758","doi":"https://doi.org/10.1109/tsmcb.2008.2004559","mag":"2113540758","pmid":"https://pubmed.ncbi.nlm.nih.gov/19095536"},"language":"en","primary_location":{"id":"doi:10.1109/tsmcb.2008.2004559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2008.2004559","pdf_url":null,"source":{"id":"https://openalex.org/S4210170378","display_name":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","issn_l":"1083-4419","issn":["1083-4419","1941-0492"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["Management Science and Information Systems Department, Rutgers Business School, Rutgers University, Newark, NJ 07102 USA. hxiong@rutgers.edu","Manage. Sci. & Inf. Syst. Dept., Rutgers Univ., Newark, NJ"],"affiliations":[{"raw_affiliation_string":"Management Science and Information Systems Department, Rutgers Business School, Rutgers University, Newark, NJ 07102 USA. hxiong@rutgers.edu","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Manage. Sci. & Inf. Syst. Dept., Rutgers Univ., Newark, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112210049","display_name":"Junjie Wu","orcid":"https://orcid.org/0009-0009-4993-8976"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wu","raw_affiliation_strings":["School of Economics and Management, Beihang University, Beijing, China","Sch. of Econ. & Manage., BeiHang Univ., Beijing"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Sch. of Econ. & Manage., BeiHang Univ., Beijing","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326440","display_name":"Jian Chen","orcid":"https://orcid.org/0000-0002-2097-5740"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Chen","raw_affiliation_strings":["Research Center of Contemporary Management, School of Economics and Management, Key Research Institute of Humanities and Social Sciences, Tsinghua University, Beijing, China","Sch. of Econ. & Manage., Tsinghua Univ., Beijing"],"affiliations":[{"raw_affiliation_string":"Research Center of Contemporary Management, School of Economics and Management, Key Research Institute of Humanities and Social Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Sch. of Econ. & Manage., Tsinghua Univ., Beijing","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101862104"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":14.6641,"has_fulltext":false,"cited_by_count":277,"citation_normalized_percentile":{"value":0.98869096,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"39","issue":"2","first_page":"318","last_page":"331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8916345238685608},{"id":"https://openalex.org/keywords/k-medians-clustering","display_name":"k-medians clustering","score":0.6286389827728271},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.596403956413269},{"id":"https://openalex.org/keywords/determining-the-number-of-clusters-in-a-data-set","display_name":"Determining the number of clusters in a data set","score":0.5399496555328369},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5334357023239136},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5157866477966309},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4930402934551239},{"id":"https://openalex.org/keywords/complete-linkage-clustering","display_name":"Complete-linkage clustering","score":0.49024420976638794},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47957032918930054},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.47631511092185974},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47504758834838867},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.43744584918022156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43301305174827576},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.42889857292175293},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3767433762550354},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.138724684715271}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8916345238685608},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.6286389827728271},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.596403956413269},{"id":"https://openalex.org/C149872217","wikidata":"https://www.wikidata.org/wiki/Q5265701","display_name":"Determining the number of clusters in a data set","level":5,"score":0.5399496555328369},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5334357023239136},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5157866477966309},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4930402934551239},{"id":"https://openalex.org/C23822008","wikidata":"https://www.wikidata.org/wiki/Q5156437","display_name":"Complete-linkage clustering","level":5,"score":0.49024420976638794},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47957032918930054},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.47631511092185974},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47504758834838867},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.43744584918022156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43301305174827576},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.42889857292175293},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3767433762550354},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.138724684715271},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tsmcb.2008.2004559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2008.2004559","pdf_url":null,"source":{"id":"https://openalex.org/S4210170378","display_name":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","issn_l":"1083-4419","issn":["1083-4419","1941-0492"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)","raw_type":"journal-article"},{"id":"pmid:19095536","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19095536","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.5024","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.5024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cimic.rutgers.edu/~hui/publication/measurekdd06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W9613553","https://openalex.org/W147860157","https://openalex.org/W1488289178","https://openalex.org/W1565377632","https://openalex.org/W1651093245","https://openalex.org/W1673310716","https://openalex.org/W1760551737","https://openalex.org/W1938740620","https://openalex.org/W1971784203","https://openalex.org/W1996510517","https://openalex.org/W2020362899","https://openalex.org/W2061240327","https://openalex.org/W2070412788","https://openalex.org/W2071664212","https://openalex.org/W2084812512","https://openalex.org/W2087962968","https://openalex.org/W2089923519","https://openalex.org/W2095897464","https://openalex.org/W2097253747","https://openalex.org/W2097413644","https://openalex.org/W2098162425","https://openalex.org/W2103868202","https://openalex.org/W2122943553","https://openalex.org/W2122994019","https://openalex.org/W2123386615","https://openalex.org/W2123497041","https://openalex.org/W2127218421","https://openalex.org/W2136663225","https://openalex.org/W2138218344","https://openalex.org/W2144182447","https://openalex.org/W2146483359","https://openalex.org/W2149148023","https://openalex.org/W2157665255","https://openalex.org/W2158312857","https://openalex.org/W2168667497","https://openalex.org/W2171975443","https://openalex.org/W2482589566","https://openalex.org/W3099514962","https://openalex.org/W3099839986","https://openalex.org/W3139328003","https://openalex.org/W3145074154","https://openalex.org/W4205380271","https://openalex.org/W4205864049","https://openalex.org/W4231029117","https://openalex.org/W4234315553","https://openalex.org/W4234317230","https://openalex.org/W4245322178","https://openalex.org/W4254182148","https://openalex.org/W4285719527","https://openalex.org/W4301491118","https://openalex.org/W6600399310","https://openalex.org/W6606145560","https://openalex.org/W6637131181","https://openalex.org/W6637231022","https://openalex.org/W6678914141","https://openalex.org/W6680536130","https://openalex.org/W6683235873"],"related_works":["https://openalex.org/W4241767317","https://openalex.org/W2599570117","https://openalex.org/W1491908038","https://openalex.org/W3092684173","https://openalex.org/W2129417512","https://openalex.org/W3004745571","https://openalex.org/W2342508359","https://openalex.org/W4200404937","https://openalex.org/W2085801246","https://openalex.org/W4310575853"],"abstract_inverted_index":{"K-means":[0,23,42,65,75,145,183,210,229],"is":[1,28],"a":[2,52,133,163],"well-known":[3],"and":[4,54,113],"widely":[5],"used":[6],"partitional":[7],"clustering":[8,24,99,119,139,232],"method.":[9],"While":[10],"there":[11],"are":[12,161,235],"considerable":[13],"research":[14],"efforts":[15],"to":[16,30,77,136,147,190,217],"characterize":[17],"the":[18,22,39,58,104,118,127,138,152,225,231,238],"key":[19],"features":[20],"of":[21,41,57,60,80,129,154,165],"algorithm,":[25],"further":[26],"investigation":[27],"needed":[29],"understand":[31],"how":[32],"data":[33,62,87,170,197],"distributions":[34,63],"can":[35],"have":[36,88],"impact":[37],"on":[38,64,117],"performance":[40],"clustering.":[43,66],"To":[44],"that":[45,74,97,144],"end,":[46],"in":[47,122,150,162,175,186,202,213],"this":[48,68,110,123],"paper,":[49],"we":[50,70,95,125],"provide":[51,114,126],"formal":[53],"organized":[55],"study":[56],"effect":[59,112],"skewed":[61],"Along":[67],"line,":[69],"first":[71],"formally":[72],"illustrate":[73],"tends":[76,146],"produce":[78,148],"clusters":[79,149],"relatively":[81],"uniform":[82,111],"size,":[83],"even":[84],"if":[85],"input":[86],"varied":[89],"\"true\"":[90,176,203,239],"cluster":[91,155,177,188,204,215,240],"sizes.":[92],"In":[93,194,221],"addition,":[94],"show":[96],"some":[98],"validation":[100],"measures,":[101],"such":[102],"as":[103,132,157],"entropy":[105],"measure,":[106],"may":[107],"not":[108],"capture":[109],"misleading":[115],"information":[116],"performance.":[120],"Viewed":[121],"light,":[124],"coefficient":[128],"variation":[130,174,185,201,212],"(CV)":[131],"necessary":[134],"criterion":[135],"validate":[137],"results.":[140],"Our":[141],"findings":[142],"reveal":[143],"which":[151,234],"variations":[153],"sizes,":[156],"measured":[158],"by":[159],"CV,":[160],"range":[164],"about":[166],"0.3-1.0.":[167],"Specifically,":[168],"for":[169,196,224],"sets":[171,198],"with":[172,199],"large":[173],"sizes":[178,189,205,216],"(e.g.,":[179,206],"CV":[180,207],">":[181],"1.0),":[182],"reduces":[184],"resultant":[187,214],"less":[191],"than":[192,219],"1.0.":[193],"contrast,":[195],"small":[200],"<":[208],"0.3),":[209],"increases":[211],"greater":[218],"0.3.":[220],"other":[222],"words,":[223],"earlier":[226],"two":[227],"cases,":[228],"produces":[230],"results":[233],"away":[236],"from":[237],"distributions.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":24},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":22}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}