{"id":"https://openalex.org/W3022935443","doi":"https://doi.org/10.1145/3388142.3388164","title":"Fast Automatic Determination of Cluster Numbers for High Dimensional Big Data","display_name":"Fast Automatic Determination of Cluster Numbers for High Dimensional Big Data","publication_year":2020,"publication_date":"2020-03-09","ids":{"openalex":"https://openalex.org/W3022935443","doi":"https://doi.org/10.1145/3388142.3388164","mag":"3022935443"},"language":"en","primary_location":{"id":"doi:10.1145/3388142.3388164","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3388142.3388164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th International Conference on Compute and Data Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5017642649","display_name":"Zohreh Safari","orcid":null},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zohreh Safari","raw_affiliation_strings":["Department of Computer Science, Texas Tech University, Lubbock, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas Tech University, Lubbock, TX","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003062703","display_name":"Khalid T. Mursi","orcid":"https://orcid.org/0000-0001-8032-8484"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]},{"id":"https://openalex.org/I4210099699","display_name":"University of Jeddah","ror":"https://ror.org/015ya8798","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210099699"]}],"countries":["SA","US"],"is_corresponding":false,"raw_author_name":"Khalid T. Mursi","raw_affiliation_strings":["Department of Computer Science, Texas Tech University, Lubbock, TX College of Computer Science and Engineering University of Jeddah, Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas Tech University, Lubbock, TX College of Computer Science and Engineering University of Jeddah, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I12315562","https://openalex.org/I4210099699"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028690312","display_name":"Yu Zhuang","orcid":"https://orcid.org/0000-0003-2717-1777"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhuang","raw_affiliation_strings":["Department of Computer Science, Texas Tech University, Lubbock, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas Tech University, Lubbock, TX","institution_ids":["https://openalex.org/I12315562"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T10057","display_name":"Face and Expression Recognition","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8529820442199707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421146631240845},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6095706820487976},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.589486300945282},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5348623394966125},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5269470810890198},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5082749724388123},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4820183515548706},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.47903457283973694},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.473578542470932},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4629690647125244},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.46192994713783264},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.43989303708076477},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43175312876701355},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4194015562534332},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41937878727912903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4168907701969147},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1694888174533844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16852539777755737},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06819978356361389}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8529820442199707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421146631240845},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6095706820487976},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.589486300945282},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5348623394966125},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5269470810890198},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5082749724388123},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4820183515548706},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.47903457283973694},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.473578542470932},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4629690647125244},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.46192994713783264},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.43989303708076477},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43175312876701355},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4194015562534332},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41937878727912903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4168907701969147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1694888174533844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16852539777755737},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06819978356361389},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3388142.3388164","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3388142.3388164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th International Conference on Compute and Data Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W106922658","https://openalex.org/W110264556","https://openalex.org/W156555589","https://openalex.org/W1508853606","https://openalex.org/W1623080549","https://openalex.org/W1978176329","https://openalex.org/W2031302834","https://openalex.org/W2041565863","https://openalex.org/W2044506145","https://openalex.org/W2047191928","https://openalex.org/W2071949631","https://openalex.org/W2088879945","https://openalex.org/W2118475084","https://openalex.org/W2125779688","https://openalex.org/W2132377940","https://openalex.org/W2137446479","https://openalex.org/W2148212498","https://openalex.org/W2153233077","https://openalex.org/W2164825364","https://openalex.org/W2166647826","https://openalex.org/W2587094051","https://openalex.org/W3000483445","https://openalex.org/W4248515679","https://openalex.org/W4297792979","https://openalex.org/W4400728041"],"related_works":["https://openalex.org/W2491448268","https://openalex.org/W2559422900","https://openalex.org/W2892323093","https://openalex.org/W3144143113","https://openalex.org/W2394193399","https://openalex.org/W2181939267","https://openalex.org/W2390610678","https://openalex.org/W3071522575","https://openalex.org/W2363054820","https://openalex.org/W2160785859"],"abstract_inverted_index":{"For":[0],"a":[1,34,76,96,106,133,156],"large":[2,157],"volume":[3],"of":[4,10,23,67,89,146,153,159,181,192,200,212],"data,":[5],"the":[6,20,48,54,63,68,90,115,121,144,151,179,187,205,210,214],"clustering":[7,58,69,92,154],"algorithm":[8,70],"is":[9,26,33,44,53,79,86],"significant":[11],"importance":[12],"to":[13,45,83,101,119,141],"categorize":[14],"and":[15,65,132,173],"analyze":[16],"data.":[17,162],"Accordingly,":[18],"choosing":[19,182],"optimal":[21,188],"number":[22,145],"clusters":[24,147],"(K)":[25],"an":[27],"essential":[28],"factor,":[29],"but":[30],"it":[31,43],"also":[32],"tricky":[35],"problem":[36],"in":[37,57],"big":[38],"data":[39,171],"analysis.":[40],"More":[41],"importantly,":[42],"efficiently":[46,142],"determine":[47,143],"best":[49],"K":[50,73,99,189],"automatically,":[51],"which":[52,94,113,137],"main":[55],"issue":[56],"algorithms.":[59],"Indeed,":[60],"considering":[61],"both":[62],"quality":[64,152],"efficiency":[66,197],"during":[71],"defining":[72],"can":[74],"be":[75,102],"trade-off":[77],"that":[78,98,175],"our":[80,166,176],"primary":[81],"purpose":[82],"overcome.":[84],"K-Means":[85,111,122,131,215],"still":[87],"one":[88],"popular":[91],"algorithms,":[93],"has":[95,178],"shortcoming":[97],"needs":[100],"pre-set.":[103],"We":[104,163],"introduce":[105],"new":[107],"process":[108],"with":[109,204,209],"fewer":[110],"running,":[112],"selects":[114],"most":[116],"promising":[117],"time":[118],"run":[120],"algorithm.":[123,216],"To":[124],"achieve":[125],"this":[126],"goal,":[127],"we":[128],"applied":[129],"Bisecting":[130],"different":[134,170,183],"splitting":[135],"measure,":[136],"all":[138],"are":[139],"contributed":[140],"automatically":[148],"while":[149],"maintaining":[150],"for":[155,185],"set":[158],"high":[160],"dimensional":[161],"carried":[164],"out":[165],"experimental":[167],"studies":[168],"on":[169],"sets":[172],"found":[174],"procedure":[177],"flexibility":[180],"criteria":[184],"determining":[186],"under":[190],"each":[191],"them.":[193],"Experiments":[194],"indicate":[195],"higher":[196],"through":[198],"decreasing":[199],"computation":[201],"cost":[202],"compared":[203],"Ray&Turi":[206],"method":[207],"or":[208],"use":[211],"only":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}