{"id":"https://openalex.org/W4322626226","doi":"https://doi.org/10.3233/jifs-224234","title":"A parallel CF tree clustering algorithm for mixed-type datasets","display_name":"A parallel CF tree clustering algorithm for mixed-type datasets","publication_year":2023,"publication_date":"2023-02-28","ids":{"openalex":"https://openalex.org/W4322626226","doi":"https://doi.org/10.3233/jifs-224234"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-224234","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-224234","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","raw_type":"journal-article"},"type":"article","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/A5101720898","display_name":"Yufeng Li","orcid":"https://orcid.org/0009-0004-7625-2439"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yufeng Li","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100827440","display_name":"Keyi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyi Xu","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100546265","display_name":"Yumei Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumei Ding","raw_affiliation_strings":["College of Sciences, Tianjin University of Science & Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Sciences, Tianjin University of Science & Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074831903","display_name":"Zhiwei Sun","orcid":"https://orcid.org/0000-0002-9798-141X"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Sun","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016896170","display_name":"Ting Ke","orcid":"https://orcid.org/0000-0003-4504-4827"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Ke","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101720898"],"corresponding_institution_ids":["https://openalex.org/I132369690"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01675336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"5","first_page":"8309","last_page":"8320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9995999932289124,"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":0.9995999932289124,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9865999817848206,"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/computer-science","display_name":"Computer science","score":0.7930420637130737},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.7324986457824707},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.728134036064148},{"id":"https://openalex.org/keywords/reducer","display_name":"Reducer","score":0.6053696870803833},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6041179299354553},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5534194707870483},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.498150110244751},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4968247711658478},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.45990511775016785},{"id":"https://openalex.org/keywords/type","display_name":"Type (biology)","score":0.4533521234989166},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4243113398551941},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39821356534957886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17633989453315735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12005865573883057},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10447749495506287},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08927243947982788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930420637130737},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.7324986457824707},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.728134036064148},{"id":"https://openalex.org/C2776985865","wikidata":"https://www.wikidata.org/wiki/Q26820931","display_name":"Reducer","level":2,"score":0.6053696870803833},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6041179299354553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5534194707870483},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.498150110244751},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4968247711658478},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.45990511775016785},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.4533521234989166},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4243113398551941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39821356534957886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17633989453315735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12005865573883057},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10447749495506287},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08927243947982788},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-224234","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-224234","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W65738273","https://openalex.org/W2061278117","https://openalex.org/W2105268089","https://openalex.org/W2291179494","https://openalex.org/W2333673279","https://openalex.org/W2735941455","https://openalex.org/W2751422831","https://openalex.org/W2803439781","https://openalex.org/W2905437091","https://openalex.org/W2943827744","https://openalex.org/W2945954897","https://openalex.org/W2962963658","https://openalex.org/W3112198433","https://openalex.org/W3114371502","https://openalex.org/W4220886846","https://openalex.org/W4225128781","https://openalex.org/W4310494058","https://openalex.org/W4311457624","https://openalex.org/W4313066738","https://openalex.org/W6762506972"],"related_works":["https://openalex.org/W2394411596","https://openalex.org/W2599888081","https://openalex.org/W2349055795","https://openalex.org/W4226030716","https://openalex.org/W2943236215","https://openalex.org/W2737431648","https://openalex.org/W2971039361","https://openalex.org/W2725465928","https://openalex.org/W2358128745","https://openalex.org/W2356918504"],"abstract_inverted_index":{"Many":[0],"traditional":[1],"clustering":[2,26],"algorithms":[3],"are":[4,40],"incapable":[5],"of":[6,45,106],"processing":[7],"mixed-type":[8,33,131],"datasets":[9,124,133],"in":[10,15,64],"parallel,":[11],"limiting":[12],"their":[13],"applications":[14],"big":[16,132],"data.":[17],"In":[18,47],"this":[19],"paper,":[20],"we":[21],"propose":[22],"a":[23,89],"CF":[24,53,61,73],"tree":[25,54],"algorithm":[27,55],"based":[28],"on":[29,121,129],"MapReduce":[30],"to":[31,58,71,146,159],"handle":[32],"datasets.":[34,127],"Mapper":[35],"phase":[36,39],"and":[37,63,84,103,119,125,142,148,155],"reducer":[38,66],"the":[41,48,51,65,77,98],"two":[42,130],"primary":[43],"phases":[44],"MR-CF.":[46,107],"mapper":[49],"phase,":[50,67],"original":[52],"is":[56,69],"modified":[57],"collect":[59],"intermediate":[60],"entries,":[62],"k-prototypes":[68],"extended":[70],"cluster":[72],"entries.":[74],"To":[75],"avoid":[76],"high":[78],"costs":[79],"associated":[80],"with":[81,112],"I/O":[82,104],"overheads":[83],"data":[85],"serialization,":[86],"MR-CF":[87,136],"loads":[88],"dataset":[90],"from":[91],"HDFS":[92],"only":[93],"once.":[94],"We":[95,108],"first":[96],"analyze":[97],"time":[99,139,152],"complexity,":[100,102],"space":[101],"complexity":[105],"also":[109],"compare":[110],"it":[111,149],"sklearn":[113],"BIRCH,":[114],"Apache":[115],"Mahout":[116],"k-means,":[117],"k-prototypes,":[118,147],"mrk-prototypes":[120],"several":[122],"real-world":[123],"synthetic":[126],"Experiments":[128],"reveal":[134],"that":[135],"reduces":[137,150],"execution":[138,151],"by":[140,153],"45.4%":[141],"61.3%":[143],"when":[144,157],"compared":[145,158],"73.8%":[154],"55.0%":[156],"mrk-prototypes.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
