{"id":"https://openalex.org/W2772904413","doi":"https://doi.org/10.1109/tnnls.2017.2770167","title":"An Algorithm for Clustering Categorical Data With Set-Valued Features","display_name":"An Algorithm for Clustering Categorical Data With Set-Valued Features","publication_year":2017,"publication_date":"2017-11-30","ids":{"openalex":"https://openalex.org/W2772904413","doi":"https://doi.org/10.1109/tnnls.2017.2770167","mag":"2772904413","pmid":"https://pubmed.ncbi.nlm.nih.gov/29990068"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2017.2770167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2017.2770167","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","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/A5013223614","display_name":"Fuyuan Cao","orcid":"https://orcid.org/0000-0003-1111-8461"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fuyuan Cao","raw_affiliation_strings":["Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0003-1111-8461","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003347359","display_name":"Joshua Zhexue Huang","orcid":"https://orcid.org/0000-0002-6797-2571"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Joshua Zhexue Huang","raw_affiliation_strings":["College of Computer Sciences and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Sciences and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiye Liang","orcid":"https://orcid.org/0000-0002-0380-2995"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiye Liang","raw_affiliation_strings":["Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-0380-2995","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063488232","display_name":"Xingwang Zhao","orcid":"https://orcid.org/0000-0002-1716-6870"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwang Zhao","raw_affiliation_strings":["Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-1716-6870","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112611699","display_name":"Yinfeng Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinfeng Meng","raw_affiliation_strings":["Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041053733","display_name":"Kai Feng","orcid":"https://orcid.org/0000-0001-8356-3009"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Feng","raw_affiliation_strings":["Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003563112","display_name":"Yuhua Qian","orcid":"https://orcid.org/0000-0001-6772-4247"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhua Qian","raw_affiliation_strings":["Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5013223614"],"corresponding_institution_ids":["https://openalex.org/I181877577"],"apc_list":null,"apc_paid":null,"fwci":3.7464,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94718497,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"29","issue":"10","first_page":"4593","last_page":"4606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9919999837875366,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7731295824050903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6754029989242554},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.652324914932251},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5989588499069214},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.542656421661377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4877236783504486},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4859691858291626},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.47685539722442627},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.47597163915634155},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.46950364112854004},{"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":0.4500017762184143},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4427059292793274},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4237223267555237},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4080970883369446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39235296845436096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3407677114009857},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17568430304527283}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7731295824050903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754029989242554},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.652324914932251},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5989588499069214},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.542656421661377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4877236783504486},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4859691858291626},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.47685539722442627},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.47597163915634155},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.46950364112854004},{"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":0.4500017762184143},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4427059292793274},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4237223267555237},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4080970883369446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39235296845436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3407677114009857},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17568430304527283},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2017.2770167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2017.2770167","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:29990068","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29990068","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2463094713","display_name":null,"funder_award_id":"61773247","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3332554125","display_name":null,"funder_award_id":"U1435212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3630857056","display_name":null,"funder_award_id":"61603230","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5485717919","display_name":null,"funder_award_id":"61473194","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5783169264","display_name":null,"funder_award_id":"61432011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G607502476","display_name":null,"funder_award_id":"2016-003","funder_id":"https://openalex.org/F4320321884","funder_display_name":"Shanxi Scholarship Council of China"},{"id":"https://openalex.org/G6417428991","display_name":null,"funder_award_id":"61573229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8265998118","display_name":null,"funder_award_id":"2015011048","funder_id":"https://openalex.org/F4320322666","funder_display_name":"Natural Science Foundation of Shanxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321884","display_name":"Shanxi Scholarship Council of China","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320322509","display_name":"Kungliga Tekniska H\u00f6gskolan","ror":"https://ror.org/026vcq606"},{"id":"https://openalex.org/F4320322551","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28"},{"id":"https://openalex.org/F4320322666","display_name":"Natural Science Foundation of Shanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W253433213","https://openalex.org/W602985745","https://openalex.org/W886192815","https://openalex.org/W1542493855","https://openalex.org/W1971605645","https://openalex.org/W1985032507","https://openalex.org/W2007635740","https://openalex.org/W2026360870","https://openalex.org/W2034445978","https://openalex.org/W2052760675","https://openalex.org/W2057712948","https://openalex.org/W2066435331","https://openalex.org/W2074359677","https://openalex.org/W2086320398","https://openalex.org/W2099581008","https://openalex.org/W2110119381","https://openalex.org/W2120887445","https://openalex.org/W2127218421","https://openalex.org/W2127971792","https://openalex.org/W2130880600","https://openalex.org/W2140190241","https://openalex.org/W2146800788","https://openalex.org/W2149230623","https://openalex.org/W2171832470","https://openalex.org/W2272985318","https://openalex.org/W2338257905","https://openalex.org/W2473552888","https://openalex.org/W3120740533","https://openalex.org/W4285719527","https://openalex.org/W6678914141"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W2892323093","https://openalex.org/W2394193399","https://openalex.org/W3174322327","https://openalex.org/W2738096727","https://openalex.org/W4240938748","https://openalex.org/W2036298232","https://openalex.org/W2363054820","https://openalex.org/W2163563073","https://openalex.org/W1987613674"],"abstract_inverted_index":{"In":[0,72,89],"data":[1,63,68,85,155,158,179],"mining,":[2],"objects":[3,99],"are":[4,54,147,150],"often":[5,55],"represented":[6],"by":[7],"a":[8,34,92,104,115],"set":[9],"of":[10,15,108,141],"features,":[11,102],"where":[12],"each":[13],"feature":[14],"an":[16,77,128],"object":[17],"has":[18],"only":[19],"one":[20],"value.":[21],"However,":[22],"in":[23,122],"reality,":[24],"some":[25],"features":[26,45,52,59],"can":[27,46],"take":[28],"on":[29,152],"multiple":[30],"values,":[31],"for":[32],"instance,":[33],"person":[35],"with":[36,57,69,86,100],"several":[37],"job":[38],"titles,":[39],"hobbies,":[40],"and":[41,53,103,127,139,156,187],"email":[42],"addresses.":[43],"These":[44],"be":[47],"referred":[48],"to":[49,66,118,131,193],"as":[50],"set-valued":[51,70,87,101,105],"treated":[56],"dummy":[58],"when":[60,176],"using":[61],"existing":[62],"mining":[64],"algorithms":[65,186],"analyze":[67],"features.":[71,88],"this":[73,90],"paper,":[74],"we":[75],"propose":[76],"SV-":[78,143,170],"$k$":[79,144,171],"-modes":[80,145,172],"algorithm":[81,130,146,173,190],"that":[82,168,188],"clusters":[83],"categorical":[84,184],"algorithm,":[91],"distance":[93],"function":[94],"is":[95,111,191],"defined":[96],"between":[97],"two":[98],"mode":[106],"representation":[107],"cluster":[109,120,135],"centers":[110,121],"proposed.":[112],"We":[113],"develop":[114],"heuristic":[116],"method":[117],"update":[119],"the":[123,133,142,169,189],"iterative":[124],"clustering":[125,177,185],"process":[126],"initialization":[129],"select":[132],"initial":[134],"centers.":[136],"The":[137,163],"convergence":[138],"complexity":[140],"analyzed.":[148],"Experiments":[149],"conducted":[151],"both":[153],"synthetic":[154],"real":[157,178],"from":[159],"five":[160],"different":[161],"applications.":[162],"experimental":[164],"results":[165],"have":[166],"shown":[167],"performs":[174],"better":[175],"than":[180],"do":[181],"three":[182],"other":[183],"scalable":[192],"large":[194],"data.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":3}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}