{"id":"https://openalex.org/W2518417797","doi":"https://doi.org/10.1109/tfuzz.2016.2604009","title":"Large Scale Document Categorization With Fuzzy Clustering","display_name":"Large Scale Document Categorization With Fuzzy Clustering","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2518417797","doi":"https://doi.org/10.1109/tfuzz.2016.2604009","mag":"2518417797"},"language":"en","primary_location":{"id":"doi:10.1109/tfuzz.2016.2604009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tfuzz.2016.2604009","pdf_url":null,"source":{"id":"https://openalex.org/S134177497","display_name":"IEEE Transactions on Fuzzy Systems","issn_l":"1063-6706","issn":["1063-6706","1941-0034"],"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 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/A5046093778","display_name":"Jian-Ping Mei","orcid":"https://orcid.org/0000-0003-1678-6215"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian-Ping Mei","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012931252","display_name":"Yangtao Wang","orcid":"https://orcid.org/0000-0003-4605-9270"},"institutions":[{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yangtao Wang","raw_affiliation_strings":["Data Analytics Department, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Data Analytics Department, A*STAR, Singapore","institution_ids":["https://openalex.org/I4210161496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718988","display_name":"Lihui Chen","orcid":"https://orcid.org/0000-0001-7452-1675"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lihui Chen","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100382077","display_name":"Chunyan Miao","orcid":"https://orcid.org/0000-0002-0300-3448"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chunyan Miao","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046093778"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":7.7125,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.97370412,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":"5","first_page":"1239","last_page":"1251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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":0.995199978351593,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7695368528366089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.736199140548706},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7173490524291992},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.6722491383552551},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5557883977890015},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5239967107772827},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.506316065788269},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5022954940795898},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4849110245704651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45199280977249146},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4479790925979614},{"id":"https://openalex.org/keywords/fuzzy-set","display_name":"Fuzzy set","score":0.42802348732948303},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3799740672111511},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14907434582710266}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7695368528366089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736199140548706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7173490524291992},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.6722491383552551},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5557883977890015},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5239967107772827},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.506316065788269},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5022954940795898},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4849110245704651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45199280977249146},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4479790925979614},{"id":"https://openalex.org/C42011625","wikidata":"https://www.wikidata.org/wiki/Q1055058","display_name":"Fuzzy set","level":3,"score":0.42802348732948303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3799740672111511},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14907434582710266}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tfuzz.2016.2604009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tfuzz.2016.2604009","pdf_url":null,"source":{"id":"https://openalex.org/S134177497","display_name":"IEEE Transactions on Fuzzy Systems","issn_l":"1063-6706","issn":["1063-6706","1941-0034"],"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 Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7249556737","display_name":null,"funder_award_id":"61502420","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8481924932","display_name":null,"funder_award_id":"LY16F020032","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W130742730","https://openalex.org/W146815106","https://openalex.org/W147860157","https://openalex.org/W1493526108","https://openalex.org/W1575476631","https://openalex.org/W1578105163","https://openalex.org/W1790954942","https://openalex.org/W1949687736","https://openalex.org/W1970544520","https://openalex.org/W1978394996","https://openalex.org/W1980102202","https://openalex.org/W2006685053","https://openalex.org/W2045036792","https://openalex.org/W2058063871","https://openalex.org/W2064128636","https://openalex.org/W2070670538","https://openalex.org/W2095897464","https://openalex.org/W2098418076","https://openalex.org/W2107871283","https://openalex.org/W2108390422","https://openalex.org/W2113594706","https://openalex.org/W2116762767","https://openalex.org/W2116963327","https://openalex.org/W2118211060","https://openalex.org/W2120322324","https://openalex.org/W2121281940","https://openalex.org/W2126337883","https://openalex.org/W2127856486","https://openalex.org/W2131687179","https://openalex.org/W2133576408","https://openalex.org/W2138072998","https://openalex.org/W2149148023","https://openalex.org/W2153622543","https://openalex.org/W2162217115","https://openalex.org/W2519540664","https://openalex.org/W2999729612","https://openalex.org/W3120740533","https://openalex.org/W4235169531","https://openalex.org/W6605363618","https://openalex.org/W6606145560","https://openalex.org/W6634394891","https://openalex.org/W6640454944","https://openalex.org/W6726280873"],"related_works":["https://openalex.org/W2049508213","https://openalex.org/W4378768646","https://openalex.org/W3214871334","https://openalex.org/W2071977683","https://openalex.org/W1988922486","https://openalex.org/W2042494732","https://openalex.org/W2101715672","https://openalex.org/W2387287989","https://openalex.org/W58095113","https://openalex.org/W1595856830"],"abstract_inverted_index":{"Clustering":[0],"documents":[1],"into":[2,23,53,128,141],"coherent":[3],"categories":[4],"is":[5,37,59,104,135,145],"a":[6,26,41,63,86,142,150,182],"very":[7,64],"useful":[8],"and":[9,15,61,78,113,125,171,203,238],"important":[10],"step":[11],"for":[12,94,117,147,162,181,220],"document":[13,33,118,184,233,253],"processing":[14],"understanding.":[16],"The":[17,98,174],"introducing":[18],"of":[19,43,69,82,111,176,200],"fuzzy":[20,72,109,139,160,177,204],"set":[21],"theory":[22],"clustering":[24,73,110,140,161,185],"provides":[25],"favorable":[27],"mechanism":[28],"to":[29,51,136,217],"capture":[30],"overlapping":[31],"among":[32],"clusters.":[34],"Document":[35],"dataset":[36,58],"commonly":[38],"represented":[39],"as":[40],"collection":[42],"high-dimensional":[44,114,221],"vectors,":[45],"which":[46,144],"may":[47,84],"not":[48],"be":[49],"able":[50],"fit":[52],"memory":[54],"entirely,":[55],"when":[56],"the":[57,70,129,191,207,239,243],"large":[60,123,183,232],"with":[62,76,149,206,223,230],"high":[65,126],"dimensionality.":[66],"However,":[67],"most":[68],"existing":[71,250],"approaches":[74,180,196,216,245],"deal":[75],"small":[77],"static":[79],"datasets.":[80],"Some":[81],"them":[83],"have":[85,235],"good":[87],"scalability":[88],"but":[89],"they":[90],"are":[91,186],"only":[92],"effective":[93,146],"low":[95],"dimensional":[96],"data.":[97],"study":[99],"presented":[100],"in":[101,159,252],"this":[102],"paper":[103],"about":[105],"new":[106,195,215],"efforts":[107],"on":[108,190],"large-scale":[112,151,164],"data-especially":[115],"suitable":[116],"categorization.":[119,254],"To":[120],"consider":[121],"both":[122],"scale":[124],"dimensionality":[127],"problem":[130],"formulation,":[131],"our":[132,214],"key":[133],"idea":[134],"incorporate":[137],"document-tailored":[138],"scheme,":[143],"dealing":[148],"problem.":[152],"We":[153],"first":[154],"identified":[155],"three":[156,208],"representative":[157],"schemes":[158],"handling":[163],"data,":[165],"namely":[166],"sampling":[167],"extension,":[168],"single":[169],"pass,":[170],"divide":[172],"ensemble.":[173],"limitation":[175],"C-means":[178],"(FCM)-based":[179],"then":[187],"investigated.":[188],"Based":[189],"study,":[192],"we":[193],"propose":[194],"by":[197],"incorporating":[198],"each":[199],"hyperspherical":[201],"FCM":[202],"coclustering":[205],"scale-up":[209],"schemes,":[210],"respectively.":[211],"This":[212],"enables":[213],"maintain":[218],"effectiveness":[219],"data":[222],"an":[224],"extended":[225],"scalability.":[226],"Extensive":[227],"experimental":[228],"studies":[229],"real-world":[231],"datasets":[234],"been":[236],"conducted":[237],"results":[240],"demonstrate":[241],"that":[242],"proposed":[244],"perform":[246],"consistently":[247],"better":[248],"over":[249],"ones":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}