{"id":"https://openalex.org/W4362580199","doi":"https://doi.org/10.1186/s40537-023-00709-4","title":"An ensemble method for estimating the number of clusters in a big data set using multiple random samples","display_name":"An ensemble method for estimating the number of clusters in a big data set using multiple random samples","publication_year":2023,"publication_date":"2023-04-01","ids":{"openalex":"https://openalex.org/W4362580199","doi":"https://doi.org/10.1186/s40537-023-00709-4"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-023-00709-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00709-4","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00709-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00709-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056369956","display_name":"Mohammad Sultan Mahmud","orcid":"https://orcid.org/0000-0002-5795-787X"},"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":true,"raw_author_name":"Mohammad Sultan Mahmud","raw_affiliation_strings":["Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]}]},{"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":["Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014049285","display_name":"Rukhsana Ruby","orcid":"https://orcid.org/0000-0002-8373-9542"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rukhsana Ruby","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy, Shenzhen, 518107, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy, Shenzhen, 518107, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001188748","display_name":"Kaishun Wu","orcid":"https://orcid.org/0000-0003-2216-0737"},"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":"Kaishun Wu","raw_affiliation_strings":["Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056369956"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":2.1538,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89652317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":"1","first_page":null,"last_page":null},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9898999929428101,"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":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7328628301620483},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7236572504043579},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7233508825302124},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.617287814617157},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49542343616485596},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4827520251274109},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.47820353507995605},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.47628775238990784},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4711272418498993},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4377145767211914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27778148651123047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2049068808555603},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07603713870048523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328628301620483},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7236572504043579},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7233508825302124},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.617287814617157},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49542343616485596},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4827520251274109},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.47820353507995605},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.47628775238990784},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4711272418498993},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4377145767211914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27778148651123047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2049068808555603},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07603713870048523},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":2,"locations":[{"id":"doi:10.1186/s40537-023-00709-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00709-4","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00709-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fd86b4da6db542a487c3aef204d0855b","is_oa":true,"landing_page_url":"https://doaj.org/article/fd86b4da6db542a487c3aef204d0855b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 10, Iss 1, Pp 1-33 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-023-00709-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00709-4","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00709-4","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7924544171","display_name":null,"funder_award_id":"61972261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362580199.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1648123822","https://openalex.org/W1967168896","https://openalex.org/W1979607399","https://openalex.org/W1987971958","https://openalex.org/W1990063425","https://openalex.org/W1992929897","https://openalex.org/W1996881001","https://openalex.org/W2036816792","https://openalex.org/W2037183202","https://openalex.org/W2043028407","https://openalex.org/W2051224630","https://openalex.org/W2071949631","https://openalex.org/W2116984363","https://openalex.org/W2118211060","https://openalex.org/W2135945534","https://openalex.org/W2153293405","https://openalex.org/W2162833336","https://openalex.org/W2165835468","https://openalex.org/W2520619240","https://openalex.org/W2625743308","https://openalex.org/W2740924709","https://openalex.org/W2773612851","https://openalex.org/W2806794445","https://openalex.org/W2807006342","https://openalex.org/W2883811944","https://openalex.org/W2884562637","https://openalex.org/W2890125629","https://openalex.org/W2942755646","https://openalex.org/W2952380632","https://openalex.org/W3018761215","https://openalex.org/W3092037388","https://openalex.org/W3112798043","https://openalex.org/W4235169531"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4256429076","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W1971174658","https://openalex.org/W2960264696","https://openalex.org/W2015634066","https://openalex.org/W2048339306","https://openalex.org/W2028295504","https://openalex.org/W3046629113"],"abstract_inverted_index":{"Abstract":[0],"Clustering":[1],"a":[2,12,25,40,46,77,127,171],"big":[3,13,41,56,101,135,187],"dataset":[4],"without":[5],"knowing":[6],"the":[7,35,55,59,66,88,96,100,106,109,117,123,134,149,154,163,175,181],"number":[8,36,67,177],"of":[9,37,48,68,119,129,153,174,178],"clusters":[10,38,69,86],"presents":[11],"challenge":[14],"to":[15,33,64,83,115,147,186],"many":[16],"existing":[17],"clustering":[18],"algorithms.":[19],"In":[20,43],"this":[21,44],"paper,":[22],"we":[23],"propose":[24],"Random":[26],"Sample":[27],"Partition-based":[28],"Centers":[29],"Ensemble":[30],"(RSPCE)":[31],"algorithm":[32,61,183],"identify":[34,65],"in":[39,73,87,99,133],"dataset.":[42,102,136],"algorithm,":[45],"set":[47,128],"disjoint":[49],"random":[50,89,168],"samples":[51,90,121,169],"is":[52,62,81,113,170,184],"selected":[53],"from":[54,95,166],"dataset,":[57],"and":[58,70,144,151,180],"I-niceDP":[60],"used":[63,114],"initial":[71,130],"centers":[72,132],"each":[74],"sample.":[75],"Subsequently,":[76],"cluster":[78,98,131],"ball":[79,107],"model":[80],"proposed":[82,155],"merge":[84],"two":[85],"that":[91,162],"are":[92],"likely":[93],"sampled":[94],"same":[97],"Finally,":[103],"based":[104],"on":[105,141],"model,":[108],"RSPCE":[110,156,182],"ensemble":[111,116,164],"method":[112],"results":[118,160],"all":[120],"into":[122],"final":[124],"result":[125,165],"as":[126],"Intensive":[137],"experiments":[138],"were":[139],"conducted":[140],"both":[142],"synthetic":[143],"real":[145],"datasets":[146],"validate":[148],"feasibility":[150],"effectiveness":[152],"algorithm.":[157],"The":[158],"experimental":[159],"show":[161],"multiple":[167],"reliable":[172],"approximation":[173],"actual":[176],"clusters,":[179],"scalable":[185],"data.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}