{"id":"https://openalex.org/W2923023146","doi":"https://doi.org/10.1109/tbdata.2019.2907624","title":"Hierarchical Density-Based Clustering Using MapReduce","display_name":"Hierarchical Density-Based Clustering Using MapReduce","publication_year":2019,"publication_date":"2019-03-26","ids":{"openalex":"https://openalex.org/W2923023146","doi":"https://doi.org/10.1109/tbdata.2019.2907624","mag":"2923023146"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2019.2907624","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2019.2907624","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/9366322/08674542.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6687317/9366322/08674542.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065389941","display_name":"Joelson Ant\u00f4nio dos Santos","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Joelson Antonio dos Santos","raw_affiliation_strings":["Department of Computer Science, University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108251249","display_name":"Talat Iqbal Syed","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Talat Iqbal Syed","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081258813","display_name":"Murilo Coelho Naldi","orcid":"https://orcid.org/0000-0002-3107-8236"},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Murilo C. Naldi","raw_affiliation_strings":["Department of Computer Science, Federal University of S\u00e3o Carlos, S\u00e3o Carlos, SP, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of S\u00e3o Carlos, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014723418","display_name":"Ricardo J. G. B. Campello","orcid":"https://orcid.org/0000-0003-0266-3492"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ricardo J. G. B. Campello","raw_affiliation_strings":["School of Mathematical & Physical Sciences, University of Newcastle, Newcastle, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematical & Physical Sciences, University of Newcastle, Newcastle, NSW, Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021763337","display_name":"J\u00f6rg Sander","orcid":"https://orcid.org/0000-0003-4068-7268"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joerg Sander","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065389941"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":3.1826,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.93521608,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"102","last_page":"114"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9951000213623047,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8595590591430664},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.788663923740387},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5841594934463501},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5484276413917542},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5140846371650696},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.504700779914856},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4803570508956909},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47943586111068726},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4196251928806305},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.41310808062553406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2671123743057251},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10867589712142944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595590591430664},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.788663923740387},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5841594934463501},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5484276413917542},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5140846371650696},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.504700779914856},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4803570508956909},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47943586111068726},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4196251928806305},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.41310808062553406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2671123743057251},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10867589712142944}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tbdata.2019.2907624","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2019.2907624","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/9366322/08674542.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Big Data","raw_type":"journal-article"},{"id":"pmh:003022632","is_oa":true,"landing_page_url":"https://doi.org/10.1109/TBDATA.2019.2907624","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"reponame:Reposit\u00f3rio Institucional da USP (Biblioteca Digital da Produ\u00e7\u00e3o Intelectual)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1109/tbdata.2019.2907624","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2019.2907624","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/9366322/08674542.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1966206360","display_name":null,"funder_award_id":"304137/2013-8","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G4789789729","display_name":null,"funder_award_id":"400772/2014-0","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322980","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","ror":"https://ror.org/00nc55f03"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2923023146.pdf","grobid_xml":"https://content.openalex.org/works/W2923023146.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W1038628138","https://openalex.org/W1497734908","https://openalex.org/W1505618376","https://openalex.org/W1559971515","https://openalex.org/W1598064945","https://openalex.org/W1673310716","https://openalex.org/W1827980970","https://openalex.org/W1829970718","https://openalex.org/W1971784203","https://openalex.org/W1987111416","https://openalex.org/W1990823052","https://openalex.org/W2002368650","https://openalex.org/W2004915662","https://openalex.org/W2024766881","https://openalex.org/W2034968907","https://openalex.org/W2041055696","https://openalex.org/W2049631158","https://openalex.org/W2051586153","https://openalex.org/W2053138484","https://openalex.org/W2061051181","https://openalex.org/W2079040080","https://openalex.org/W2096984027","https://openalex.org/W2100077146","https://openalex.org/W2101344335","https://openalex.org/W2104736343","https://openalex.org/W2117544284","https://openalex.org/W2120636855","https://openalex.org/W2128364989","https://openalex.org/W2132215016","https://openalex.org/W2133035795","https://openalex.org/W2159037239","https://openalex.org/W2160642098","https://openalex.org/W2173213060","https://openalex.org/W2180566385","https://openalex.org/W2231104193","https://openalex.org/W2319660501","https://openalex.org/W2479778494","https://openalex.org/W2541380671","https://openalex.org/W2799290011","https://openalex.org/W2802863387","https://openalex.org/W2995564009","https://openalex.org/W3120740533","https://openalex.org/W4213146104","https://openalex.org/W4235169531","https://openalex.org/W4247105055","https://openalex.org/W6629949607","https://openalex.org/W6637131181","https://openalex.org/W6660692168","https://openalex.org/W6729316624","https://openalex.org/W6751068773"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W1525022337","https://openalex.org/W3146523624","https://openalex.org/W2384052049","https://openalex.org/W2390610678","https://openalex.org/W3140018618","https://openalex.org/W2171583777","https://openalex.org/W2186905933","https://openalex.org/W2407786351","https://openalex.org/W2087424554"],"abstract_inverted_index":{"Hierarchical":[0],"density-based":[1,100,138,168,205],"clustering":[2,38,104,125,139,169,186,206],"is":[3,30,54,148,198,220],"a":[4,41,55,178,190,210,233],"powerful":[5],"tool":[6],"for":[7],"exploratory":[8],"data":[9,62,211,215],"analysis,":[10],"which":[11,87,147],"can":[12,90],"play":[13],"an":[14,151,184],"important":[15],"role":[16],"in":[17,45,88,222],"the":[18,33,46,75,95,202,230],"understanding":[19],"and":[20,64,227,240],"organization":[21],"of":[22,36,48,98,224,229,235],"datasets.":[23,73],"However,":[24],"its":[25,238],"applicability":[26],"to":[27,50,59,81,94,109,122,129,136,164,170],"large":[28,171],"datasets":[29,172],"limited":[31],"because":[32],"computational":[34],"complexity":[35],"hierarchical":[37,99,103,167,204],"methods":[39],"has":[40],"quadratic":[42],"lower":[43],"bound":[44],"number":[47,234],"objects":[49],"be":[51,92,162],"clustered.":[52],"MapReduce":[53,127],"popular":[56],"programming":[57],"model":[58],"speed":[60],"up":[61],"mining":[63],"machine":[65],"learning":[66],"algorithms":[67,83,105],"operating":[68],"on":[69,150,189,200,232],"large,":[70],"possibly":[71],"distributed":[72],"In":[74,113],"literature,":[76],"there":[77],"have":[78],"been":[79],"attempts":[80],"parallelize":[82,110,123],"such":[84,145],"as":[85],"Single-Linkage,":[86],"principle":[89],"also":[91],"extended":[93],"broader":[96],"scope":[97],"clustering,":[101],"but":[102],"are":[106],"inherently":[107],"difficult":[108],"with":[111,209],"MapReduce.":[112],"this":[114],"paper,":[115],"we":[116,142,175],"discuss":[117,143],"why":[118],"adapting":[119],"previous":[120],"approaches":[121],"Single-Linkage":[124],"using":[126,173],"leads":[128],"very":[130,154],"inefficient":[131],"solutions":[132],"when":[133],"one":[134,144],"wants":[135],"compute":[137],"hierarchies.":[140],"Preliminarily,":[141],"solution,":[146],"based":[149,188,199],"exact,":[152],"yet":[153],"computationally":[155],"demanding,":[156],"random":[157],"blocks":[158],"parallelization":[159,180],"scheme.":[160],"To":[161],"able":[163],"efficiently":[165],"apply":[166],"MapReduce,":[174],"then":[176],"propose":[177],"different":[179],"scheme":[181],"that":[182],"computes":[183],"approximate":[185],"hierarchy":[187],"much":[191],"faster,":[192],"recursive":[193],"sampling":[194],"approach.":[195],"This":[196],"approach":[197],"HDBSCAN*,":[201],"state-of-the-art":[203],"algorithm,":[207],"combined":[208],"summarization":[212],"technique":[213],"called":[214],"bubbles.":[216],"The":[217],"proposed":[218],"method":[219],"evaluated":[221],"terms":[223],"both":[225],"runtime":[226],"quality":[228],"approximation":[231],"datasets,":[236],"showing":[237],"effectiveness":[239],"scalability.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}