{"id":"https://openalex.org/W2735941455","doi":"https://doi.org/10.1007/s10844-017-0472-5","title":"One-pass MapReduce-based clustering method for mixed large scale data","display_name":"One-pass MapReduce-based clustering method for mixed large scale data","publication_year":2017,"publication_date":"2017-07-15","ids":{"openalex":"https://openalex.org/W2735941455","doi":"https://doi.org/10.1007/s10844-017-0472-5","mag":"2735941455"},"language":"en","primary_location":{"id":"doi:10.1007/s10844-017-0472-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-017-0472-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10844-017-0472-5.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"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 Intelligent Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs10844-017-0472-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035735137","display_name":"Mohamed Aymen Ben HajKacem","orcid":"https://orcid.org/0000-0002-0161-6646"},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210140729","display_name":"Institut Sup\u00e9rieur de Gestion de Tunis","ror":"https://ror.org/04w9mdw91","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Mohamed Aymen Ben HajKacem","raw_affiliation_strings":["Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, 41 Avenue de la libert\u00e9, cit\u00e9 Bouchoucha, 2000, Le Bardo, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, 41 Avenue de la libert\u00e9, cit\u00e9 Bouchoucha, 2000, Le Bardo, Tunisia","institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006094657","display_name":"Chiheb-Eddine Ben N\u2019Cir","orcid":"https://orcid.org/0000-0003-4014-8264"},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210140729","display_name":"Institut Sup\u00e9rieur de Gestion de Tunis","ror":"https://ror.org/04w9mdw91","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Chiheb-Eddine Ben N\u2019cir","raw_affiliation_strings":["Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, cit\u00e9 Bouchoucha, Tunisia","Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, 41 Avenue de la libert\u00e9, cit\u00e9 Bouchoucha, 2000, Le Bardo, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, cit\u00e9 Bouchoucha, Tunisia","institution_ids":["https://openalex.org/I4210140729"]},{"raw_affiliation_string":"Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, 41 Avenue de la libert\u00e9, cit\u00e9 Bouchoucha, 2000, Le Bardo, Tunisia","institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110248637","display_name":"Nadia Essoussi","orcid":null},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210140729","display_name":"Institut Sup\u00e9rieur de Gestion de Tunis","ror":"https://ror.org/04w9mdw91","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Nadia Essoussi","raw_affiliation_strings":["Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, cit\u00e9 Bouchoucha, Tunisia","Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, 41 Avenue de la libert\u00e9, cit\u00e9 Bouchoucha, 2000, Le Bardo, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, cit\u00e9 Bouchoucha, Tunisia","institution_ids":["https://openalex.org/I4210140729"]},{"raw_affiliation_string":"Institut Sup\u00e9rieur de Gestion de Tunis, LARODEC, Universit\u00e9 de Tunis, 41 Avenue de la libert\u00e9, cit\u00e9 Bouchoucha, 2000, Le Bardo, Tunisia","institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006094657","https://openalex.org/A5110248637"],"corresponding_institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210140729"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":1.59,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.87506818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"52","issue":"3","first_page":"619","last_page":"636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9969000220298767,"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":0.9898999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8841066360473633},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7569983005523682},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7128541469573975},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5995693802833557},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5342497229576111},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.529748797416687},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5124066472053528},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.4950386583805084},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4927709400653839},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4919533431529999},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.44481557607650757},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4372102618217468},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4366976022720337},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4298168420791626},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42158159613609314},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36257460713386536},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32924070954322815},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23068848252296448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10810807347297668},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10239863395690918},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06720438599586487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8841066360473633},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7569983005523682},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7128541469573975},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5995693802833557},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5342497229576111},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.529748797416687},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5124066472053528},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.4950386583805084},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4927709400653839},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4919533431529999},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.44481557607650757},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4372102618217468},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4366976022720337},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4298168420791626},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42158159613609314},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36257460713386536},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32924070954322815},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23068848252296448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10810807347297668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10239863395690918},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06720438599586487},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10844-017-0472-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-017-0472-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10844-017-0472-5.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"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 Intelligent Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10844-017-0472-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-017-0472-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10844-017-0472-5.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"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 Intelligent Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2735941455.pdf","grobid_xml":"https://content.openalex.org/works/W2735941455.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W61255252","https://openalex.org/W114704759","https://openalex.org/W1491405570","https://openalex.org/W1547566968","https://openalex.org/W1598064945","https://openalex.org/W1965563268","https://openalex.org/W1974209792","https://openalex.org/W1976860187","https://openalex.org/W1990643970","https://openalex.org/W1992419399","https://openalex.org/W2002368650","https://openalex.org/W2033139024","https://openalex.org/W2043819533","https://openalex.org/W2044936152","https://openalex.org/W2048367757","https://openalex.org/W2089165876","https://openalex.org/W2101109743","https://openalex.org/W2104237323","https://openalex.org/W2108399535","https://openalex.org/W2116762767","https://openalex.org/W2135964318","https://openalex.org/W2140190241","https://openalex.org/W2142335847","https://openalex.org/W2142720090","https://openalex.org/W2144743826","https://openalex.org/W2162151748","https://openalex.org/W2171832470","https://openalex.org/W2173213060","https://openalex.org/W2185136252","https://openalex.org/W2189465200","https://openalex.org/W2261525379","https://openalex.org/W2272535016","https://openalex.org/W2291179494","https://openalex.org/W2557422164","https://openalex.org/W3124773047","https://openalex.org/W4236642514","https://openalex.org/W4285719527","https://openalex.org/W6635687051","https://openalex.org/W6680704940","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W3107178186","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2773208253","https://openalex.org/W2605086803","https://openalex.org/W2745792676","https://openalex.org/W4206278474"],"abstract_inverted_index":{"Big":[0],"data":[1,53,63,103,146,187,195],"is":[2,77,166,202],"often":[3],"characterized":[4],"by":[5,177],"a":[6,10,31,115,127,169],"huge":[7],"volume":[8],"and":[9,17,26,51,108,112,144,186,193,204],"mixed":[11,35,136],"types":[12],"of":[13,47,56,88,99,160,208],"attributes":[14],"namely,":[15],"numeric":[16],"categorical.":[18],"K-prototypes":[19],"has":[20,29],"been":[21],"fitted":[22],"into":[23],"MapReduce":[24,83,94,158],"framework":[25],"hence":[27],"it":[28],"become":[30],"solution":[32],"for":[33,80,135],"clustering":[34,133,175],"large":[36,137],"scale":[37,138],"data.":[38,139],"However,":[39],"k-prototypes":[40,76,89,132,211],"requires":[41],"computing":[42],"all":[43],"distances":[44],"between":[45,183],"each":[46,97],"the":[48,52,68,85,101,152,163,174,179,199,206,209],"cluster":[49,70,184],"centers":[50,185],"points.":[54,188],"Many":[55],"these":[57,123],"distance":[58,181],"computations":[59,182],"are":[60],"redundant,":[61],"because":[62],"points":[64],"usually":[65],"stay":[66],"in":[67],"same":[69],"after":[71],"first":[72],"few":[73],"iterations.":[74],"Also,":[75],"not":[78],"suitable":[79],"running":[81],"within":[82],"framework:":[84],"iterative":[86],"nature":[87],"cannot":[90],"be":[91,106],"modeled":[92],"through":[93],"since":[95],"at":[96],"iteration":[98],"k-prototypes,":[100],"whole":[102],"set":[104],"must":[105],"read":[107],"written":[109],"to":[110,156,172],"disks":[111],"this":[113],"results":[114],"high":[116],"input/output":[117],"(I/O)":[118],"operations.":[119],"To":[120],"deal":[121],"with":[122],"issues,":[124],"we":[125],"propose":[126],"new":[128],"one-pass":[129],"accelerated":[130],"MapReduce-based":[131],"method":[134,142,165,201],"The":[140],"proposed":[141,164,200],"reads":[143],"writes":[145],"only":[147],"once":[148],"which":[149],"reduces":[150],"largely":[151],"I/O":[153],"operations":[154],"compared":[155],"existing":[157,210],"implementation":[159],"k-prototypes.":[161],"Furthermore,":[162],"based":[167],"on":[168,191],"pruning":[170],"strategy":[171],"accelerate":[173],"process":[176],"reducing":[178],"redundant":[180],"Experiments":[189],"performed":[190],"simulated":[192],"real":[194],"sets":[196],"show":[197],"that":[198],"scalable":[203],"improves":[205],"efficiency":[207],"methods.":[212]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}