{"id":"https://openalex.org/W4206780559","doi":"https://doi.org/10.1109/bigdata52589.2021.9671362","title":"MapReduce Clustering for Big Data","display_name":"MapReduce Clustering for Big Data","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4206780559","doi":"https://doi.org/10.1109/bigdata52589.2021.9671362"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671362","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-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/A5060957707","display_name":"Badih Ghattas","orcid":"https://orcid.org/0000-0002-6160-9341"},"institutions":[{"id":"https://openalex.org/I4210138206","display_name":"Institut de Math\u00e9matiques de Marseille","ror":"https://ror.org/042h2y225","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210138206","https://openalex.org/I4210141950","https://openalex.org/I4210142724"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Badih Ghattas","raw_affiliation_strings":["Aix Marseille Universit\u00e9 - CNRS Institut de Math\u00e9matiques de Marseille, Marseille, France"],"affiliations":[{"raw_affiliation_string":"Aix Marseille Universit\u00e9 - CNRS Institut de Math\u00e9matiques de Marseille, Marseille, France","institution_ids":["https://openalex.org/I4210138206","https://openalex.org/I21491767","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051090026","display_name":"Antoine Pinto","orcid":null},"institutions":[{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210138206","display_name":"Institut de Math\u00e9matiques de Marseille","ror":"https://ror.org/042h2y225","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210138206","https://openalex.org/I4210141950","https://openalex.org/I4210142724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Pinto","raw_affiliation_strings":["Aix Marseille Universit\u00e9 Institut de Math\u00e9matiques de Marseille Aix Marseille School of Economics, Marseille, France"],"affiliations":[{"raw_affiliation_string":"Aix Marseille Universit\u00e9 Institut de Math\u00e9matiques de Marseille Aix Marseille School of Economics, Marseille, France","institution_ids":["https://openalex.org/I4210138206","https://openalex.org/I21491767"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090063330","display_name":"Sambou Diao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087487","display_name":"Assistance Publique H\u00f4pitaux de Marseille","ror":"https://ror.org/002cp4060","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210087487"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sambou Diao","raw_affiliation_strings":["Assistance Publique des H\u00f4pitaux de Marseille Service d\u2019information m\u00e9dicale, Marseille, France","Assistance Publique des H\u00f4pitaux de Marseille Service d'information m\u00e9dicale, Marseille, France"],"affiliations":[{"raw_affiliation_string":"Assistance Publique des H\u00f4pitaux de Marseille Service d\u2019information m\u00e9dicale, Marseille, France","institution_ids":["https://openalex.org/I4210087487"]},{"raw_affiliation_string":"Assistance Publique des H\u00f4pitaux de Marseille Service d'information m\u00e9dicale, Marseille, France","institution_ids":["https://openalex.org/I4210087487"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060957707"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210138206"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20794457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"344","issue":null,"first_page":"5116","last_page":"5124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8825213313102722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8205239772796631},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6767492294311523},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.59294193983078},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.574863076210022},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5654967427253723},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5113213062286377},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4969964325428009},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4665363132953644},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4524593949317932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24341437220573425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09387549757957458},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05041980743408203}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8825213313102722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205239772796631},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6767492294311523},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.59294193983078},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.574863076210022},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5654967427253723},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5113213062286377},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4969964325428009},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4665363132953644},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4524593949317932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24341437220573425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09387549757957458},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05041980743408203},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671362","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03581393v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03581393","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data), Dec 2021, Orlando, France. pp.5116-5124, ⟨10.1109/BigData52589.2021.9671362⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2002368650","https://openalex.org/W2061025330","https://openalex.org/W2061051181","https://openalex.org/W2064883676","https://openalex.org/W2069903846","https://openalex.org/W2073459066","https://openalex.org/W2108399535","https://openalex.org/W2116762767","https://openalex.org/W2126626732","https://openalex.org/W2128422078","https://openalex.org/W2519132385","https://openalex.org/W2582743722","https://openalex.org/W2585986260","https://openalex.org/W2795859997","https://openalex.org/W2860903707","https://openalex.org/W2965768238","https://openalex.org/W3103508235"],"related_works":["https://openalex.org/W2491448268","https://openalex.org/W2559422900","https://openalex.org/W2892323093","https://openalex.org/W3144143113","https://openalex.org/W2394193399","https://openalex.org/W2181939267","https://openalex.org/W2390610678","https://openalex.org/W3071522575","https://openalex.org/W2363054820","https://openalex.org/W2160785859"],"abstract_inverted_index":{"We":[0,40,55],"introduce":[1],"a":[2,20,43,48],"new":[3],"clustering":[4,26,34,50],"procedure":[5,22],"specialized":[6],"for":[7,23],"Big":[8],"Data.":[9],"It":[10],"is":[11],"inspired":[12],"by":[13,68],"the":[14,29],"work":[15],"of":[16],"[1],":[17],"and":[18,36,64],"applies":[19],"MapReduce":[21],"any":[24],"base":[25,49],"algorithm,":[27],"split-ting":[28],"data":[30],"set":[31],"at":[32],"hand,":[33],"subsamples,":[35],"combining":[37],"intermediate":[38],"results.":[39],"use":[41],"thus":[42],"high":[44],"level":[45],"parallelization":[46],"running":[47],"approach":[51,60],"on":[52],"small":[53],"samples.":[54],"analyse":[56],"in":[57],"detail":[58],"our":[59],"exploring":[61],"various":[62],"alternatives":[63],"showing":[65],"its":[66],"efficiency":[67],"simulations.":[69]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}