{"id":"https://openalex.org/W2123297508","doi":"https://doi.org/10.1109/tkde.2003.1198387","title":"Clustering data streams: theory and practice","display_name":"Clustering data streams: theory and practice","publication_year":2003,"publication_date":"2003-05-01","ids":{"openalex":"https://openalex.org/W2123297508","doi":"https://doi.org/10.1109/tkde.2003.1198387","mag":"2123297508"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2003.1198387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2003.1198387","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","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/A5017534381","display_name":"Suvajyoti Guha","orcid":"https://orcid.org/0000-0002-7622-2721"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Guha","raw_affiliation_strings":["Department of Computer Science, University of Pennsylvania, Philadelphia, PA, USA","Dept. of Comput. Sci., Pennsylvania Univ., Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Pennsylvania Univ., Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113788789","display_name":"Adam Meyerson","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Meyerson","raw_affiliation_strings":["Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","Dept. of Comput. Sci., Carnegie-Mellon Univ., Pittsburgh, PA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Carnegie-Mellon Univ., Pittsburgh, PA, USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018532292","display_name":"Nita Mishra","orcid":"https://orcid.org/0000-0002-3343-1056"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Mishra","raw_affiliation_strings":["Hewlett Packard Laboratories, Palo Alto, CA, USA","Hewlett\u2013Packard Laboratories, Palo Alto, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett\u2013Packard Laboratories, Palo Alto, CA, USA#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112923360","display_name":"R. Motwani","orcid":null},"institutions":[{"id":"https://openalex.org/I3132238960","display_name":"Institute of Electrical and Electronics Engineers","ror":"https://ror.org/01n002310","country_code":"US","type":"education","lineage":["https://openalex.org/I3132238960"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Motwani","raw_affiliation_strings":["Department of Computer Science, University of Stanford, Stanford, CA, USA","IEEE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Stanford, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"IEEE#TAB#","institution_ids":["https://openalex.org/I3132238960"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007530385","display_name":"Liadan O'Callaghan","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. O'Callaghan","raw_affiliation_strings":["Department of Computer Science, University of Stanford, Stanford, CA, USA","[Department of Computer Science, University of Stanford, Stanford, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Stanford, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Computer Science, University of Stanford, Stanford, CA, USA]","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.0576,"has_fulltext":false,"cited_by_count":900,"citation_normalized_percentile":{"value":0.99647753,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"15","issue":"3","first_page":"515","last_page":"528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9986000061035156,"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":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8830395936965942},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.8228565454483032},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6874451637268066},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5703790187835693},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.5612711906433105},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.5246115922927856},{"id":"https://openalex.org/keywords/streams","display_name":"STREAMS","score":0.45853739976882935},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41739511489868164},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.15484619140625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1393638551235199},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.13692262768745422},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0763305127620697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8830395936965942},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.8228565454483032},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6874451637268066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5703790187835693},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5612711906433105},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.5246115922927856},{"id":"https://openalex.org/C42090638","wikidata":"https://www.wikidata.org/wiki/Q4048907","display_name":"STREAMS","level":2,"score":0.45853739976882935},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41739511489868164},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.15484619140625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1393638551235199},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.13692262768745422},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0763305127620697},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2003.1198387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2003.1198387","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.9085","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.9085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.virginia.edu/papers/Clustering_Data_Streams.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.841","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-db.stanford.edu/~loc/tkdepaper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":109,"referenced_works":["https://openalex.org/W147860157","https://openalex.org/W181296567","https://openalex.org/W1488532897","https://openalex.org/W1493454437","https://openalex.org/W1529320607","https://openalex.org/W1556911662","https://openalex.org/W1566114229","https://openalex.org/W1575476631","https://openalex.org/W1601227146","https://openalex.org/W1601435884","https://openalex.org/W1633659671","https://openalex.org/W1660133578","https://openalex.org/W1673310716","https://openalex.org/W1761167196","https://openalex.org/W1766932551","https://openalex.org/W1854155592","https://openalex.org/W1891203375","https://openalex.org/W1921984393","https://openalex.org/W1943182387","https://openalex.org/W1949687736","https://openalex.org/W1952127226","https://openalex.org/W1971784203","https://openalex.org/W1977496278","https://openalex.org/W1977541023","https://openalex.org/W1979750072","https://openalex.org/W1983266860","https://openalex.org/W1984953641","https://openalex.org/W1991407520","https://openalex.org/W1994698869","https://openalex.org/W1995433152","https://openalex.org/W1996510517","https://openalex.org/W2001907516","https://openalex.org/W2004110412","https://openalex.org/W2004154913","https://openalex.org/W2005983304","https://openalex.org/W2006514056","https://openalex.org/W2006685053","https://openalex.org/W2010410498","https://openalex.org/W2012365979","https://openalex.org/W2023770210","https://openalex.org/W2025051251","https://openalex.org/W2028154682","https://openalex.org/W2028660080","https://openalex.org/W2029432209","https://openalex.org/W2039100193","https://openalex.org/W2043553302","https://openalex.org/W2045851525","https://openalex.org/W2047424291","https://openalex.org/W2050516752","https://openalex.org/W2053075747","https://openalex.org/W2058295780","https://openalex.org/W2058991275","https://openalex.org/W2064379477","https://openalex.org/W2065060195","https://openalex.org/W2073583237","https://openalex.org/W2076746184","https://openalex.org/W2080068757","https://openalex.org/W2082553115","https://openalex.org/W2085751730","https://openalex.org/W2086486316","https://openalex.org/W2095897464","https://openalex.org/W2100369465","https://openalex.org/W2101622070","https://openalex.org/W2102815056","https://openalex.org/W2103020243","https://openalex.org/W2112452856","https://openalex.org/W2114944618","https://openalex.org/W2122381782","https://openalex.org/W2122929038","https://openalex.org/W2126626732","https://openalex.org/W2128869116","https://openalex.org/W2130891992","https://openalex.org/W2131518207","https://openalex.org/W2131687179","https://openalex.org/W2133311553","https://openalex.org/W2140115873","https://openalex.org/W2140190241","https://openalex.org/W2151242668","https://openalex.org/W2156943642","https://openalex.org/W2157424698","https://openalex.org/W2160642098","https://openalex.org/W2319660501","https://openalex.org/W2606195968","https://openalex.org/W2611804663","https://openalex.org/W2809211406","https://openalex.org/W2978337448","https://openalex.org/W2999729612","https://openalex.org/W3148765228","https://openalex.org/W4230573295","https://openalex.org/W4234318375","https://openalex.org/W4234409091","https://openalex.org/W4243637616","https://openalex.org/W4243828308","https://openalex.org/W4247105055","https://openalex.org/W4255348059","https://openalex.org/W4256417298","https://openalex.org/W6606145560","https://openalex.org/W6629175646","https://openalex.org/W6631561827","https://openalex.org/W6633857196","https://openalex.org/W6634394891","https://openalex.org/W6636065709","https://openalex.org/W6636873521","https://openalex.org/W6637052001","https://openalex.org/W6637685275","https://openalex.org/W6662778435","https://openalex.org/W6666760815","https://openalex.org/W6671428793","https://openalex.org/W6682343373"],"related_works":["https://openalex.org/W4293083682","https://openalex.org/W4311602221","https://openalex.org/W4389449520","https://openalex.org/W127192698","https://openalex.org/W4295135728","https://openalex.org/W1802840531","https://openalex.org/W2522231769","https://openalex.org/W4312214159","https://openalex.org/W2045938006","https://openalex.org/W2079625735"],"abstract_inverted_index":{"The":[0],"data":[1,33,60,75],"stream":[2],"model":[3],"has":[4],"recently":[5],"attracted":[6],"attention":[7],"for":[8],"its":[9],"applicability":[10],"to":[11,30],"numerous":[12],"types":[13],"of":[14,25,42,67],"data,":[15,27],"including":[16],"telephone":[17],"records,":[18],"Web":[19],"documents,":[20],"and":[21,73],"clickstreams.":[22],"For":[23],"analysis":[24],"such":[26,52],"the":[28,32,68],"ability":[29],"process":[31],"in":[34],"a":[35,39,53],"single":[36],"pass,":[37],"or":[38],"small":[40],"number":[41],"passes,":[43],"while":[44],"using":[45],"little":[46],"memory,":[47],"is":[48],"crucial.":[49],"We":[50,62],"describe":[51],"streaming":[54],"algorithm":[55],"that":[56],"effectively":[57],"clusters":[58],"large":[59],"streams.":[61,76],"also":[63],"provide":[64],"empirical":[65],"evidence":[66],"algorithm's":[69],"performance":[70],"on":[71],"synthetic":[72],"real":[74]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":57},{"year":2017,"cited_by_count":60},{"year":2016,"cited_by_count":49},{"year":2015,"cited_by_count":58},{"year":2014,"cited_by_count":68},{"year":2013,"cited_by_count":75},{"year":2012,"cited_by_count":60}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}