{"id":"https://openalex.org/W3081072117","doi":"https://doi.org/10.1109/tkde.2020.3018744","title":"Fast Streaming k-Means Clustering with Coreset Caching","display_name":"Fast Streaming k-Means Clustering with Coreset Caching","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3081072117","doi":"https://doi.org/10.1109/tkde.2020.3018744","mag":"3081072117"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.3018744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.3018744","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":true,"oa_status":"green","oa_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=1261&context=ece_pubs","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085953574","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0001-7959-3213"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054849628","display_name":"Kanat Tangwongsan","orcid":"https://orcid.org/0000-0001-9775-8165"},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kanat Tangwongsan","raw_affiliation_strings":["Compute Science Program, Mahidol University International College, Nakhon Pathom, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Compute Science Program, Mahidol University International College, Nakhon Pathom, Thailand","institution_ids":["https://openalex.org/I25399158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047034711","display_name":"Srikanta Tirthapura","orcid":"https://orcid.org/0000-0001-5321-924X"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikanta Tirthapura","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6771,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76873775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991000294685364,"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":0.9991000294685364,"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/T11478","display_name":"Caching and Content Delivery","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9957000017166138,"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":0.8101570010185242},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7986094951629639},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7357912659645081},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.5222293138504028},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.4824000597000122},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.44458386301994324},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4271260201931},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.4197229743003845},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4049619138240814},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37882617115974426},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3534146845340729},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.30587488412857056},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.30060943961143494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13595795631408691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1346927285194397},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.1311817169189453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101570010185242},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7986094951629639},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7357912659645081},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.5222293138504028},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.4824000597000122},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.44458386301994324},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4271260201931},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.4197229743003845},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4049619138240814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37882617115974426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3534146845340729},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.30587488412857056},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.30060943961143494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13595795631408691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1346927285194397},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.1311817169189453},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2020.3018744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.3018744","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:lib.dr.iastate.edu:ece_pubs-1261","is_oa":true,"landing_page_url":"https://lib.dr.iastate.edu/ece_pubs/257","pdf_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=1261&context=ece_pubs","source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:lib.dr.iastate.edu:ece_pubs-1261","is_oa":true,"landing_page_url":"https://lib.dr.iastate.edu/ece_pubs/257","pdf_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=1261&context=ece_pubs","source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Publications","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081072117.pdf","grobid_xml":"https://content.openalex.org/works/W3081072117.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1968301997","https://openalex.org/W1978906111","https://openalex.org/W1981773323","https://openalex.org/W2018165284","https://openalex.org/W2045964207","https://openalex.org/W2048442462","https://openalex.org/W2095897464","https://openalex.org/W2116318219","https://openalex.org/W2123297508","https://openalex.org/W2123513914","https://openalex.org/W2150593711","https://openalex.org/W2170936641","https://openalex.org/W2238750598","https://openalex.org/W2307392679","https://openalex.org/W2949910245","https://openalex.org/W3120740533","https://openalex.org/W4236385439","https://openalex.org/W6614148910","https://openalex.org/W6668990524","https://openalex.org/W6677939283","https://openalex.org/W6678914141","https://openalex.org/W6683136438"],"related_works":["https://openalex.org/W2892323093","https://openalex.org/W2559422900","https://openalex.org/W2491448268","https://openalex.org/W3144143113","https://openalex.org/W2394193399","https://openalex.org/W2181939267","https://openalex.org/W2390610678","https://openalex.org/W2117838073","https://openalex.org/W3071522575","https://openalex.org/W2363054820"],"abstract_inverted_index":{"We":[0,84,115],"present":[1,86,116],"new":[2],"algorithms":[3,28,56],"for":[4,36,65],"<inline-formula><tex-math":[5,102],"notation=\"LaTeX\">$k$</tex-math></inline-formula>":[6,103],"-means":[7,104],"clustering":[8,21,55,72,133],"on":[9,16],"a":[10,14,74,98],"data":[11],"stream":[12],"with":[13,97],"focus":[15],"providing":[17],"fast":[18],"responses":[19],"to":[20,24,80],"queries.":[22],"Compared":[23],"the":[25,33,41,59,70,93,124],"state-of-the-art,":[26],"our":[27,131],"provide":[29,111],"substantial":[30],"improvements":[31],"in":[32,68],"query":[34,113],"time":[35],"cluster-center":[37],"queries":[38,67],"while":[39],"retaining":[40],"desirable":[42],"properties":[43],"of":[44,62,129],"provably":[45],"small":[46],"approximation":[47],"error":[48],"and":[49,120,127],"low":[50],"space":[51],"usage.":[52],"Our":[53],"proposed":[54,132],"systematically":[57],"reuse":[58],"\u201ccoresets\u201d":[60],"(summaries":[61],"data)":[63],"computed":[64],"recent":[66],"answering":[69],"current":[71],"query,":[73],"novel":[75],"technique":[76],"which":[77],"we":[78],"refer":[79],"as":[81],"coreset":[82,94],"caching.":[83],"also":[85],"an":[87],"algorithm":[88,109],"called":[89],"<monospace>OnlineCC</monospace>":[90,108],"that":[91],"integrates":[92],"caching":[95],"idea":[96],"simple":[99],"sequential":[100],"streaming":[101],"algorithm.":[105],"In":[106],"practice,":[107],"can":[110],"constant":[112],"time.":[114],"both":[117],"theoretical":[118],"analysis":[119],"detailed":[121],"experiments":[122],"demonstrating":[123],"correctness,":[125],"accuracy,":[126],"efficiency":[128],"all":[130],"algorithms.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
