{"id":"https://openalex.org/W2101866139","doi":"https://doi.org/10.1109/icde.2004.1320061","title":"Scaling clustering algorithms for massive data sets using data streams","display_name":"Scaling clustering algorithms for massive data sets using data streams","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2101866139","doi":"https://doi.org/10.1109/icde.2004.1320061","mag":"2101866139"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2004.1320061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","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/A5081849221","display_name":"Silvia Nittel","orcid":"https://orcid.org/0000-0002-3891-5922"},"institutions":[{"id":"https://openalex.org/I7947594","display_name":"University of Maine","ror":"https://ror.org/01adr0w49","country_code":"US","type":"education","lineage":["https://openalex.org/I2802397601","https://openalex.org/I7947594"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Nittel","raw_affiliation_strings":["SIE & NCGIA, University of Maine, Orono, ME, USA","SIE, Maine Univ., Orono, ME, USA"],"affiliations":[{"raw_affiliation_string":"SIE & NCGIA, University of Maine, Orono, ME, USA","institution_ids":["https://openalex.org/I7947594"]},{"raw_affiliation_string":"SIE, Maine Univ., Orono, ME, USA","institution_ids":["https://openalex.org/I7947594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085655875","display_name":"Kelvin T. Leung","orcid":"https://orcid.org/0000-0001-8892-7537"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K.T. Leung","raw_affiliation_strings":["Computer Science, University of California, Los Angeles, CA, USA","[Computer Science, University of California, Los Angeles, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"[Computer Science, University of California, Los Angeles, CA, USA]","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113899356","display_name":"A. J. Braverman","orcid":null},"institutions":[{"id":"https://openalex.org/I1334627681","display_name":"Jet Propulsion Laboratory","ror":"https://ror.org/027k65916","country_code":"US","type":"facility","lineage":["https://openalex.org/I122411786","https://openalex.org/I1334627681","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Braverman","raw_affiliation_strings":["Earth & Space Science Division, Jet Propulsion Laboratory, Pasadena, CA, USA","Earth and Space Science Division, Jet Propulsion Laboratory, Pasadena, CA, USA"],"affiliations":[{"raw_affiliation_string":"Earth & Space Science Division, Jet Propulsion Laboratory, Pasadena, CA, USA","institution_ids":["https://openalex.org/I1334627681"]},{"raw_affiliation_string":"Earth and Space Science Division, Jet Propulsion Laboratory, Pasadena, CA, USA","institution_ids":["https://openalex.org/I1334627681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081849221"],"corresponding_institution_ids":["https://openalex.org/I7947594"],"apc_list":null,"apc_paid":null,"fwci":1.7988,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.87504426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"830","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991999864578247,"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":0.9991999864578247,"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/T11106","display_name":"Data Management and Algorithms","score":0.9927999973297119,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9908000230789185,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8136682510375977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.784966230392456},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7106682658195496},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.7091574668884277},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.6021484136581421},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5938968062400818},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5182166695594788},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5042506456375122},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48418429493904114},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4591902792453766},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.45356887578964233},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.44989675283432007},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4195978045463562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1673351526260376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13982492685317993}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8136682510375977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784966230392456},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7106682658195496},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.7091574668884277},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.6021484136581421},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5938968062400818},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5182166695594788},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5042506456375122},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48418429493904114},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4591902792453766},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.45356887578964233},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.44989675283432007},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4195978045463562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1673351526260376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13982492685317993},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2004.1320061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W147860157","https://openalex.org/W152920516","https://openalex.org/W1501524276","https://openalex.org/W1502359728","https://openalex.org/W1530595269","https://openalex.org/W1547978973","https://openalex.org/W1566114229","https://openalex.org/W1575476631","https://openalex.org/W1582133336","https://openalex.org/W1597826525","https://openalex.org/W1822348499","https://openalex.org/W1943557536","https://openalex.org/W1949687736","https://openalex.org/W1977496278","https://openalex.org/W1989703244","https://openalex.org/W2005188603","https://openalex.org/W2042035594","https://openalex.org/W2072110278","https://openalex.org/W2095897464","https://openalex.org/W2099358357","https://openalex.org/W2110209868","https://openalex.org/W2112056262","https://openalex.org/W2118229812","https://openalex.org/W2131578006","https://openalex.org/W2131687179","https://openalex.org/W2161463763","https://openalex.org/W2167487034","https://openalex.org/W2212047990"],"related_works":["https://openalex.org/W4301002638","https://openalex.org/W2160785859","https://openalex.org/W2371010743","https://openalex.org/W2163563073","https://openalex.org/W3088133960","https://openalex.org/W3146523624","https://openalex.org/W4253632195","https://openalex.org/W3124860551","https://openalex.org/W3186815950","https://openalex.org/W2202413591"],"abstract_inverted_index":{"Computing":[0],"clustering":[1,153,173],"techniques":[2],"on":[3],"massive":[4],"data":[5,19,34,45,59,63,72,95,120,145,162],"sets":[6],"is":[7,102,149],"still":[8],"not":[9],"feasible":[10],"nor":[11],"efficient":[12],"today.":[13],"For":[14],"instance,":[15],"raw":[16],"satellite":[17],"imagery":[18],"can":[20,65],"be":[21,54,66,128,133],"replaced":[22],"with":[23,105],"compressed":[24],"counterparts":[25],"for":[26,143],"many":[27],"scientific":[28,33,144],"applications.":[29],"However,":[30],"to":[31,107,123,132,150,158],"facilitate":[32],"analysis":[35],"the":[36,41,44,57,70],"high":[37,97,171],"order":[38],"correlation":[39],"between":[40],"attributes":[42],"in":[43,56,96,130,164],"set":[46,73],"as":[47,49],"well":[48],"their":[50],"nonparametric":[51],"distribution":[52],"must":[53,127],"preserved":[55],"reduced":[58],"set.":[60],"Therefore,":[61],"practical":[62],"reduction":[64],"achieved":[67],"by":[68,86],"partitioning":[69],"overall":[71],"via":[74],"a":[75,114,124,136,141,152,165],"coarse":[76],"regular":[77],"spatial":[78,94],"grid,":[79],"and":[80,110,169],"compressing":[81],"each":[82],"grid":[83,125,167],"cell":[84,126],"individually":[85],"computing":[87],"multivariate":[88],"histograms":[89],"or":[90],"k-means":[91,101,116],"clustering.":[92],"Clustering":[93],"dimensional":[98],"spaces":[99],"using":[100],"expensive":[103],"both":[104],"regard":[106],"computational":[108],"costs":[109],"memory":[111,131],"requirements.":[112],"In":[113],"traditional":[115],"implementation":[117],"all":[118],"N":[119],"points":[121,163],"belonging":[122],"kept":[129],"clustered":[134],"at":[135],"time,":[137],"which":[138],"often":[139],"establishes":[140],"bottleneck":[142],"sets.":[146],"Our":[147],"objective":[148],"define":[151],"algorithm":[154],"that":[155],"scales":[156],"automatically":[157],"any":[159],"number":[160],"of":[161],"single":[166],"cell,":[168],"provides":[170],"quality":[172],"results.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}