{"id":"https://openalex.org/W2123904884","doi":"https://doi.org/10.1109/icdm.2002.1183915","title":"O-Cluster: scalable clustering of large high dimensional data sets","display_name":"O-Cluster: scalable clustering of large high dimensional data sets","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2123904884","doi":"https://doi.org/10.1109/icdm.2002.1183915","mag":"2123904884"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2002.1183915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","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/A5008597328","display_name":"Boriana L. Milenova","orcid":null},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"B.L. Milenova","raw_affiliation_strings":["Oracle Data Mining Technologies, Burlington, MA, USA","Oracle Data Min. Technol., Burlington, MA, USA"],"affiliations":[{"raw_affiliation_string":"Oracle Data Mining Technologies, Burlington, MA, USA","institution_ids":["https://openalex.org/I1342911587"]},{"raw_affiliation_string":"Oracle Data Min. Technol., Burlington, MA, USA","institution_ids":["https://openalex.org/I1342911587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037120683","display_name":"Marcos M. Campos","orcid":null},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.M. Campos","raw_affiliation_strings":["Oracle Data Mining Technologies, Burlington, MA, USA","Oracle Data Min. Technol., Burlington, MA, USA"],"affiliations":[{"raw_affiliation_string":"Oracle Data Mining Technologies, Burlington, MA, USA","institution_ids":["https://openalex.org/I1342911587"]},{"raw_affiliation_string":"Oracle Data Min. Technol., Burlington, MA, USA","institution_ids":["https://openalex.org/I1342911587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008597328"],"corresponding_institution_ids":["https://openalex.org/I1342911587"],"apc_list":null,"apc_paid":null,"fwci":5.6156,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.95930496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"290","last_page":"297"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9905999898910522,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9901999831199646,"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":0.8829936385154724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792047262191772},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.686761200428009},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.6565544009208679},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.6231936812400818},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.6185756921768188},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6087987422943115},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6030077934265137},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5500879287719727},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5348932147026062},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.4391508996486664},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.43256449699401855},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4281190037727356},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.42400574684143066},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32925841212272644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20450693368911743},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11212819814682007}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8829936385154724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792047262191772},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.686761200428009},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.6565544009208679},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.6231936812400818},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.6185756921768188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6087987422943115},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6030077934265137},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5500879287719727},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5348932147026062},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.4391508996486664},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.43256449699401855},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4281190037727356},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.42400574684143066},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32925841212272644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20450693368911743},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11212819814682007},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdm.2002.1183915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.866","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.oracle.com/technology/products/bi/odm/pdf/o_cluster_algorithm.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":35,"referenced_works":["https://openalex.org/W147860157","https://openalex.org/W204885769","https://openalex.org/W308932931","https://openalex.org/W1493454437","https://openalex.org/W1529320607","https://openalex.org/W1566114229","https://openalex.org/W1575476631","https://openalex.org/W1595303882","https://openalex.org/W1633659671","https://openalex.org/W1660133578","https://openalex.org/W1672197616","https://openalex.org/W1673310716","https://openalex.org/W1977496278","https://openalex.org/W1996510517","https://openalex.org/W2006685053","https://openalex.org/W2065811242","https://openalex.org/W2095897464","https://openalex.org/W2112210867","https://openalex.org/W2127218421","https://openalex.org/W2131687179","https://openalex.org/W2137460067","https://openalex.org/W2160066096","https://openalex.org/W2978337448","https://openalex.org/W2999729612","https://openalex.org/W4244268470","https://openalex.org/W4254311734","https://openalex.org/W6608319432","https://openalex.org/W6631561827","https://openalex.org/W6633857196","https://openalex.org/W6635487554","https://openalex.org/W6636873521","https://openalex.org/W6637052001","https://openalex.org/W6678914141","https://openalex.org/W6680671007","https://openalex.org/W6683247491"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2188840951","https://openalex.org/W3140018618","https://openalex.org/W2590117803","https://openalex.org/W2393707058","https://openalex.org/W3124860551","https://openalex.org/W2389934482","https://openalex.org/W2388628913","https://openalex.org/W3186815950","https://openalex.org/W2202413591"],"abstract_inverted_index":{"Clustering":[0],"large":[1,31,60,78],"data":[2,26,62],"sets":[3,27],"of":[4,33,41,47,52,70,80,106,136],"high":[5,39,107,134],"dimensionality":[6],"has":[7],"always":[8],"been":[9],"a":[10,29,37,45,84,92,117,125],"challenge":[11],"for":[12],"clustering":[13,18,86,139],"algorithms.":[14],"Many":[15],"recently":[16],"developed":[17],"algorithms":[19,54],"have":[20],"attempted":[21],"to":[22,102,143],"address":[23],"either":[24],"handling":[25],"with":[28,36,77,97],"very":[30,38,59],"number":[32,40],"records":[34],"and/or":[35],"dimensions.":[42],"We":[43,131],"provide":[44],"discussion":[46],"the":[48,68,73,110,129,133,137],"advantages":[49],"and":[50,72,121,145],"limitations":[51],"existing":[53],"when":[55],"they":[56],"operate":[57],"on":[58,116],"multidimensional":[61],"sets.":[63],"To":[64],"simultaneously":[65],"overcome":[66],"both":[67],"\"curse":[69],"dimensionality\"":[71],"scalability":[74],"problems":[75],"associated":[76],"amounts":[79],"data,":[81],"we":[82],"propose":[83],"new":[85],"algorithm":[87],"called":[88],"O-Cluster.":[89],"O-Cluster":[90],"combines":[91],"novel":[93],"active":[94],"sampling":[95],"technique":[96],"an":[98],"axis-parallel":[99],"partitioning":[100],"strategy":[101],"identify":[103],"continuous":[104],"areas":[105],"density":[108],"in":[109],"input":[111],"space.":[112],"The":[113],"method":[114],"operates":[115],"limited":[118],"memory":[119],"buffer":[120],"requires":[122],"at":[123],"most":[124],"single":[126],"scan":[127],"through":[128],"data.":[130],"demonstrate":[132],"quality":[135],"obtained":[138],"solutions,":[140],"their":[141],"robustness":[142],"noise,":[144],"O-Cluster's":[146],"excellent":[147],"scalability.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}