{"id":"https://openalex.org/W2027926002","doi":"https://doi.org/10.1021/ci0499222","title":"Accelerated K-Means Clustering in Metric Spaces","display_name":"Accelerated K-Means Clustering in Metric Spaces","publication_year":2004,"publication_date":"2004-09-30","ids":{"openalex":"https://openalex.org/W2027926002","doi":"https://doi.org/10.1021/ci0499222","mag":"2027926002","pmid":"https://pubmed.ncbi.nlm.nih.gov/15554661"},"language":"en","primary_location":{"id":"doi:10.1021/ci0499222","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci0499222","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Computer Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5059933948","display_name":"Andrew Smellie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121633","display_name":"Arqule (United States)","ror":"https://ror.org/02nftnt56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121633"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Smellie","raw_affiliation_strings":["ArQule Inc., 19 Presidential Way, Woburn, Massachusetts 01801","ArQule Inc., 19 Presidential Way, Woburn, Massachusetts 01801, USA"],"affiliations":[{"raw_affiliation_string":"ArQule Inc., 19 Presidential Way, Woburn, Massachusetts 01801","institution_ids":["https://openalex.org/I4210121633"]},{"raw_affiliation_string":"ArQule Inc., 19 Presidential Way, Woburn, Massachusetts 01801, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059933948"],"corresponding_institution_ids":["https://openalex.org/I4210121633"],"apc_list":null,"apc_paid":null,"fwci":1.7988,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87116429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"44","issue":"6","first_page":"1929","last_page":"1935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9968000054359436,"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":0.9968000054359436,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.8325178027153015},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.803462028503418},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6175633072853088},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5982571840286255},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.595464289188385},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5785423517227173},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5746012926101685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5699589848518372},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5464134216308594},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5432255864143372},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5010063648223877},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.46818578243255615},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.45602530241012573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4078017771244049},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38366568088531494},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.33449435234069824},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.29857346415519714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2726207971572876},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.13110420107841492},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.09997010231018066}],"concepts":[{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.8325178027153015},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.803462028503418},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6175633072853088},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5982571840286255},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.595464289188385},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5785423517227173},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5746012926101685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5699589848518372},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5464134216308594},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5432255864143372},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5010063648223877},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.46818578243255615},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.45602530241012573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4078017771244049},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38366568088531494},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.33449435234069824},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.29857346415519714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2726207971572876},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.13110420107841492},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.09997010231018066},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1021/ci0499222","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci0499222","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Computer Sciences","raw_type":"journal-article"},{"id":"pmid:15554661","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15554661","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and computer sciences","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1977556410","https://openalex.org/W2061565400","https://openalex.org/W2069447707","https://openalex.org/W2130618490","https://openalex.org/W2140405352","https://openalex.org/W2150593711"],"related_works":["https://openalex.org/W2357582197","https://openalex.org/W4285613040","https://openalex.org/W1985101567","https://openalex.org/W2384052049","https://openalex.org/W4220814143","https://openalex.org/W2365091638","https://openalex.org/W2367205823","https://openalex.org/W2087424554","https://openalex.org/W1989337993","https://openalex.org/W2357108794"],"abstract_inverted_index":{"The":[0,45],"K-means":[1],"method":[2,76,129],"is":[3,52],"a":[4,30,75,122],"popular":[5],"technique":[6],"for":[7],"clustering":[8,109],"data":[9,102,106],"into":[10],"k-partitions.":[11],"In":[12],"the":[13,17,37,41,53,68,71,84,108],"adaptive":[14],"form":[15],"of":[16,32,49,55,70,77,110,127],"algorithm,":[18],"Lloyds":[19],"method,":[20],"an":[21],"iterative":[22],"procedure":[23],"alternately":[24],"assigns":[25],"cluster":[26,43,63,81],"membership":[27,82],"based":[28,39,113],"on":[29,40],"set":[31],"centroids":[33,38],"and":[34,92,104,130],"then":[35],"redefines":[36],"computed":[42],"membership.":[44],"most":[46],"time-consuming":[47],"part":[48],"this":[50],"algorithm":[51],"determination":[54],"which":[56,62],"points":[57,85],"being":[58,86],"clustered":[59,87],"belong":[60,88],"to":[61,89,121,131],"center.":[64],"This":[65],"paper":[66],"discusses":[67],"use":[69],"vantage-point":[72],"tree":[73],"as":[74],"more":[78],"quickly":[79],"assigning":[80],"when":[83],"intrinsically":[90],"low-":[91],"medium-dimensional":[93],"metric":[94],"spaces.":[95],"Results":[96],"will":[97,118],"be":[98,119],"discussed":[99],"from":[100],"simulated":[101],"sets":[103],"real-world":[105],"in":[107],"molecular":[111],"databases":[112],"upon":[114],"physicochemical":[115],"properties.":[116],"Comparisons":[117],"made":[120],"highly":[123],"optimized":[124],"brute-force":[125],"implementation":[126],"Lloyd's":[128],"other":[132],"pruning":[133],"strategies.":[134]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}