{"id":"https://openalex.org/W2159945133","doi":"https://doi.org/10.1109/icdm.2002.1183896","title":"Cluster merging and splitting in hierarchical clustering algorithms","display_name":"Cluster merging and splitting in hierarchical clustering algorithms","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2159945133","doi":"https://doi.org/10.1109/icdm.2002.1183896","mag":"2159945133"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2002.1183896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183896","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":"conference-paper","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/A5019708931","display_name":"C.-L. Ding","orcid":"https://orcid.org/0009-0003-9271-0885"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Ding","raw_affiliation_strings":["NERSC Division, Lawrence Berkeley National Laboratory, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC Division, Lawrence Berkeley National Laboratory, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101434435","display_name":"Xiaofeng He","orcid":"https://orcid.org/0000-0002-6911-348X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I4210151627","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521","https://openalex.org/I4210151627"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofeng He","raw_affiliation_strings":["NERSC Division, Lawrence Berkeley National Laboratory, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERSC Division, Lawrence Berkeley National Laboratory, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I4210151627","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":167,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"139","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9997000098228455,"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":0.9997000098228455,"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":0.992900013923645,"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":0.9858999848365784,"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":0.8406717777252197},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.8030757904052734},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.7087089419364929},{"id":"https://openalex.org/keywords/complete-linkage-clustering","display_name":"Complete-linkage clustering","score":0.6727179288864136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6361241936683655},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.617030918598175},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5796265006065369},{"id":"https://openalex.org/keywords/k-medians-clustering","display_name":"k-medians clustering","score":0.5761796236038208},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.557446300983429},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.5008759498596191},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.478089302778244},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4460917115211487},{"id":"https://openalex.org/keywords/determining-the-number-of-clusters-in-a-data-set","display_name":"Determining the number of clusters in a data set","score":0.4440832734107971},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4433775246143341},{"id":"https://openalex.org/keywords/complete-linkage","display_name":"Complete linkage","score":0.4267333149909973},{"id":"https://openalex.org/keywords/hierarchical-clustering-of-networks","display_name":"Hierarchical clustering of networks","score":0.4178740680217743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39347994327545166},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36725014448165894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35883015394210815},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.06704595685005188}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8406717777252197},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.8030757904052734},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.7087089419364929},{"id":"https://openalex.org/C23822008","wikidata":"https://www.wikidata.org/wiki/Q5156437","display_name":"Complete-linkage clustering","level":5,"score":0.6727179288864136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6361241936683655},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.617030918598175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5796265006065369},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.5761796236038208},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.557446300983429},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.5008759498596191},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.478089302778244},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4460917115211487},{"id":"https://openalex.org/C149872217","wikidata":"https://www.wikidata.org/wiki/Q5265701","display_name":"Determining the number of clusters in a data set","level":5,"score":0.4440832734107971},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4433775246143341},{"id":"https://openalex.org/C38734473","wikidata":"https://www.wikidata.org/wiki/Q5156506","display_name":"Complete linkage","level":5,"score":0.4267333149909973},{"id":"https://openalex.org/C82261393","wikidata":"https://www.wikidata.org/wiki/Q17038699","display_name":"Hierarchical clustering of networks","level":5,"score":0.4178740680217743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39347994327545166},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36725014448165894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35883015394210815},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.06704595685005188},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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":3,"locations":[{"id":"doi:10.1109/icdm.2002.1183896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183896","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:10.1.1.13.6124","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.6124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nersc.gov/research/SCG/cding/papers_ps/merge.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.484.8485","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.484.8485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://faculty.ksu.edu.sa/ghazy/CBD_MSc/Ref-9.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1492327544","https://openalex.org/W1524787014","https://openalex.org/W1971784203","https://openalex.org/W2049633694","https://openalex.org/W2121947440","https://openalex.org/W2134737843","https://openalex.org/W2138745909","https://openalex.org/W2139850885","https://openalex.org/W2140190241","https://openalex.org/W2141585940","https://openalex.org/W2319660501","https://openalex.org/W3139328003","https://openalex.org/W6680704940","https://openalex.org/W6680905637","https://openalex.org/W6770641979","https://openalex.org/W6791582515","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2959239999","https://openalex.org/W583850877","https://openalex.org/W1985101567","https://openalex.org/W2072104876","https://openalex.org/W328064821","https://openalex.org/W2402452210","https://openalex.org/W4241767317","https://openalex.org/W2569013970","https://openalex.org/W4232307982","https://openalex.org/W2188840951"],"abstract_inverted_index":{"Hierarchical":[0],"clustering":[1,57,76,107],"constructs":[2],"a":[3,15,20,43,90],"hierarchy":[4],"of":[5,46,102,115],"clusters":[6,13],"by":[7],"either":[8],"repeatedly":[9],"merging":[10],"two":[11],"smaller":[12,24],"into":[14,23],"larger":[16,21],"one":[17],"or":[18,39],"splitting":[19],"cluster":[22],"ones.":[25],"The":[26],"crucial":[27],"step":[28],"is":[29,70,81,89],"how":[30],"to":[31,37,59,93,110],"best":[32,72,83],"select":[33],"the":[34,67,71,78,82,100,113],"next":[35],"cluster(s)":[36],"split":[38],"merge.":[40],"We":[41,54,97],"provide":[42],"comprehensive":[44],"analysis":[45],"selection":[47,62],"methods":[48],"and":[49,64,77,106],"propose":[50],"several":[51],"new":[52],"methods.":[53],"perform":[55],"extensive":[56],"experiments":[58],"test":[60],"8":[61],"methods,":[63],"find":[65],"that":[66],"average":[68],"similarity":[69],"method":[73],"in":[74,84],"divisive":[75],"minmax":[79],"linkage":[80],"agglomerative":[85],"clustering.":[86,116],"Cluster":[87],"balance":[88],"key":[91],"factor":[92],"achieve":[94],"good":[95],"performance.":[96],"also":[98],"introduce":[99],"concept":[101],"objective":[103],"function":[104],"saturation":[105],"target":[108],"distance":[109],"effectively":[111],"assess":[112],"quality":[114]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}