{"id":"https://openalex.org/W2153922613","doi":"https://doi.org/10.1109/icdm.2002.1183893","title":"Feature selection for clustering - a filter solution","display_name":"Feature selection for clustering - a filter solution","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2153922613","doi":"https://doi.org/10.1109/icdm.2002.1183893","mag":"2153922613"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2002.1183893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183893","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/A5043358521","display_name":"Manoranjan Dash","orcid":"https://orcid.org/0000-0003-1216-8700"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Dash","raw_affiliation_strings":["Department of Elect & Comp Engineering, Northwestern University, Evanston, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Elect & Comp Engineering, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101887792","display_name":"Keunho Choi","orcid":"https://orcid.org/0009-0009-1343-2500"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Choi","raw_affiliation_strings":["Department of Elect & Comp Engineering, Northwestern University, Evanston, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Elect & Comp Engineering, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031838897","display_name":"Peter Scheuermann","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Scheuermann","raw_affiliation_strings":["Department of Elect & Comp Engineering, Northwestern University, Evanston, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Elect & Comp Engineering, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100338946","display_name":"Huan Liu","orcid":"https://orcid.org/0000-0002-3264-7904"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huan Liu","raw_affiliation_strings":["Department of Camp Sci & Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Camp Sci & Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043358521"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":15.4428,"has_fulltext":false,"cited_by_count":380,"citation_normalized_percentile":{"value":0.99021684,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"122"},"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/T10057","display_name":"Face and Expression Recognition","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8394235372543335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6388744115829468},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.632628858089447},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.6322764158248901},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6027518510818481},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.6012632250785828},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.5915838479995728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5560815334320068},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5345667004585266},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5186492800712585},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.5104116797447205},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.48726096749305725},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.4872359335422516},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4267062544822693}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8394235372543335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6388744115829468},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.632628858089447},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.6322764158248901},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6027518510818481},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.6012632250785828},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.5915838479995728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5560815334320068},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5345667004585266},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5186492800712585},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.5104116797447205},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.48726096749305725},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.4872359335422516},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4267062544822693},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdm.2002.1183893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183893","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:10.1.1.7.7169","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.7169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.northwestern.edu/~peters/feature_selection_for_clustering.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.8.5141","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.5141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.public.asu.edu/~huanliu/papers/icdm02.ps","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":30,"referenced_works":["https://openalex.org/W1525435190","https://openalex.org/W1526719228","https://openalex.org/W1554275123","https://openalex.org/W1672197616","https://openalex.org/W1890873505","https://openalex.org/W1972294657","https://openalex.org/W1977496278","https://openalex.org/W1980053379","https://openalex.org/W2042035594","https://openalex.org/W2065811242","https://openalex.org/W2073308541","https://openalex.org/W2084134149","https://openalex.org/W2084812512","https://openalex.org/W2119689447","https://openalex.org/W2133462743","https://openalex.org/W2135346934","https://openalex.org/W2142819948","https://openalex.org/W2999729612","https://openalex.org/W3017143921","https://openalex.org/W3039539181","https://openalex.org/W4231916799","https://openalex.org/W4234536190","https://openalex.org/W4254311734","https://openalex.org/W4298882835","https://openalex.org/W6631377893","https://openalex.org/W6631457093","https://openalex.org/W6633167049","https://openalex.org/W6639419968","https://openalex.org/W6677786031","https://openalex.org/W6780396083"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W2160785859","https://openalex.org/W2188840951","https://openalex.org/W3120229345","https://openalex.org/W2393707058","https://openalex.org/W3186815950","https://openalex.org/W2590117803","https://openalex.org/W2202413591","https://openalex.org/W2389934482","https://openalex.org/W2388628913"],"abstract_inverted_index":{"Processing":[0],"applications":[1,73],"with":[2,129,183],"a":[3,10,36,57,109,132],"large":[4],"number":[5,88,185],"of":[6,89,94,115,140,177,186,195],"dimensions":[7],"has":[8,131,157],"been":[9,40],"challenge":[11],"for":[12,42,45,171],"the":[13,33,87,92,125,173,184,193],"KDD":[14],"community.":[15],"Feature":[16],"selection,":[17],"an":[18,24,149],"effective":[19],"dimensionality":[20],"reduction":[21],"technique,":[22],"is":[23,68,113,122,153,169,181,189],"essential":[25],"pre-processing":[26],"method":[27,111,121],"to":[28,60,75,98,138],"remove":[29],"noisy":[30],"features.":[31],"In":[32,104],"literature":[34],"only":[35,191],"few":[37],"methods":[38,51],"have":[39],"proposed":[41,120],"feature":[43,63],"selection":[44],"clustering,":[46],"and":[47,91,160,188,203],"almost":[48],"all":[49],"these":[50],"are":[52],"'wrapper'":[53],"techniques":[54],"that":[55,82,112,127,139,152],"require":[56,83],"clustering":[58,80,96,100,117],"algorithm":[59],"evaluate":[61,99],"candidate":[62],"subsets.":[64],"The":[65,119,166],"wrapper":[66],"approach":[67],"largely":[69],"unsuitable":[70],"in":[71,101],"real-world":[72],"due":[74],"its":[76,207],"heavy":[77],"reliance":[78],"on":[79,124],"algorithms":[81],"parameters":[84],"such":[85],"as":[86],"clusters,":[90],"lack":[93],"suitable":[95,170],"criteria":[97],"different":[102,134],"subspaces.":[103],"this":[105,146],"paper":[106],"we":[107,147],"propose":[108,148],"'filter'":[110],"independent":[114],"any":[116],"algorithm.":[118],"based":[123],"observation":[126],"data":[128,141,156],"clusters":[130,159],"very":[133],"point-to-point":[135],"distance":[136],"histogram":[137],"without":[142],"clusters.":[143],"By":[144],"exploiting":[145],"entropy":[150,167],"measure":[151,168],"low":[154],"if":[155,162],"distinct":[158],"high":[161],"it":[163,180],"does":[164],"not.":[165],"selecting":[172],"most":[174],"important":[175],"subset":[176],"features":[178],"because":[179],"invariant":[182],"dimensions,":[187],"affected":[190],"by":[192],"quality":[194],"clustering.":[196],"Extensive":[197],"performance":[198],"evaluation":[199],"over":[200],"synthetic,":[201],"benchmark,":[202],"real":[204],"datasets":[205],"shows":[206],"effectiveness.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":27},{"year":2012,"cited_by_count":28}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}