{"id":"https://openalex.org/W1998901634","doi":"https://doi.org/10.1145/1376616.1376638","title":"Outlier-robust clustering using independent components","display_name":"Outlier-robust clustering using independent components","publication_year":2008,"publication_date":"2008-06-09","ids":{"openalex":"https://openalex.org/W1998901634","doi":"https://doi.org/10.1145/1376616.1376638","mag":"1998901634"},"language":"en","primary_location":{"id":"doi:10.1145/1376616.1376638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","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/A5062860517","display_name":"Christian B\u00f6hm","orcid":"https://orcid.org/0000-0002-2237-9969"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christian B\u00f6hm","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035605036","display_name":"Christos Faloutsos","orcid":"https://orcid.org/0000-0003-2996-9790"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos Faloutsos","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009516958","display_name":"Claudia Plant","orcid":"https://orcid.org/0000-0001-5274-8123"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Plant","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062860517"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":7.03562244,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.97732203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9936000108718872,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.8280298709869385},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6218591928482056},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5774402022361755},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5672472715377808},{"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":0.563154399394989},{"id":"https://openalex.org/keywords/k-medians-clustering","display_name":"k-medians clustering","score":0.549227237701416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5329633355140686},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5239455699920654},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49548208713531494},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.48895418643951416},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.48542746901512146},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.46084001660346985},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4607490301132202},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4276324510574341},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38993555307388306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3861393332481384},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3274553418159485}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8280298709869385},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6218591928482056},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5774402022361755},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5672472715377808},{"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":0.563154399394989},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.549227237701416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5329633355140686},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5239455699920654},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49548208713531494},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.48895418643951416},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.48542746901512146},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.46084001660346985},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4607490301132202},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4276324510574341},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38993555307388306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3861393332481384},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3274553418159485},{"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":1,"locations":[{"id":"doi:10.1145/1376616.1376638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","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":26,"referenced_works":["https://openalex.org/W1548802052","https://openalex.org/W1585280831","https://openalex.org/W1585610988","https://openalex.org/W1621977827","https://openalex.org/W1673310716","https://openalex.org/W1977496278","https://openalex.org/W1988157641","https://openalex.org/W2049633694","https://openalex.org/W2067877017","https://openalex.org/W2084812512","https://openalex.org/W2093100781","https://openalex.org/W2095897464","https://openalex.org/W2099242680","https://openalex.org/W2112210867","https://openalex.org/W2144182447","https://openalex.org/W2150753219","https://openalex.org/W2160642098","https://openalex.org/W2165874743","https://openalex.org/W2327714094","https://openalex.org/W2978337448","https://openalex.org/W4205778870","https://openalex.org/W4244268470","https://openalex.org/W4247105055","https://openalex.org/W4254182148","https://openalex.org/W6682346614","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W2042755526","https://openalex.org/W3186815950","https://openalex.org/W2188840951","https://openalex.org/W1481928625","https://openalex.org/W2393816671","https://openalex.org/W3176177124","https://openalex.org/W2389934482","https://openalex.org/W4253222414","https://openalex.org/W4241252752","https://openalex.org/W2366173344"],"abstract_inverted_index":{"How":[0],"can":[1],"we":[2,109],"efficiently":[3],"find":[4],"a":[5,8,16,59,67,117,137,162,171,196],"clustering,":[6],"i.e.":[7],"concise":[9],"description":[10],"of":[11,15,25,27,92,102,139,210,220],"the":[12,44,55,63,75,83,98,103,127,150,158,208,211,218],"cluster":[13,46,56,133,163],"structure,":[14],"given":[17],"data":[18,64,77,85,100,104],"set":[19,65],"which":[20,120,135],"contains":[21,66],"an":[22,88,178],"unknown":[23],"number":[24,91],"clusters":[26,93],"different":[28],"shape":[29],"and":[30,32,48,143,175,180,188,194],"distribution":[31,61,78,101,130,146],"is":[33,94,136,192],"contaminated":[34],"by":[35,124],"noise?":[36],"Most":[37],"existing":[38],"clustering":[39,118,173,198,213],"methods":[40],"are":[41,49],"restricted":[42],"to":[43,52,71,96],"Gaussian":[45],"model":[47,134],"very":[50,200],"sensitive":[51],"noise.":[53],"If":[54],"content":[57],"follows":[58],"non-Gaussian":[60],"and/or":[62],"few":[68],"outliers":[69],"belonging":[70],"no":[72],"cluster,":[73],"then":[74],"computed":[76],"does":[79],"not":[80],"match":[81],"well":[82,165,216],"true":[84,99],"distribution,":[86],"or":[87],"unnaturally":[89],"high":[90],"required":[95],"represent":[97],"set.":[105],"In":[106],"this":[107],"paper":[108],"propose":[110],"OCI":[111],"(Outlier-robust":[112],"Clustering":[113],"using":[114],"Independent":[115,151],"Components),":[116],"method":[119,191],"overcomes":[121],"these":[122],"problems":[123],"(1)":[125],"applying":[126,149],"exponential":[128],"power":[129],"(EPD)":[131],"as":[132,164,166,195,215,217],"generalization":[138],"Gaussian,":[140],"uniform,":[141],"Laplacian":[142],"many":[144],"other":[145],"functions,":[147],"(2)":[148],"Component":[152],"Analysis":[153],"(ICA)":[154],"for":[155,183],"both":[156,207],"determining":[157],"main":[159],"directions":[160],"inside":[161],"finding":[167],"split":[168],"planes":[169],"in":[170],"top-down":[172,197],"approach,":[174],"(3)":[176],"defining":[177],"efficient":[179],"effective":[181],"filter":[182],"outliers,":[184],"based":[185],"on":[186],"EPD":[187],"ICA.":[189],"Our":[190],"parameter-free":[193],"approach":[199],"efficient.":[201],"An":[202],"extensive":[203],"experimental":[204],"evaluation":[205],"shows":[206],"accuracy":[209],"obtained":[212],"result":[214],"efficiency":[219],"our":[221],"method.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}