{"id":"https://openalex.org/W2089055054","doi":"https://doi.org/10.1145/1401890.1401956","title":"Finding non-redundant, statistically significant regions in high dimensional data","display_name":"Finding non-redundant, statistically significant regions in high dimensional data","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2089055054","doi":"https://doi.org/10.1145/1401890.1401956","mag":"2089055054"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401956","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5004130921","display_name":"Gabriela Moise","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Gabriela Moise","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021763337","display_name":"J\u00f6rg Sander","orcid":"https://orcid.org/0000-0003-4068-7268"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Sander","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004130921"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":18.3056,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":{"value":0.9922889,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"533","last_page":"541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9990000128746033,"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":0.9990000128746033,"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/T11106","display_name":"Data Management and Algorithms","score":0.9961000084877014,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8229163885116577},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.6987409591674805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6221479773521423},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5618934035301208},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5579137206077576},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5475640296936035},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5402798652648926},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.5187913775444031},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5122577548027039},{"id":"https://openalex.org/keywords/complete-linkage-clustering","display_name":"Complete-linkage clustering","score":0.4910736083984375},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.48677730560302734},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.464912474155426},{"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":0.4474654793739319},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4297116696834564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3972739577293396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3467006981372833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3252643346786499},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.14548331499099731}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8229163885116577},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.6987409591674805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6221479773521423},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5618934035301208},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5579137206077576},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5475640296936035},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5402798652648926},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.5187913775444031},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5122577548027039},{"id":"https://openalex.org/C23822008","wikidata":"https://www.wikidata.org/wiki/Q5156437","display_name":"Complete-linkage clustering","level":5,"score":0.4910736083984375},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.48677730560302734},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.464912474155426},{"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":0.4474654793739319},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4297116696834564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3972739577293396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3467006981372833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3252643346786499},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.14548331499099731},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1401890.1401956","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","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/W191006456","https://openalex.org/W1484413656","https://openalex.org/W1506285740","https://openalex.org/W1515984610","https://openalex.org/W1531520279","https://openalex.org/W1562753845","https://openalex.org/W1672197616","https://openalex.org/W1913389890","https://openalex.org/W1977496278","https://openalex.org/W1995433152","https://openalex.org/W2006533296","https://openalex.org/W2042035594","https://openalex.org/W2065811242","https://openalex.org/W2097743039","https://openalex.org/W2099058255","https://openalex.org/W2101133417","https://openalex.org/W2101741219","https://openalex.org/W2102286993","https://openalex.org/W2104809968","https://openalex.org/W2109130989","https://openalex.org/W2110065044","https://openalex.org/W2153790277","https://openalex.org/W2161284614","https://openalex.org/W2167091752","https://openalex.org/W2492952205","https://openalex.org/W4254311734"],"related_works":["https://openalex.org/W4241767317","https://openalex.org/W2188840951","https://openalex.org/W4220814143","https://openalex.org/W3080491161","https://openalex.org/W4232307982","https://openalex.org/W2121197635","https://openalex.org/W2533990316","https://openalex.org/W2141140100","https://openalex.org/W2213356533","https://openalex.org/W1481928625"],"abstract_inverted_index":{"Projected":[0,14],"and":[1],"subspace":[2],"clustering":[3,15,34],"algorithms":[4],"search":[5],"for":[6],"clusters":[7,36,98],"of":[8,12,31,37,42,51,67,82,102],"points":[9,38],"in":[10,27,39,60,111,114],"subsets":[11,41],"attributes.":[13,32],"computes":[16],"several":[17],"disjoint":[18],"clusters,":[19],"plus":[20],"outliers,":[21],"so":[22],"that":[23,55,63],"each":[24],"cluster":[25,83],"exists":[26],"its":[28],"own":[29],"subset":[30],"Subspace":[33],"enumerates":[35],"all":[40],"attributes,":[43],"typically":[44],"producing":[45],"many":[46],"overlapping":[47],"clusters.":[48,75],"One":[49],"problem":[50,78],"existing":[52],"approaches":[53],"is":[54,64,79],"their":[56],"objectives":[57],"are":[58,99],"stated":[59],"a":[61,115],"way":[62],"not":[65],"independent":[66],"the":[68,80,96,103,112],"particular":[69],"algorithm":[70,104],"proposed":[71],"to":[72,93],"detect":[73],"such":[74],"A":[76],"second":[77],"definition":[81],"density":[84],"based":[85],"on":[86],"user-defined":[87],"parameters,":[88],"which":[89],"makes":[90],"it":[91],"hard":[92],"assess":[94],"whether":[95,106],"reported":[97],"an":[100],"artifact":[101],"or":[105],"they":[107],"actually":[108],"stand":[109],"out":[110],"data":[113],"statistical":[116],"sense.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":14}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}