{"id":"https://openalex.org/W3203165331","doi":null,"title":"Applications of resampling methods to estimate the number of clusters and to improve the accuracy of a clustering method","display_name":"Applications of resampling methods to estimate the number of clusters and to improve the accuracy of a clustering method","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W3203165331","mag":"3203165331"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.25.5002","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.25.5002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stat.Berkeley.EDU/tech-reports/600.ps.Z","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5080124702","display_name":"Jane Fridlyand","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jane Fridlyand","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018207168","display_name":"Sandrine Dudoit","orcid":"https://orcid.org/0000-0002-6069-8629","observed_orcids":["https://orcid.org/0000-0002-6069-8629"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandrine Dudoit","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6069-8629","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2127,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.95827484,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.6060000061988831,"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":0.6060000061988831,"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/T10885","display_name":"Gene expression and cancer classification","score":0.35569998621940613,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.029200000688433647,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/resampling","display_name":"resampling","score":0.9070000052452087},{"id":"https://openalex.org/keywords/clustering","display_name":"clustering","score":0.7400000095367432},{"id":"https://openalex.org/keywords/number-of-clusters-estimation","display_name":"optimal number of clusters","score":0.8009999990463257},{"id":"https://openalex.org/keywords/bagging","display_name":"bagging","score":0.9390000104904175},{"id":"https://openalex.org/keywords/discriminant-analysis","display_name":"discriminant analysis","score":0.953000009059906},{"id":"https://openalex.org/keywords/clustering-accuracy","display_name":"clustering accuracy","score":0.8240000009536743},{"id":"https://openalex.org/keywords/gene-expression-data","display_name":"gene expression data","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.686247706413269},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.6416381597518921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5640829801559448},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4348641633987427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4067034125328064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39100098609924316}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.25.5002","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.25.5002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stat.Berkeley.EDU/tech-reports/600.ps.Z","raw_type":"text"},{"id":"pmh:oai:berkeley.edu:28722-bk0000n3x9z","doi":null,"is_oa":false,"landing_page_url":"http://stat-reports.lib.berkeley.edu/accessPages/600.html","pdf_url":null,"source":{"id":"https://openalex.org/S7407050879","display_name":"UC Berkeley","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I95457486","host_organization_name":"University of California, Berkeley","host_organization_lineage":["https://openalex.org/I95457486"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"technical reports"},{"id":"mag:3203165331","doi":null,"is_oa":false,"landing_page_url":"https://digicoll.lib.berkeley.edu/record/85915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W919538277","https://openalex.org/W1886306325","https://openalex.org/W2107208924","https://openalex.org/W7095912918","https://openalex.org/W2146261447","https://openalex.org/W1772981906","https://openalex.org/W2107318313","https://openalex.org/W2141951767","https://openalex.org/W2394765402","https://openalex.org/W1548779692"],"abstract_inverted_index":{"The":[0,26,84],"burgeoning":[1],"field":[2],"of":[3,31,59,77,86],"genomics,":[4],"and":[5,16,23,54,89,97],"in":[6,13,36,45,81],"particular":[7],"microarray":[8,106],"experiments,":[9],"have":[10],"revived":[11],"interest":[12],"both":[14],"discriminant":[15,46],"cluster":[17,37,60],"analysis,":[18,47],"by":[19],"raising":[20],"new":[21],"methodological":[22],"computational":[24],"challenges.":[25],"present":[27],"paper":[28],"discusses":[29],"applications":[30],"resampling":[32,40,68],"methods":[33,91],"to":[34,50,55,73],"problems":[35],"analysis.":[38],"A":[39,65],"method,":[41],"known":[42],"as":[43],"bagging":[44],"is":[48,70],"applied":[49],"increase":[51],"clustering":[52],"accuracy":[53],"assess":[56],"the":[57,75,87],"confidence":[58],"assignments":[61],"for":[62],"individual":[63],"observations.":[64],"novel":[66],"prediction-based":[67],"method":[69],"also":[71],"proposed":[72,88],"estimate":[74],"number":[76],"clusters,":[78],"if":[79],"any,":[80],"a":[82],"dataset.":[83],"performance":[85],"existing":[90],"are":[92],"compared":[93],"using":[94],"simulated":[95],"data":[96,100],"gene":[98],"expression":[99],"from":[101],"four":[102],"recently":[103],"published":[104],"cancer":[105],"studies.":[107]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-10T09:11:00.788812","created_date":"2021-10-11T00:00:00"}