{"id":"https://openalex.org/W2123193743","doi":"https://doi.org/10.1109/iri.2009.5211613","title":"Feature selection with biased sample distributions","display_name":"Feature selection with biased sample distributions","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2123193743","doi":"https://doi.org/10.1109/iri.2009.5211613","mag":"2123193743"},"language":"en","primary_location":{"id":"doi:10.1109/iri.2009.5211613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2009.5211613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Information Reuse & Integration","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/A5022745266","display_name":"Abu Hena Mustafa Kamal","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abu H. M. Kamal","raw_affiliation_strings":["Dept. of Computer Science & Engineering, Florida Atlantic University, Boca Raton, FL, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Engineering, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084641325","display_name":"Xingquan Zhu","orcid":"https://orcid.org/0000-0003-4129-9611"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Xingquan Zhu","raw_affiliation_strings":["Dept. of Computer Science & Engineering, Florida Atlantic University, Boca Raton, FL, USA","Faculty of Engineering & Information Tech., University of Technology, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Engineering, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Faculty of Engineering & Information Tech., University of Technology, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112683390","display_name":"Abhijit S. Pandya","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhijit Pandya","raw_affiliation_strings":["Dept. of Computer Science & Engineering, Florida Atlantic University, Boca Raton, FL, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Engineering, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109189868","display_name":"Sam Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Hsu","raw_affiliation_strings":["Dept. of Computer Science & Engineering, Florida Atlantic University, Boca Raton, FL, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Engineering, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022745266"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":null,"apc_paid":null,"fwci":0.4516,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74580387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"297","issue":null,"first_page":"23","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.993399977684021,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.993399977684021,"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":0.9901000261306763,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.7194469571113586},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7121360301971436},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5938526391983032},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5845356583595276},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.579155445098877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.550504207611084},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5192430019378662},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5090398192405701},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.5044432878494263},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.48144763708114624},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40681594610214233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194469571113586},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7121360301971436},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5938526391983032},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5845356583595276},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.579155445098877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550504207611084},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5192430019378662},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5090398192405701},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.5044432878494263},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48144763708114624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40681594610214233},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iri.2009.5211613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2009.5211613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Information Reuse & Integration","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/19195","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/19195","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W297888808","https://openalex.org/W1500895378","https://openalex.org/W1570448133","https://openalex.org/W1570713908","https://openalex.org/W2017337590","https://openalex.org/W2055271333","https://openalex.org/W2067445549","https://openalex.org/W2109363337","https://openalex.org/W2113890143","https://openalex.org/W2116079122","https://openalex.org/W2140785063","https://openalex.org/W2147169507","https://openalex.org/W2152393478","https://openalex.org/W2523842147","https://openalex.org/W2911964244","https://openalex.org/W2966207845","https://openalex.org/W2996326575","https://openalex.org/W4244238212","https://openalex.org/W4285719527","https://openalex.org/W6676195635","https://openalex.org/W6682728332"],"related_works":["https://openalex.org/W2317823609","https://openalex.org/W4241263575","https://openalex.org/W3130462184","https://openalex.org/W2902287117","https://openalex.org/W4318256508","https://openalex.org/W2401463593","https://openalex.org/W2349808627","https://openalex.org/W2391671934","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"Feature":[0],"selection":[1,25],"concerns":[2],"the":[3,13,31,35,49,52,56,90,110,151,158,161],"problem":[4],"of":[5,9,74,109,160],"selecting":[6,165],"a":[7,106],"number":[8],"important":[10,142],"features":[11,143,167],"(w.r.t.":[12],"class":[14,45,73,92],"labels)":[15],"in":[16,55,164],"order":[17],"to":[18,29,40,48,140],"build":[19],"accurate":[20,118],"prediction":[21],"models.":[22],"Traditional":[23],"feature":[24],"methods,":[26],"however,":[27],"fail":[28],"take":[30],"sample":[32,172],"distributions":[33],"into":[34],"consideration":[36],"which":[37],"may":[38],"lead":[39],"poor":[41],"predictions":[42],"for":[43,117],"minority":[44,91],"examples.":[46],"Due":[47],"sophistication":[50],"and":[51,101,135],"cost":[53],"involved":[54],"data":[57,69,111,146,169],"collection":[58],"process,":[59],"many":[60],"applications,":[61,89],"such":[62,94],"as":[63,95],"Biomedical":[64],"research,":[65],"commonly":[66],"face":[67],"biased":[68,145,171],"collections":[70,112],"with":[71,150,170],"one":[72],"examples":[75],"(e.g.,":[76,84],"diseased":[77],"samples)":[78],"significantly":[79],"less":[80],"than":[81],"other":[82],"classes":[83],"normal":[85],"samples).":[86],"For":[87],"these":[88],"examples,":[93],"disease":[96],"samples,":[97],"credit":[98],"card":[99],"frauds,":[100],"network":[102],"intrusions,":[103],"are":[104],"only":[105],"small":[107],"portion":[108],"but":[113],"deserve":[114],"full":[115],"attentions":[116],"prediction.":[119],"In":[120],"this":[121],"paper,":[122],"we":[123],"propose":[124],"three":[125],"filtering":[126],"techniques,":[127],"Higher":[128],"Weight":[129],"(HW),":[130],"Differential":[131],"Minority":[132,137],"Repeat":[133,138],"(DMR)":[134],"Balanced":[136],"(BMR),":[139],"identify":[141],"from":[144,168],"collections.":[147],"Experimental":[148],"comparisons":[149],"ReliefF":[152],"method":[153],"on":[154],"five":[155],"datasets":[156],"demonstrate":[157],"effectiveness":[159],"proposed":[162],"methods":[163],"informative":[166],"distributions.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}