{"id":"https://openalex.org/W1975368942","doi":"https://doi.org/10.1109/iri.2010.5558961","title":"A novel feature selection technique for highly imbalanced data","display_name":"A novel feature selection technique for highly imbalanced data","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W1975368942","doi":"https://doi.org/10.1109/iri.2010.5558961","mag":"1975368942"},"language":"en","primary_location":{"id":"doi:10.1109/iri.2010.5558961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2010.5558961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Information Reuse & Integration","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089170562","display_name":"Taghi M. Khoshgoftaar","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":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["Florida Atlantic University, Boca Raton, FL, USA","Florida Atlantic University, Boca Raton, 33431 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Florida Atlantic University, Boca Raton, 33431 USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109235962","display_name":"Kehan Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I203331390","display_name":"Eastern Connecticut State University","ror":"https://ror.org/01mhgwt57","country_code":"US","type":"education","lineage":["https://openalex.org/I203331390","https://openalex.org/I4210132746"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kehan Gao","raw_affiliation_strings":["Eastern Connecticut State University, Willimantic, CT, USA","Eastern Connecticut State University, Willimantic, 06226, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Connecticut State University, Willimantic, CT, USA","institution_ids":["https://openalex.org/I203331390"]},{"raw_affiliation_string":"Eastern Connecticut State University, Willimantic, 06226, USA","institution_ids":["https://openalex.org/I203331390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111933705","display_name":"Jason Van Hulse","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":"Jason Van Hulse","raw_affiliation_strings":["Florida Atlantic University, Boca Raton, FL, USA","Florida Atlantic University, Boca Raton, 33431 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Florida Atlantic University, Boca Raton, 33431 USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2188,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.45942976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"80","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9958000183105469,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/feature-selection","display_name":"Feature selection","score":0.7773581743240356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748173177242279},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6965974569320679},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6344209909439087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5698685646057129},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5619032382965088},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5464963912963867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49510708451271057},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.49139609932899475},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4723186194896698},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4454386234283447},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4354616403579712},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.42277806997299194},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41197627782821655},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4084477424621582}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7773581743240356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748173177242279},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6965974569320679},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6344209909439087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698685646057129},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5619032382965088},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5464963912963867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49510708451271057},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.49139609932899475},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4723186194896698},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4454386234283447},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4354616403579712},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.42277806997299194},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41197627782821655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4084477424621582},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iri.2010.5558961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2010.5558961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Information Reuse & Integration","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W615842445","https://openalex.org/W1545453017","https://openalex.org/W1570448133","https://openalex.org/W1582984768","https://openalex.org/W1583700199","https://openalex.org/W2004471480","https://openalex.org/W2006407062","https://openalex.org/W2006782375","https://openalex.org/W2075681522","https://openalex.org/W2080521990","https://openalex.org/W2098340665","https://openalex.org/W2101008678","https://openalex.org/W2102831150","https://openalex.org/W2103333826","https://openalex.org/W2104471998","https://openalex.org/W2119168155","https://openalex.org/W2129712776","https://openalex.org/W2139749383","https://openalex.org/W2142481192","https://openalex.org/W2165669526","https://openalex.org/W2314199904","https://openalex.org/W2966207845","https://openalex.org/W3147002886","https://openalex.org/W6670589064","https://openalex.org/W6675969814"],"related_works":["https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2798997222","https://openalex.org/W2798198862","https://openalex.org/W2793336762","https://openalex.org/W2091548507","https://openalex.org/W2368816706","https://openalex.org/W3159414774"],"abstract_inverted_index":{"Two":[0],"challenges":[1],"often":[2],"encountered":[3],"in":[4,13,22,26,45],"data":[5,15,44,60,104,124,149],"mining":[6],"are":[7],"the":[8,23,46,69,73,96,100,103,142,148],"presence":[9],"of":[10,20,48,55,59,122],"excessive":[11],"features":[12],"a":[14,27,36,56,89],"set":[16,150],"and":[17,66,106],"unequal":[18],"numbers":[19],"examples":[21],"two":[24,84,120,144],"classes":[25],"binary":[28],"classification":[29],"problem.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35],"novel":[37],"approach":[38],"to":[39],"feature":[40,64,78,91,107,133],"selection":[41,79,134],"for":[42],"imbalanced":[43],"context":[47],"software":[49,123],"quality":[50],"engineering.":[51],"This":[52,76],"technique":[53,93],"consists":[54],"repetitive":[57,74,77,132],"process":[58],"sampling":[61,105],"followed":[62],"by":[63],"ranking":[65,92,108],"finally":[67],"aggregating":[68],"results":[70,127],"generated":[71],"during":[72],"process.":[75],"method":[80,135],"is":[81,116,151],"compared":[82],"with":[83],"other":[85,101,143],"approaches:":[86],"one":[87],"uses":[88,102],"filter-based":[90],"alone":[94],"on":[95,119,137],"original":[97],"data,":[98],"while":[99],"techniques":[109],"together":[110],"only":[111],"once.":[112],"The":[113,126],"empirical":[114],"validation":[115],"carried":[117],"out":[118],"groups":[121],"sets.":[125],"demonstrate":[128],"that":[129],"our":[130],"proposed":[131],"performs":[136],"average":[138],"significantly":[139],"better":[140],"than":[141],"approaches,":[145],"especially":[146],"when":[147],"highly":[152],"imbalanced.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}