{"id":"https://openalex.org/W2131229395","doi":"https://doi.org/10.4304/jsw.9.3.697-704","title":"An Empirical Study for Software Fault-Proneness Prediction with Ensemble Learning Models on Imbalanced Data Sets","display_name":"An Empirical Study for Software Fault-Proneness Prediction with Ensemble Learning Models on Imbalanced Data Sets","publication_year":2014,"publication_date":"2014-03-01","ids":{"openalex":"https://openalex.org/W2131229395","doi":"https://doi.org/10.4304/jsw.9.3.697-704","mag":"2131229395"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.9.3.697-704","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.3.697-704","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-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/A5040892865","display_name":"Renqing Li","orcid":"https://orcid.org/0000-0002-0141-6812"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renqing Li","raw_affiliation_strings":["Beihang Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang Univ.#TAB#","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054827179","display_name":"Shihai Wang","orcid":"https://orcid.org/0000-0002-0241-0009"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihai Wang","raw_affiliation_strings":["Beihang Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang Univ.#TAB#","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":4.8514,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95248615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9995999932289124,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.771702766418457},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.5583728551864624},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5492501258850098},{"id":"https://openalex.org/keywords/software-reliability-testing","display_name":"Software reliability testing","score":0.5267117619514465},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.5202797055244446},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.5151640176773071},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.5049484372138977},{"id":"https://openalex.org/keywords/software-sizing","display_name":"Software sizing","score":0.49120110273361206},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4792492389678955},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4511706531047821},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.43724051117897034},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.4360602796077728},{"id":"https://openalex.org/keywords/verification-and-validation","display_name":"Verification and validation","score":0.4213048815727234},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.35339879989624023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33625954389572144},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.33038702607154846},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08080720901489258},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07736614346504211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771702766418457},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5583728551864624},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5492501258850098},{"id":"https://openalex.org/C52928878","wikidata":"https://www.wikidata.org/wiki/Q7554226","display_name":"Software reliability testing","level":5,"score":0.5267117619514465},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.5202797055244446},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.5151640176773071},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.5049484372138977},{"id":"https://openalex.org/C201515116","wikidata":"https://www.wikidata.org/wiki/Q7554363","display_name":"Software sizing","level":5,"score":0.49120110273361206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4792492389678955},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4511706531047821},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.43724051117897034},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.4360602796077728},{"id":"https://openalex.org/C48002344","wikidata":"https://www.wikidata.org/wiki/Q2919644","display_name":"Verification and validation","level":2,"score":0.4213048815727234},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.35339879989624023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33625954389572144},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.33038702607154846},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08080720901489258},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07736614346504211},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4304/jsw.9.3.697-704","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.3.697-704","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.825.8544","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.825.8544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ojs.academypublisher.com/index.php/jsw/article/download/jsw0903697704/8993/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1504694836","https://openalex.org/W1544435011","https://openalex.org/W1563938718","https://openalex.org/W1570448133","https://openalex.org/W1938740620","https://openalex.org/W1980851144","https://openalex.org/W2007347131","https://openalex.org/W2008526771","https://openalex.org/W2019338079","https://openalex.org/W2023639956","https://openalex.org/W2057780988","https://openalex.org/W2065436165","https://openalex.org/W2072058346","https://openalex.org/W2075977007","https://openalex.org/W2105776892","https://openalex.org/W2112076978","https://openalex.org/W2125055259","https://openalex.org/W2131650177","https://openalex.org/W2137235241","https://openalex.org/W2145073242","https://openalex.org/W2148143831","https://openalex.org/W2149298154","https://openalex.org/W2154063878","https://openalex.org/W2313957989","https://openalex.org/W3005805959","https://openalex.org/W4251572646","https://openalex.org/W6681651645"],"related_works":["https://openalex.org/W2068483578","https://openalex.org/W2439389792","https://openalex.org/W2182881874","https://openalex.org/W2893321311","https://openalex.org/W2140677443","https://openalex.org/W2381526714","https://openalex.org/W2291789896","https://openalex.org/W2798306226","https://openalex.org/W2012057830","https://openalex.org/W4224250221"],"abstract_inverted_index":{"Abstract\u2014Software":[0],"faults":[1,40,93],"could":[2],"cause":[3],"serious":[4],"system":[5],"errors":[6],"and":[7,19,26,41,83,157,212,231],"failures,":[8],"leading":[9],"to":[10,24,37,61,226],"huge":[11],"economic":[12],"losses.":[13],"But":[14],"currently":[15],"none":[16],"of":[17,55,80,86,105,114,132,171,236],"inspection":[18],"verification":[20],"technique":[21],"is":[22,33,48,59,122],"able":[23],"find":[25],"eliminate":[27],"all":[28],"software":[29,43,64,81,88,92,106,135,145,161,176,207,237,241],"faults.":[30],"Software":[31],"testing":[32,65,82],"an":[34,142,165],"important":[35,60],"way":[36],"inspect":[38],"these":[39,172],"raise":[42],"reliability,":[44],"but":[45],"obviously":[46],"it":[47],"a":[49,56,124,185,223,228],"really":[50,123],"expensive":[51],"job.":[52],"The":[53,91],"estimation":[54],"module\u2019s":[57,229],"fault-proneness":[58,230],"minimize":[62],"the":[63,70,74,78,84,87,99,112,127,130,169,190,193,196,200,205,217,234],"resources":[66],"required":[67],"by":[68,149],"guiding":[69],"resource":[71],"allocation":[72],"on":[73,144,160,168,174,189,203,220],"high-risk":[75,206],"modules.":[76],"Consequently":[77],"efficiency":[79,235],"reliability":[85],"are":[89,116],"improved.":[90],"data":[94,120,178,246],"sets,":[95],"however,":[96],"originally":[97],"have":[98],"imbalanced":[100,119,175,245],"distribution.":[101],"A":[102],"small":[103],"amount":[104],"modules":[107,115,208],"holds":[108],"most":[109,113],"faults,":[110],"while":[111],"fault-free.":[117],"Such":[118],"distribution":[121],"challenge":[125],"for":[126,134],"researchers":[128],"in":[129],"field":[131],"prediction":[133,147,243],"fault-proneness.":[136],"In":[137],"this":[138],"paper,":[139],"we":[140],"make":[141],"investigation":[143],"fault-prone":[146],"models":[148,173,202],"employing":[150],"C4.5,":[151],"SVM,":[152],"KNN,":[153],"Logistic,":[154],"NaiveBayes,":[155],"AdaBoost":[156],"SMOTEBoost":[158,194,221],"based":[159,188,219],"metrics.":[162],"We":[163],"perform":[164],"empirical":[166],"study":[167],"effectiveness":[170],"fault":[177],"sets":[179,247],"obtained":[180],"from":[181],"NASA\u2019s":[182],"MDP.":[183],"After":[184],"comprehensive":[186],"comparison":[187],"experiment":[191],"results,":[192],"reveals":[195],"outstanding":[197],"performances":[198],"than":[199],"other":[201],"predicting":[204],"with":[209],"higher":[210],"recall":[211],"AUC":[213],"values,":[214],"which":[215],"demonstrates":[216],"model":[218],"has":[222],"better":[224],"ability":[225],"estimate":[227],"furthermore":[232],"improve":[233],"testing.":[238],"Index":[239],"Terms\u2014SMOTEBoost,":[240],"fault-prone,":[242],"model,":[244],"I.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}