{"id":"https://openalex.org/W4281652406","doi":"https://doi.org/10.1145/3524304.3524310","title":"Improving software fault prediction in imbalanced datasets using the under-sampling approach","display_name":"Improving software fault prediction in imbalanced datasets using the under-sampling approach","publication_year":2022,"publication_date":"2022-02-24","ids":{"openalex":"https://openalex.org/W4281652406","doi":"https://doi.org/10.1145/3524304.3524310"},"language":"en","primary_location":{"id":"doi:10.1145/3524304.3524310","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524304.3524310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 11th International Conference on Software and Computer Applications","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/A5010706372","display_name":"Golnoush Abaei","orcid":"https://orcid.org/0000-0002-8916-759X"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Golnoush Abaei","raw_affiliation_strings":["School of Information Technology, Monash University Malaysia, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016516617","display_name":"Wen Zhong Tah","orcid":null},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Wen Zhong Tah","raw_affiliation_strings":["School of Information Technology, Monash University Malaysia, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041115821","display_name":"Jason Zhern Wee Toh","orcid":null},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jason Zhern Wee Toh","raw_affiliation_strings":["School of Information Technology, Monash University Malaysia, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015716266","display_name":"Ethan Sheng Jian Hor","orcid":null},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ethan Sheng Jian Hor","raw_affiliation_strings":["School of Information Technology, Monash University Malaysia, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Monash University Malaysia, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010706372"],"corresponding_institution_ids":["https://openalex.org/I11662577"],"apc_list":null,"apc_paid":null,"fwci":1.5162,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85845865,"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":"41","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9983000159263611,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.7976590394973755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7334201335906982},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6701239943504333},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6405126452445984},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5895047187805176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5868736505508423},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5787004828453064},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5577888488769531},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5426396131515503},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.541839063167572},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4664919376373291},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.4588587284088135},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.4330846965312958},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41565585136413574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976590394973755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7334201335906982},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6701239943504333},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6405126452445984},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5895047187805176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5868736505508423},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5787004828453064},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5577888488769531},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5426396131515503},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.541839063167572},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4664919376373291},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.4588587284088135},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.4330846965312958},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41565585136413574},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524304.3524310","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524304.3524310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 11th International Conference on Software and Computer Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W49700977","https://openalex.org/W298212978","https://openalex.org/W2015283109","https://openalex.org/W2036599383","https://openalex.org/W2076514170","https://openalex.org/W2116702209","https://openalex.org/W2150757437","https://openalex.org/W2234236208","https://openalex.org/W2244669237","https://openalex.org/W2345946136","https://openalex.org/W2620760558","https://openalex.org/W2772617084","https://openalex.org/W2789758093","https://openalex.org/W2810298341","https://openalex.org/W2904149589","https://openalex.org/W2986296038","https://openalex.org/W3082648102","https://openalex.org/W4247922705","https://openalex.org/W6757412713"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W138569904","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W3092506759","https://openalex.org/W2390914021","https://openalex.org/W2389417819","https://openalex.org/W3195278891"],"abstract_inverted_index":{"To":[0,50],"make":[1],"most":[2,29],"software":[3,16,30,61],"defect-free,":[4],"a":[5,84,97,145],"considerable":[6],"amount":[7],"of":[8,89,104,122,178,187,212],"budget":[9,25],"needs":[10],"to":[11,14,59,202,228],"be":[12,75],"allocated":[13,76],"the":[15,87,102,120,127,148,151,154,157,169,176,182,188],"testing":[17],"phase.":[18],"As":[19],"each":[20],"day":[21],"goes":[22],"by,":[23],"this":[24,82],"slowly":[26],"rises,":[27],"as":[28,101,132],"grows":[31],"in":[32,112,181,218,232],"size":[33],"and":[34,156,205,220,224],"complexity,":[35],"which":[36,174],"causes":[37],"an":[38,164],"issue":[39,103],"for":[40],"specific":[41],"companies":[42],"that":[43,65,72,116],"cannot":[44],"allocate":[45],"sufficient":[46],"resources":[47,73],"towards":[48],"testing.":[49,80],"tackle":[51],"this,":[52],"many":[53,109],"researchers":[54],"use":[55],"machine":[56,91,196],"learning":[57,92,197],"methods":[58,137],"create":[60],"fault":[62],"prediction":[63,123,146],"models":[64,93,124],"can":[66,74,117],"help":[67],"detect":[68],"defect-prone":[69],"modules":[70],"so":[71],"more":[77],"efficiently":[78],"during":[79],"Although":[81],"is":[83,191],"feasible":[85],"plan,":[86],"effectiveness":[88],"these":[90],"also":[94],"depends":[95],"on":[96,194],"few":[98],"factors,":[99],"such":[100],"data":[105,179],"imbalance.":[106],"There":[107],"are":[108,138],"known":[110],"techniques":[111],"class":[113],"imbalance":[114],"research":[115,230],"potentially":[118],"improve":[119],"performance":[121,186],"through":[125],"processing":[126],"dataset":[128,149],"before":[129],"providing":[130],"it":[131,201],"input.":[133],"However,":[134],"not":[135],"all":[136],"compatible":[139],"with":[140],"one":[141],"another.":[142],"Before":[143],"building":[144],"model,":[147],"undergoes":[150],"preprocessing":[152],"step,":[153],"under-sampling,":[155],"feature":[158],"selection":[159],"process.":[160],"This":[161],"study":[162],"uses":[163],"under-sampling":[165],"process":[166],"by":[167,199,222],"employing":[168],"Instance":[170],"Hardness":[171],"Threshold":[172],"(IHT),":[173],"reduces":[175],"number":[177],"present":[180],"majority":[183],"class.":[184],"The":[185,210],"proposed":[189,214],"approach":[190,215],"evaluated":[192],"based":[193],"eight":[195,203],"algorithms":[198],"applying":[200],"moderate":[204],"highly":[206],"imbalanced":[207],"NASA":[208],"datasets.":[209,234],"results":[211],"our":[213],"show":[216],"improvement":[217],"AUC":[219],"F1-Score":[221],"33%":[223],"26%,":[225],"respectively,":[226],"compared":[227],"other":[229],"work":[231],"some":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}