{"id":"https://openalex.org/W4293228314","doi":"https://doi.org/10.1145/3511430.3511444","title":"Feature Transformation for Improved Software Bug Detection Models","display_name":"Feature Transformation for Improved Software Bug Detection Models","publication_year":2022,"publication_date":"2022-02-15","ids":{"openalex":"https://openalex.org/W4293228314","doi":"https://doi.org/10.1145/3511430.3511444"},"language":"en","primary_location":{"id":"doi:10.1145/3511430.3511444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511430.3511444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"15th Innovations in Software Engineering Conference","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/A5056190672","display_name":"Shamse Tasnim Cynthia","orcid":"https://orcid.org/0000-0001-9529-0132"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shamse Tasnim Cynthia","raw_affiliation_strings":["University of Saskatchewan, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015470184","display_name":"Banani Roy","orcid":"https://orcid.org/0000-0003-1247-7781"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Banani Roy","raw_affiliation_strings":["University of Saskatchewan, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015544517","display_name":"Debajyoti Mondal","orcid":"https://orcid.org/0000-0002-7370-8697"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Debajyoti Mondal","raw_affiliation_strings":["University of Saskatchewan, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32625721"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9987999796867371,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9987000226974487,"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":0.7819139957427979},{"id":"https://openalex.org/keywords/software-regression","display_name":"Software regression","score":0.7679330110549927},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.7042493224143982},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.629795491695404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6056286692619324},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6022589802742004},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5874878764152527},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.551845908164978},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5113105773925781},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4848853051662445},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4817657470703125},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.47085991501808167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4646223485469818},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.44261792302131653},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4343249201774597},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.42007747292518616},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.3763166666030884},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12740939855575562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819139957427979},{"id":"https://openalex.org/C191727507","wikidata":"https://www.wikidata.org/wiki/Q24346","display_name":"Software regression","level":5,"score":0.7679330110549927},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.7042493224143982},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.629795491695404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6056286692619324},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6022589802742004},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5874878764152527},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.551845908164978},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5113105773925781},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4848853051662445},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4817657470703125},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.47085991501808167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4646223485469818},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.44261792302131653},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4343249201774597},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.42007747292518616},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3763166666030884},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12740939855575562},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511430.3511444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511430.3511444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"15th Innovations in Software Engineering Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W147281455","https://openalex.org/W1844386498","https://openalex.org/W1965709710","https://openalex.org/W1967320885","https://openalex.org/W1969728218","https://openalex.org/W1982147649","https://openalex.org/W2026750231","https://openalex.org/W2095321290","https://openalex.org/W2119169789","https://openalex.org/W2119821739","https://openalex.org/W2149423951","https://openalex.org/W2187089797","https://openalex.org/W2787986668","https://openalex.org/W2901523495","https://openalex.org/W2901830053","https://openalex.org/W2903658097","https://openalex.org/W2911964244","https://openalex.org/W2919518469","https://openalex.org/W2922601124","https://openalex.org/W2950911467","https://openalex.org/W2967758098","https://openalex.org/W2990200213","https://openalex.org/W3021198183","https://openalex.org/W3025029468","https://openalex.org/W3034060521","https://openalex.org/W3035303393","https://openalex.org/W3037686829","https://openalex.org/W3086800606","https://openalex.org/W3093575449","https://openalex.org/W3094704314","https://openalex.org/W3102659406","https://openalex.org/W3102725096","https://openalex.org/W3114793362","https://openalex.org/W3139075488","https://openalex.org/W4210964816","https://openalex.org/W4235354960","https://openalex.org/W6677480971"],"related_works":["https://openalex.org/W4293525103","https://openalex.org/W3200179079","https://openalex.org/W4224277717","https://openalex.org/W4385452144","https://openalex.org/W3006057552","https://openalex.org/W3196819515","https://openalex.org/W4352976596","https://openalex.org/W3188307501","https://openalex.org/W3125658235","https://openalex.org/W4293228314"],"abstract_inverted_index":{"Testing":[0],"software":[1,13,40,171],"is":[2,54],"considered":[3],"to":[4,36,56,175],"be":[5],"one":[6],"of":[7,24,31,62,110,168],"the":[8,59,73,80,103,132,137,147,176],"most":[9],"crucial":[10,55],"phases":[11],"in":[12,39,86,125,162],"development":[14],"life":[15],"cycle.":[16],"Software":[17],"bug":[18,88,98,145],"fixing":[19],"requires":[20],"a":[21,48,93,107,114,126],"significant":[22],"amount":[23],"time":[25],"and":[26,50,83,129,150],"effort.":[27],"A":[28],"rich":[29],"body":[30],"recent":[32],"research":[33],"explored":[34],"ways":[35],"predict":[37],"bugs":[38,120],"artifacts":[41],"using":[42,113,136],"machine":[43,64,133],"learning":[44,65,134],"based":[45],"techniques.":[46],"For":[47],"reliable":[49],"trustworthy":[51],"prediction,":[52],"it":[53],"also":[57],"consider":[58],"explainability":[60],"aspects":[61],"such":[63],"models.":[66,90],"In":[67,140],"this":[68],"paper,":[69],"we":[70],"show":[71],"how":[72],"feature":[74,157],"transformation":[75,109,158],"techniques":[76],"can":[77],"significantly":[78],"improve":[79],"prediction":[81,89,99],"accuracy":[82],"build":[84],"confidence":[85],"building":[87],"We":[91],"propose":[92],"novel":[94],"approach":[95],"for":[96],"improved":[97],"that":[100,117,155],"first":[101],"extracts":[102],"features,":[104],"then":[105],"finds":[106],"weighted":[108],"these":[111],"features":[112],"genetic":[115],"algorithm":[116],"best":[118],"separates":[119],"from":[121],"non-bugs":[122],"when":[123,173],"plotted":[124],"low-dimensional":[127],"space,":[128],"finally,":[130],"trains":[131],"model":[135],"transformed":[138],"dataset.":[139],"our":[141],"experiment":[142],"with":[143],"real-life":[144],"datasets,":[146],"random":[148],"forest":[149],"k-nearest":[151],"neighbor":[152],"classifier":[153],"models":[154,177],"leveraged":[156],"showed":[159],"4.25%":[160],"improvement":[161],"recall":[163],"values":[164],"on":[165,179],"an":[166],"average":[167],"over":[169],"8":[170],"systems":[172],"compared":[174],"built":[178],"original":[180],"data.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}