{"id":"https://openalex.org/W3138904555","doi":"https://doi.org/10.1109/tse.2021.3079841","title":"On the Value of Oversampling for Deep Learning in Software Defect Prediction","display_name":"On the Value of Oversampling for Deep Learning in Software Defect Prediction","publication_year":2021,"publication_date":"2021-05-12","ids":{"openalex":"https://openalex.org/W3138904555","doi":"https://doi.org/10.1109/tse.2021.3079841","mag":"3138904555"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2021.3079841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2021.3079841","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.03835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056240329","display_name":"Rahul Yedida","orcid":"https://orcid.org/0000-0003-2069-5949"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Yedida","raw_affiliation_strings":["Department of Computer Science, North Carolina State University, Raleigh, NC, USA","North Carolina State University ,"],"raw_orcid":"https://orcid.org/0000-0003-2069-5949","affiliations":[{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University ,","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077008083","display_name":"Tim Menzies","orcid":"https://orcid.org/0000-0002-5040-3196"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Menzies","raw_affiliation_strings":["Department of Computer Science, North Carolina State University, Raleigh, NC, USA","Computer Science, North Carolina State University College of Engineering, 242510 Raleigh, North Carolina, United States, 27695-7901 (e-mail: timm@ieee.org)"],"raw_orcid":"https://orcid.org/0000-0002-5040-3196","affiliations":[{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Computer Science, North Carolina State University College of Engineering, 242510 Raleigh, North Carolina, United States, 27695-7901 (e-mail: timm@ieee.org)","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.8503,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7854983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"48","issue":"8","first_page":"3103","last_page":"3116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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":0.9955000281333923,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9898999929428101,"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/oversampling","display_name":"Oversampling","score":0.9421062469482422},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7461017966270447},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.7282009124755859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7162426114082336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.695126473903656},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6693549156188965},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6157850623130798},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5534845590591431},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5532073378562927},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5077189207077026},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44799110293388367},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3758941888809204},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3478793203830719},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1920369565486908}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9421062469482422},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7461017966270447},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.7282009124755859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7162426114082336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695126473903656},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6693549156188965},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6157850623130798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5534845590591431},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5532073378562927},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5077189207077026},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44799110293388367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3758941888809204},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3478793203830719},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1920369565486908},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tse.2021.3079841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2021.3079841","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2008.03835","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03835","pdf_url":"https://arxiv.org/pdf/2008.03835","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3138904555","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.03835.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.03835","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.03835","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.03835","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03835","pdf_url":"https://arxiv.org/pdf/2008.03835","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1769683952","display_name":null,"funder_award_id":"CCF-1703487","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W6681031","https://openalex.org/W203932818","https://openalex.org/W1498436455","https://openalex.org/W1507777432","https://openalex.org/W1560107318","https://openalex.org/W1665214252","https://openalex.org/W1849277567","https://openalex.org/W1953529280","https://openalex.org/W1964962870","https://openalex.org/W1973445088","https://openalex.org/W2005504865","https://openalex.org/W2024352272","https://openalex.org/W2088558968","https://openalex.org/W2105511939","https://openalex.org/W2106411961","https://openalex.org/W2109676405","https://openalex.org/W2111421634","https://openalex.org/W2113207845","https://openalex.org/W2126598020","https://openalex.org/W2133227149","https://openalex.org/W2133711389","https://openalex.org/W2137235241","https://openalex.org/W2138428785","https://openalex.org/W2148143831","https://openalex.org/W2158864412","https://openalex.org/W2161388792","https://openalex.org/W2163837601","https://openalex.org/W2167363007","https://openalex.org/W2260550436","https://openalex.org/W2338571852","https://openalex.org/W2344072768","https://openalex.org/W2360967250","https://openalex.org/W2402619042","https://openalex.org/W2511803001","https://openalex.org/W2617227509","https://openalex.org/W2618735982","https://openalex.org/W2619465136","https://openalex.org/W2753715782","https://openalex.org/W2767106145","https://openalex.org/W2767521898","https://openalex.org/W2767717989","https://openalex.org/W2767852858","https://openalex.org/W2781474777","https://openalex.org/W2794607770","https://openalex.org/W2795013017","https://openalex.org/W2802049774","https://openalex.org/W2809090039","https://openalex.org/W2809254203","https://openalex.org/W2896224010","https://openalex.org/W2898124301","https://openalex.org/W2898435572","https://openalex.org/W2899171197","https://openalex.org/W2911831256","https://openalex.org/W2914608582","https://openalex.org/W2921565836","https://openalex.org/W2949266019","https://openalex.org/W2954149564","https://openalex.org/W2954903132","https://openalex.org/W2955230520","https://openalex.org/W2955991060","https://openalex.org/W2963351448","https://openalex.org/W2963640412","https://openalex.org/W2994130976","https://openalex.org/W3015923933","https://openalex.org/W3049429073","https://openalex.org/W3098598077","https://openalex.org/W3169336656","https://openalex.org/W4250023757","https://openalex.org/W6600259872","https://openalex.org/W6608286391","https://openalex.org/W6637242042","https://openalex.org/W6676179485","https://openalex.org/W6677088747","https://openalex.org/W6679740073","https://openalex.org/W6725533135","https://openalex.org/W6745148249","https://openalex.org/W6747227044","https://openalex.org/W6751512867","https://openalex.org/W6771097827"],"related_works":["https://openalex.org/W3161746459","https://openalex.org/W3047644063","https://openalex.org/W3212111403","https://openalex.org/W3121926098","https://openalex.org/W2914103415","https://openalex.org/W3157699413","https://openalex.org/W1980201834","https://openalex.org/W2056750472","https://openalex.org/W2994099454","https://openalex.org/W2962911862","https://openalex.org/W2950081799","https://openalex.org/W3012089510","https://openalex.org/W3032307374","https://openalex.org/W3007351208","https://openalex.org/W2809182263","https://openalex.org/W3213485676","https://openalex.org/W3095787923","https://openalex.org/W3128563065","https://openalex.org/W3011626867","https://openalex.org/W3113192049"],"abstract_inverted_index":{"One":[0],"truism":[1,46],"of":[2,16,36,64,87,113],"deep":[3,37,102,118],"learning":[4,38,119],"is":[5,47],"that":[6,44,45],"the":[7,13,33,83,88,111],"automatic":[8],"feature":[9,26],"engineering":[10,27],"(seen":[11],"in":[12,90],"first":[14],"layers":[15],"those":[17],"networks)":[18],"excuses":[19],"data":[20,53,93],"scientists":[21],"from":[22],"performing":[23],"tedious":[24],"manual":[25],"prior":[28,84,115],"to":[29,116],"running":[30],"DL.":[31],"For":[32],"specific":[34],"case":[35,109],"for":[39,73,110],"defect":[40,92,122],"prediction,":[41],"we":[42,51,77],"show":[43],"false.":[48],"Specifically,":[49],"when":[50],"pre-process":[52],"with":[54],"a":[55,65,107],"novel":[56],"oversampling":[57,114],"technique":[58],"called":[59,68],"fuzzy":[60],"sampling,":[61],"as":[62],"part":[63],"larger":[66],"pipeline":[67],"GHOST":[69],"(Goal-oriented":[70],"Hyper-parameter":[71],"Optimization":[72],"Scalable":[74],"Training),":[75],"then":[76],"can":[78],"do":[79],"significantly":[80,100],"better":[81],"than":[82],"DL":[85],"state":[86],"art":[89],"14/20":[91],"sets.":[94],"Our":[95],"approach":[96],"yields":[97],"state-of-the-art":[98],"results":[99,105],"faster":[101],"learners.":[103],"These":[104],"present":[106],"cogent":[108],"use":[112],"applying":[117],"on":[120],"software":[121],"prediction":[123],"datasets.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}