{"id":"https://openalex.org/W2295673959","doi":"https://doi.org/10.1109/tr.2015.2461676","title":"Empirical Studies of a Two-Stage Data Preprocessing Approach for Software Fault Prediction","display_name":"Empirical Studies of a Two-Stage Data Preprocessing Approach for Software Fault Prediction","publication_year":2015,"publication_date":"2015-08-13","ids":{"openalex":"https://openalex.org/W2295673959","doi":"https://doi.org/10.1109/tr.2015.2461676","mag":"2295673959"},"language":"en","primary_location":{"id":"doi:10.1109/tr.2015.2461676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2015.2461676","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Reliability","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/A5013668456","display_name":"Wangshu Liu","orcid":"https://orcid.org/0000-0001-8862-0690"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wangshu Liu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056982862","display_name":"Shulong Liu","orcid":"https://orcid.org/0000-0002-3496-5113"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulong Liu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061025205","display_name":"Qing Gu","orcid":"https://orcid.org/0000-0002-1112-790X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Gu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078773589","display_name":"Jiaqiang Chen","orcid":"https://orcid.org/0000-0002-8031-3079"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqiang Chen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441911","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0002-1180-3891"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["School of Computer Science and Technology, Nantong University, Nantong, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112771285","display_name":"Daoxu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daoxu Chen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5013668456"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":25.4829,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.99419281,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"65","issue":"1","first_page":"38","last_page":"53"},"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":0.9994000196456909,"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":0.9983999729156494,"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":0.7360248565673828},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7118268013000488},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6236329674720764},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5998498201370239},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5828300714492798},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5179558992385864},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4848093092441559},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4823855459690094},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.47802719473838806},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.466174840927124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43457892537117004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4244476556777954},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.26174312829971313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360248565673828},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7118268013000488},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6236329674720764},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5998498201370239},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5828300714492798},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5179558992385864},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4848093092441559},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4823855459690094},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.47802719473838806},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.466174840927124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43457892537117004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4244476556777954},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.26174312829971313},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tr.2015.2461676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2015.2461676","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Reliability","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3678090145","display_name":null,"funder_award_id":"61373012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3679381194","display_name":null,"funder_award_id":"61202006)","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6667581590","display_name":null,"funder_award_id":"61321491","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7434031079","display_name":null,"funder_award_id":"91218302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8189926395","display_name":null,"funder_award_id":"2009CB320705)","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1491307969","https://openalex.org/W1491675663","https://openalex.org/W1504694836","https://openalex.org/W1505753439","https://openalex.org/W1560107318","https://openalex.org/W1565746575","https://openalex.org/W1570448133","https://openalex.org/W1661871015","https://openalex.org/W1808644423","https://openalex.org/W1969483024","https://openalex.org/W1970789984","https://openalex.org/W1978859404","https://openalex.org/W1984111870","https://openalex.org/W1991622368","https://openalex.org/W1998259093","https://openalex.org/W2016944307","https://openalex.org/W2027902860","https://openalex.org/W2031812206","https://openalex.org/W2033418259","https://openalex.org/W2037691959","https://openalex.org/W2040900804","https://openalex.org/W2043683548","https://openalex.org/W2046830558","https://openalex.org/W2048832497","https://openalex.org/W2050496630","https://openalex.org/W2060074204","https://openalex.org/W2061019658","https://openalex.org/W2062020999","https://openalex.org/W2066477694","https://openalex.org/W2068430427","https://openalex.org/W2074805796","https://openalex.org/W2080521990","https://openalex.org/W2081025867","https://openalex.org/W2086095861","https://openalex.org/W2096945460","https://openalex.org/W2097883090","https://openalex.org/W2098340665","https://openalex.org/W2104329051","https://openalex.org/W2105776892","https://openalex.org/W2107323945","https://openalex.org/W2111421634","https://openalex.org/W2112658968","https://openalex.org/W2118283821","https://openalex.org/W2118978333","https://openalex.org/W2119683921","https://openalex.org/W2120457925","https://openalex.org/W2122702470","https://openalex.org/W2123704085","https://openalex.org/W2123977051","https://openalex.org/W2125055259","https://openalex.org/W2132887549","https://openalex.org/W2134086158","https://openalex.org/W2139749383","https://openalex.org/W2142481192","https://openalex.org/W2145793758","https://openalex.org/W2149783794","https://openalex.org/W2150874999","https://openalex.org/W2151666086","https://openalex.org/W2153745044","https://openalex.org/W2156571267","https://openalex.org/W2158698691","https://openalex.org/W2160958420","https://openalex.org/W2164627280","https://openalex.org/W2171095014","https://openalex.org/W2172232422","https://openalex.org/W2190423096","https://openalex.org/W2408181256","https://openalex.org/W2432517183","https://openalex.org/W3141218678","https://openalex.org/W3141989311","https://openalex.org/W4206600618","https://openalex.org/W4234346598","https://openalex.org/W4238859253","https://openalex.org/W6633497745","https://openalex.org/W6636914306","https://openalex.org/W6678797503","https://openalex.org/W6682904970","https://openalex.org/W6687537609"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Software":[0],"fault":[1,26],"prediction":[2],"is":[3,18],"a":[4,60,88,165],"valuable":[5],"exercise":[6],"in":[7,75,151],"software":[8,25,40,128],"quality":[9,52],"assurance":[10],"to":[11,97,110],"best":[12],"allocate":[13],"limited":[14],"testing":[15],"resources.":[16],"Classification":[17],"one":[19],"of":[20,46,53,160],"the":[21,35,44,47,51,76,102,112,115,148,158],"effective":[22],"methods":[23],"for":[24,167],"prediction.":[27],"The":[28,154],"classification":[29],"models":[30,48],"are":[31],"trained":[32],"based":[33],"on":[34,50],"datasets":[36,125],"obtained":[37],"by":[38],"mining":[39],"historical":[41],"repositories.":[42],"However,":[43],"performance":[45],"depends":[49],"datasets.":[54],"In":[55,101,120],"this":[56],"paper,":[57],"we":[58,80,106,123,136],"propose":[59,87],"novel":[61,93],"two-stage":[62,175],"data":[63,170],"preprocessing":[64,171],"approach":[65,139],"which":[66],"incorporates":[67],"both":[68],"feature":[69,77],"selection":[70,78],"and":[71,85,117,133,145,163],"instance":[72,103],"reduction.":[73],"Specifically,":[74],"stage,":[79,105],"first":[81],"perform":[82],"relevance":[83],"analysis,":[84],"then":[86],"threshold-based":[89,94],"clustering":[90,95],"method,":[91],"called":[92],"algorithm,":[96],"conduct":[98],"redundancy":[99],"control.":[100],"reduction":[104],"apply":[107],"random":[108],"under-sampling":[109],"keep":[111],"balance":[113],"between":[114],"faulty":[116],"non-faulty":[118],"instances.":[119],"empirical":[121],"studies,":[122],"chose":[124],"from":[126],"real-world":[127],"projects,":[129],"such":[130],"as":[131],"Eclipse":[132],"NASA.":[134],"Then":[135],"compared":[137],"our":[138,152,161,174],"with":[140],"some":[141],"classical":[142],"baseline":[143],"methods,":[144],"further":[146],"investigated":[147],"influencing":[149],"factors":[150],"approach.":[153,176],"final":[155],"results":[156],"demonstrate":[157],"effectiveness":[159],"approach,":[162],"provide":[164],"guideline":[166],"achieving":[168],"cost-effective":[169],"when":[172],"using":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}