{"id":"https://openalex.org/W2980281552","doi":"https://doi.org/10.1109/access.2019.2945858","title":"Tackling Class Imbalance Problem in Software Defect Prediction Through Cluster-Based Over-Sampling With Filtering","display_name":"Tackling Class Imbalance Problem in Software Defect Prediction Through Cluster-Based Over-Sampling With Filtering","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2980281552","doi":"https://doi.org/10.1109/access.2019.2945858","mag":"2980281552"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2945858","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2945858","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2019.2945858","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027202117","display_name":"Lina Gong","orcid":"https://orcid.org/0000-0002-5272-6706"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Gong","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","Mine Digitization Engineering Research Center of Ministry of Education, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5272-6706","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"Mine Digitization Engineering Research Center of Ministry of Education, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002351235","display_name":"Shujuan Jiang","orcid":"https://orcid.org/0000-0003-0643-0565"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujuan Jiang","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","Mine Digitization Engineering Research Center of Ministry of Education, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0643-0565","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"Mine Digitization Engineering Research Center of Ministry of Education, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102889918","display_name":"Li Jiang","orcid":"https://orcid.org/0000-0003-1314-4735"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","Mine Digitization Engineering Research Center of Ministry of Education, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"Mine Digitization Engineering Research Center of Ministry of Education, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":9.222,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.97813851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"145725","last_page":"145737"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9923999905586243,"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":0.9839000105857849,"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":0.7388994693756104},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6493113040924072},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6208028197288513},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6193792819976807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5164594650268555},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5068731904029846},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5024497509002686},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.47136297821998596},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4659344553947449},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46153295040130615},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4534570574760437},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4381101429462433},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.42093223333358765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3543359935283661},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3351389765739441}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388994693756104},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6493113040924072},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6208028197288513},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6193792819976807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5164594650268555},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5068731904029846},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5024497509002686},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.47136297821998596},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4659344553947449},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46153295040130615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4534570574760437},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4381101429462433},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.42093223333358765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3543359935283661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3351389765739441},{"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/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2945858","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2945858","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:41677458655e4b57bda29dfcca319bfc","is_oa":true,"landing_page_url":"https://doaj.org/article/41677458655e4b57bda29dfcca319bfc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 145725-145737 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2945858","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2945858","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2349992327","display_name":null,"funder_award_id":"2019BSCX28","funder_id":"https://openalex.org/F4320321392","funder_display_name":"Northwestern Polytechnical University"}],"funders":[{"id":"https://openalex.org/F4320321392","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1533970595","https://openalex.org/W1574715085","https://openalex.org/W1576442155","https://openalex.org/W1581797854","https://openalex.org/W1592804209","https://openalex.org/W1603574869","https://openalex.org/W1818898085","https://openalex.org/W1966359730","https://openalex.org/W1974647637","https://openalex.org/W1988790447","https://openalex.org/W2022477494","https://openalex.org/W2026750231","https://openalex.org/W2031770898","https://openalex.org/W2037691959","https://openalex.org/W2040900804","https://openalex.org/W2056601071","https://openalex.org/W2065547122","https://openalex.org/W2068430427","https://openalex.org/W2087240369","https://openalex.org/W2096945460","https://openalex.org/W2097883090","https://openalex.org/W2101227285","https://openalex.org/W2103715428","https://openalex.org/W2104933073","https://openalex.org/W2107138773","https://openalex.org/W2120457925","https://openalex.org/W2125999269","https://openalex.org/W2132791018","https://openalex.org/W2143637886","https://openalex.org/W2145793758","https://openalex.org/W2146338950","https://openalex.org/W2148143831","https://openalex.org/W2160958420","https://openalex.org/W2164873210","https://openalex.org/W2168453597","https://openalex.org/W2172232422","https://openalex.org/W2181965785","https://openalex.org/W2338006743","https://openalex.org/W2543851504","https://openalex.org/W2735995639","https://openalex.org/W2743749501","https://openalex.org/W2766296277","https://openalex.org/W2808595449","https://openalex.org/W2963520355","https://openalex.org/W2963548617","https://openalex.org/W3141989311","https://openalex.org/W4238859253","https://openalex.org/W4245807786","https://openalex.org/W4285719527","https://openalex.org/W6631885290","https://openalex.org/W6634357899","https://openalex.org/W6635892212","https://openalex.org/W6638442771","https://openalex.org/W6675634716","https://openalex.org/W6685986551"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W4206637278","https://openalex.org/W4386005305","https://openalex.org/W3082051559","https://openalex.org/W4386214543","https://openalex.org/W1969988626","https://openalex.org/W2141301039","https://openalex.org/W3173198409","https://openalex.org/W2152863486"],"abstract_inverted_index":{"In":[0],"practice,":[1],"Software":[2],"Defect":[3],"Prediction":[4],"(SDP)":[5],"models":[6],"often":[7],"suffer":[8],"from":[9],"highly":[10],"imbalanced":[11],"data,":[12],"which":[13],"makes":[14],"classifiers":[15],"difficult":[16],"to":[17,26,39,89,144,156,231],"identify":[18],"defective":[19,50,57,99,104,120,129],"instances.":[20,58,148],"Recently,":[21],"many":[22,68],"techniques":[23],"were":[24],"proposed":[25],"tackle":[27,90],"this":[28,134],"problem,":[29],"over-sampling":[30,136,161,169,218],"technique":[31,45],"is":[32,227],"one":[33],"of":[34,49,112,128,241],"the":[35,47,73,126,138,146,189,239],"most":[36],"well-known":[37],"methods":[38,200,219],"address":[40],"class":[41,91],"imbalance":[42,92],"problem.":[43],"This":[44],"balances":[46],"number":[48],"and":[51,67,102,179,205,220,237],"non-defective":[52],"instances":[53,71,100,105,111,121],"by":[54,77,108],"generating":[55],"new":[56,103,119],"However,":[59],"these":[60,118],"approaches":[61,162],"would":[62,122],"generate":[63,232],"non-diverse":[64],"synthetic":[65],"instances,":[66],"unnecessary":[69],"noise":[70,85,147],"at":[72],"same":[74,190],"time.":[75],"Motived":[76],"this,":[78,117],"we":[79,132,192],"propose":[80],"a":[81],"Cluster-based":[82],"Over-sampling":[83],"with":[84,159,196],"filtering":[86],"(KMFOS)":[87],"approach":[88,230],"problem":[93],"in":[94,125],"SDP.":[95],"KMFOS":[96,158,195,212,226],"firstly":[97],"divides":[98],"into$K$clusters,":[101],"are":[106],"generated":[107],"interpolation":[109],"between":[110],"each":[113],"two":[114],"clusters.":[115],"After":[116],"diversely":[123],"spread":[124],"space":[127],"dataset.":[130],"Then,":[131],"extend":[133],"cluster-based":[135],"through":[137],"Closest":[139],"List":[140],"Noise":[141],"Identification":[142],"(CLNI)":[143],"clean":[145],"We":[149],"do":[150],"extensive":[151],"experiments":[152],"on":[153],"24":[154],"projects":[155],"compare":[157,194],"some":[160],"such":[163],"as":[164],"SMOTE,":[165,172],"Borderline-SMOTE,":[166],"ADASYN,":[167],"random":[168],"(ROS),":[170],"K-means":[171],"SMOTE":[173,176,180],"+":[174,177,181],"IPF,":[175],"ENN":[178],"Tomek":[182],"Links":[183],"using":[184],"five":[185],"prediction":[186],"classifiers.":[187],"At":[188],"time,":[191],"also":[193],"other":[197,217,221],"state-of-the-art":[198],"class-imbalance":[199,223],"including":[201],"balancebaggingclassifier,":[202],"RUSboostclassifier,":[203],"InstanceHardnessThreshold":[204],"cost-sensitive":[206],"methods.":[207,224],"Experimental":[208],"results":[209],"indicate":[210],"our":[211],"can":[213],"obtain":[214],"betterRecallandbalvalues":[215],"than":[216],"compared":[222],"Hence,":[225],"an":[228],"efficient":[229],"balanced":[233],"data":[234],"for":[235],"SDP":[236],"improves":[238],"performance":[240],"predicting":[242],"models.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}