{"id":"https://openalex.org/W4400733155","doi":"https://doi.org/10.11591/ijai.v13.i3.pp2987-2998","title":"A three-step combination strategy for addressing outliers and class imbalance in software defect prediction","display_name":"A three-step combination strategy for addressing outliers and class imbalance in software defect prediction","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4400733155","doi":"https://doi.org/10.11591/ijai.v13.i3.pp2987-2998"},"language":"en","primary_location":{"id":"doi:10.11591/ijai.v13.i3.pp2987-2998","doi":"https://doi.org/10.11591/ijai.v13.i3.pp2987-2998","is_oa":true,"landing_page_url":"http://dx.doi.org/10.11591/ijai.v13.i3.pp2987-2998","pdf_url":"https://ijai.iaescore.com/index.php/IJAI/article/download/25002/14108","source":{"id":"https://openalex.org/S2764408626","display_name":"IAES International Journal of Artificial Intelligence","issn_l":"2089-4872","issn":["2089-4872","2252-8938"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IAES International Journal of Artificial Intelligence (IJ-AI)","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ijai.iaescore.com/index.php/IJAI/article/download/25002/14108","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017244994","display_name":"Muhammad Rizky Pribadi","orcid":"https://orcid.org/0000-0001-7440-9667","observed_orcids":["https://orcid.org/0000-0001-7440-9667"]},"institutions":[{"id":"https://openalex.org/I4392021167","display_name":"Universitas Multi Data Palembang","ror":"https://ror.org/04mv64y65","country_code":"ID","type":"education","lineage":["https://openalex.org/I4392021167"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Muhammad Rizky Pribadi","raw_affiliation_strings":["Universitas Multi Data Palembang"],"raw_orcid":"https://orcid.org/0000-0001-7440-9667","affiliations":[{"raw_affiliation_string":"Universitas Multi Data Palembang","institution_ids":["https://openalex.org/I4392021167"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046569780","display_name":"Hindriyanto Dwi Purnomo","orcid":"https://orcid.org/0000-0001-6728-7868","observed_orcids":["https://orcid.org/0000-0001-6728-7868"]},"institutions":[{"id":"https://openalex.org/I157219812","display_name":"Satya Wacana Christian University","ror":"https://ror.org/009nnre75","country_code":"ID","type":"education","lineage":["https://openalex.org/I157219812"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Hindriyanto Dwi Purnomo","raw_affiliation_strings":["Satya Wacana Christian University"],"raw_orcid":"https://orcid.org/0000-0001-6728-7868","affiliations":[{"raw_affiliation_string":"Satya Wacana Christian University","institution_ids":["https://openalex.org/I157219812"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039332919","display_name":"Hendry Hendry","orcid":"https://orcid.org/0000-0002-7387-2622","observed_orcids":["https://orcid.org/0000-0002-7387-2622"]},"institutions":[{"id":"https://openalex.org/I157219812","display_name":"Satya Wacana Christian University","ror":"https://ror.org/009nnre75","country_code":"ID","type":"education","lineage":["https://openalex.org/I157219812"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Hendry Hendry","raw_affiliation_strings":["Satya Wacana Christian University"],"raw_orcid":"https://orcid.org/0000-0002-7387-2622","affiliations":[{"raw_affiliation_string":"Satya Wacana Christian University","institution_ids":["https://openalex.org/I157219812"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5275,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6234998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"13","issue":"3","first_page":"2987","last_page":"2987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9911999702453613,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9911999702453613,"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/T10260","display_name":"Software Engineering Research","score":0.006599999964237213,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0007999999797903001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/software-defect-prediction","display_name":"software defect prediction","score":1.0},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.9629999995231628},{"id":"https://openalex.org/keywords/minority-class","display_name":"minority class","score":0.5509999990463257},{"id":"https://openalex.org/keywords/smote","display_name":"SMOTE","score":0.7490000128746033},{"id":"https://openalex.org/keywords/synthetic-minority-samples","display_name":"synthetic minority samples","score":0.7080000042915344},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.8759999871253967},{"id":"https://openalex.org/keywords/oversampling","display_name":"oversampling","score":0.9269999861717224},{"id":"https://openalex.org/keywords/imbalanced-learning","display_name":"imbalanced learning","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9162110090255737},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7841355800628662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767890453338623},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6134000420570374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5600970983505249},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5472509264945984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5464467406272888},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46683159470558167},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45014363527297974},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4219067394733429},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37184518575668335},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.11214625835418701},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.11591/ijai.v13.i3.pp2987-2998","doi":"https://doi.org/10.11591/ijai.v13.i3.pp2987-2998","is_oa":true,"landing_page_url":"http://dx.doi.org/10.11591/ijai.v13.i3.pp2987-2998","pdf_url":"https://ijai.iaescore.com/index.php/IJAI/article/download/25002/14108","source":{"id":"https://openalex.org/S2764408626","display_name":"IAES International Journal of Artificial Intelligence","issn_l":"2089-4872","issn":["2089-4872","2252-8938"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IAES International Journal of Artificial Intelligence (IJ-AI)","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.11591/ijai.v13.i3.pp2987-2998","doi":"https://doi.org/10.11591/ijai.v13.i3.pp2987-2998","is_oa":true,"landing_page_url":"http://dx.doi.org/10.11591/ijai.v13.i3.pp2987-2998","pdf_url":"https://ijai.iaescore.com/index.php/IJAI/article/download/25002/14108","source":{"id":"https://openalex.org/S2764408626","display_name":"IAES International Journal of Artificial Intelligence","issn_l":"2089-4872","issn":["2089-4872","2252-8938"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IAES International Journal of Artificial Intelligence (IJ-AI)","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400733155.pdf","grobid_xml":"https://content.openalex.org/works/W4400733155.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2098063110","https://openalex.org/W2101807845","https://openalex.org/W2148143831","https://openalex.org/W2523268328","https://openalex.org/W2586292313","https://openalex.org/W2604881091","https://openalex.org/W2756182389","https://openalex.org/W2766296277","https://openalex.org/W2808595449","https://openalex.org/W2947615792","https://openalex.org/W2994099454","https://openalex.org/W2999309192","https://openalex.org/W3006252432","https://openalex.org/W3088828278","https://openalex.org/W3105012514","https://openalex.org/W3109072952","https://openalex.org/W3117098906","https://openalex.org/W3127988644","https://openalex.org/W3134574975","https://openalex.org/W3135880764","https://openalex.org/W3136410796","https://openalex.org/W3153214111","https://openalex.org/W3156712279","https://openalex.org/W3163694685","https://openalex.org/W3173198409","https://openalex.org/W3174740339","https://openalex.org/W3175845646","https://openalex.org/W3203201894","https://openalex.org/W4221057950","https://openalex.org/W4253461361","https://openalex.org/W4292170267","https://openalex.org/W4293242646","https://openalex.org/W4302287551","https://openalex.org/W4308386860","https://openalex.org/W4309263396","https://openalex.org/W4320016010","https://openalex.org/W4377104366","https://openalex.org/W4377704482"],"related_works":["https://openalex.org/W4415760634","https://openalex.org/W4288774554","https://openalex.org/W4407929715","https://openalex.org/W7163550916","https://openalex.org/W4414638338","https://openalex.org/W4310720697","https://openalex.org/W4206403383","https://openalex.org/W4245807786","https://openalex.org/W3009421588","https://openalex.org/W4387434018"],"abstract_inverted_index":{"Software":[0],"defect":[1],"prediction":[2],"often":[3],"involves":[4],"datasets":[5],"with":[6,87],"imbalanced":[7,59,110],"distributions":[8],"where":[9],"one":[10],"or":[11],"more":[12],"classes":[13,24],"are":[14,25,75],"underrepresented,":[15],"referred":[16],"to":[17,43,57,81,92,117,131,142,152,159,182],"as":[18,28],"the":[19,29,39,46,71,126,133,138,154,160],"minority":[20,40,48,67,97],"class,":[21,41],"while":[22],"other":[23],"overrepresented,":[26],"known":[27],"majority":[30,72],"class.":[31],"This":[32,78],"imbalance":[33],"can":[34,63],"hinder":[35],"accurate":[36],"predictions":[37],"of":[38,119],"leading":[42],"misclassification.":[44],"While":[45],"synthetic":[47,66,96],"oversampling":[49,124],"technique":[50],"(SMOTE)":[51],"is":[52,106,115],"a":[53],"widely":[54],"used":[55],"approach":[56],"address":[58],"learning":[60],"data,":[61],"it":[62,86,136,158],"inadvertently":[64],"generate":[65],"samples":[68],"that":[69,118,167],"resemble":[70],"class":[73],"and":[74,112,144,175],"considered":[76],"outliers.":[77,146],"study":[79],"aims":[80],"enhance":[82],"SMOTE":[83,130,150],"by":[84],"integrating":[85],"an":[88,109],"efficient":[89],"algorithm":[90,141],"designed":[91],"identify":[93],"outliers":[94,104],"among":[95],"samples.":[98],"The":[99,163],"resulting":[100],"method,":[101],"called":[102],"reduced":[103],"(RO)-SMOTE,":[105],"evaluated":[107],"using":[108,129],"dataset,":[111],"its":[113],"performance":[114],"compared":[116,181],"SMOTE.":[120,183],"RO-SMOTE":[121,148,168],"first":[122],"performs":[123],"on":[125],"training":[127],"data":[128],"balance":[132],"dataset.":[134],"Next,":[135],"applies":[137,149],"mining":[139],"outlier":[140],"detect":[143],"eliminate":[145],"Finally,":[147],"again":[151],"rebalance":[153],"dataset":[155],"before":[156],"introducing":[157],"underlying":[161],"classifier.":[162],"experimental":[164],"results":[165],"demonstrate":[166],"achieves":[169],"higher":[170],"accuracy,":[171],"precision,":[172],"recall,":[173],"F1-score,":[174],"area":[176],"under":[177],"curve":[178],"(AUC)":[179],"values":[180]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-07-18T00:00:00"}