{"id":"https://openalex.org/W4399390121","doi":"https://doi.org/10.1007/s10515-024-00454-9","title":"Exploring the impact of data preprocessing techniques on composite classifier algorithms in cross-project defect prediction","display_name":"Exploring the impact of data preprocessing techniques on composite classifier algorithms in cross-project defect prediction","publication_year":2024,"publication_date":"2024-06-06","ids":{"openalex":"https://openalex.org/W4399390121","doi":"https://doi.org/10.1007/s10515-024-00454-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10515-024-00454-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10515-024-00454-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10515-024-00454-9.pdf","source":{"id":"https://openalex.org/S4210177399","display_name":"Automated Software Engineering","issn_l":"0928-8910","issn":["0928-8910","1573-7535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automated Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10515-024-00454-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007286541","display_name":"Andreea Ve\u0219can","orcid":"https://orcid.org/0000-0002-9049-5726"},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Andreea Vescan","raw_affiliation_strings":["Computer Science Department, Babes-Bolyai University, Cluj-Napoca, Cluj, Romania","Computer Science Department, Babes-Bolyai University, M. Kogalniceanu 1, 400084, Cluj-Napoca, Cluj, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Babes-Bolyai University, Cluj-Napoca, Cluj, Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Computer Science Department, Babes-Bolyai University, M. Kogalniceanu 1, 400084, Cluj-Napoca, Cluj, Romania","institution_ids":["https://openalex.org/I3125347698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026075190","display_name":"Radu G\u0103ceanu","orcid":"https://orcid.org/0000-0002-0977-4104"},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Radu G\u0103ceanu","raw_affiliation_strings":["Computer Science Department, Babes-Bolyai University, Cluj-Napoca, Cluj, Romania","Computer Science Department, Babes-Bolyai University, M. Kogalniceanu 1, 400084, Cluj-Napoca, Cluj, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Babes-Bolyai University, Cluj-Napoca, Cluj, Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Computer Science Department, Babes-Bolyai University, M. Kogalniceanu 1, 400084, Cluj-Napoca, Cluj, Romania","institution_ids":["https://openalex.org/I3125347698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082913216","display_name":"Camelia \u015eerban","orcid":"https://orcid.org/0000-0002-5741-2597"},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Camelia \u015eerban","raw_affiliation_strings":["Computer Science Department, Babes-Bolyai University, Cluj-Napoca, Cluj, Romania","Computer Science Department, Babes-Bolyai University, M. Kogalniceanu 1, 400084, Cluj-Napoca, Cluj, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Babes-Bolyai University, Cluj-Napoca, Cluj, Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Computer Science Department, Babes-Bolyai University, M. Kogalniceanu 1, 400084, Cluj-Napoca, Cluj, Romania","institution_ids":["https://openalex.org/I3125347698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007286541","https://openalex.org/A5026075190","https://openalex.org/A5082913216"],"corresponding_institution_ids":["https://openalex.org/I3125347698"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":1.9804,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89403522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"31","issue":"2","first_page":null,"last_page":null},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9972000122070312,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6620811820030212},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6050387620925903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.575927197933197},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.5182761549949646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4959166944026947},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.489229679107666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45212462544441223},{"id":"https://openalex.org/keywords/composite-number","display_name":"Composite number","score":0.44250592589378357},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38902372121810913},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3475918173789978},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32234621047973633}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6620811820030212},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6050387620925903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.575927197933197},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.5182761549949646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4959166944026947},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.489229679107666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45212462544441223},{"id":"https://openalex.org/C104779481","wikidata":"https://www.wikidata.org/wiki/Q50707","display_name":"Composite number","level":2,"score":0.44250592589378357},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38902372121810913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3475918173789978},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32234621047973633}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10515-024-00454-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10515-024-00454-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10515-024-00454-9.pdf","source":{"id":"https://openalex.org/S4210177399","display_name":"Automated Software Engineering","issn_l":"0928-8910","issn":["0928-8910","1573-7535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automated Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10515-024-00454-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10515-024-00454-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10515-024-00454-9.pdf","source":{"id":"https://openalex.org/S4210177399","display_name":"Automated Software Engineering","issn_l":"0928-8910","issn":["0928-8910","1573-7535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automated Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1278101024","display_name":null,"funder_award_id":"PN-III-P1-1.1-TE2021-0892","funder_id":"https://openalex.org/F4320318622","funder_display_name":"Ministerul Cercet\u0103rii, Inov\u0103rii \u015fi Digitaliz\u0103rii"}],"funders":[{"id":"https://openalex.org/F4320318622","display_name":"Ministerul Cercet\u0103rii, Inov\u0103rii \u015fi Digitaliz\u0103rii","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399390121.pdf"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1506481126","https://openalex.org/W1857789879","https://openalex.org/W1992345889","https://openalex.org/W2045320819","https://openalex.org/W2046830558","https://openalex.org/W2056020020","https://openalex.org/W2064161267","https://openalex.org/W2107323945","https://openalex.org/W2121866145","https://openalex.org/W2127623179","https://openalex.org/W2135093973","https://openalex.org/W2154343132","https://openalex.org/W2167846874","https://openalex.org/W2179438935","https://openalex.org/W2316564661","https://openalex.org/W2513147184","https://openalex.org/W2570224090","https://openalex.org/W2586292313","https://openalex.org/W2594132308","https://openalex.org/W2604254957","https://openalex.org/W2743316948","https://openalex.org/W2774137886","https://openalex.org/W2778343020","https://openalex.org/W2793567451","https://openalex.org/W2793681838","https://openalex.org/W2793779211","https://openalex.org/W2809203308","https://openalex.org/W2809385755","https://openalex.org/W2810961790","https://openalex.org/W2890548519","https://openalex.org/W2896871833","https://openalex.org/W2898435572","https://openalex.org/W2939917263","https://openalex.org/W2945699300","https://openalex.org/W2955438753","https://openalex.org/W2963124679","https://openalex.org/W2968017208","https://openalex.org/W2971269091","https://openalex.org/W2988881551","https://openalex.org/W2994638898","https://openalex.org/W3013019166","https://openalex.org/W3013707541","https://openalex.org/W3100297620","https://openalex.org/W3150137677","https://openalex.org/W3154474119","https://openalex.org/W3209490187","https://openalex.org/W3213259750","https://openalex.org/W4220904023","https://openalex.org/W4239808474","https://openalex.org/W4256546180"],"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":{"Abstract":[0],"Success":[1],"in":[2,75,163,190,201,208,214],"software":[3,20,34],"projects":[4],"is":[5,17,45,60,68,158,177,237],"now":[6],"an":[7],"important":[8],"challenge.":[9],"The":[10,62,126,138,205],"main":[11],"focus":[12],"of":[13,26,64,92,140,192,203,210],"the":[14,24,50,73,76,90,99,141,145,164,180,183,187,193,198,215,230,234],"engineering":[15],"community":[16],"to":[18,48,71,82,121],"predict":[19],"defects":[21],"based":[22],"on":[23],"history":[25],"classes":[27],"and":[28,80,96,111,132,134,195,223,251],"other":[29,84],"code":[30],"elements.":[31],"However,":[32],"these":[33],"defect":[35,58,87,124],"prediction":[36,51,59,88],"techniques":[37],"are":[38,113,167,172],"effective":[39],"only":[40],"as":[41,43],"long":[42],"there":[44],"enough":[46],"data":[47,151],"train":[49],"model.":[52],"To":[53],"mitigate":[54],"this":[55,65,103],"problem,":[56],"cross-project":[57,123],"used.":[61,114,178],"purpose":[63],"research":[66],"investigation":[67],"twofold:":[69],"first,":[70],"replicate":[72],"experiments":[74,127,143],"original":[77,146,165,181,235],"paper":[78,166],"proposal,":[79],"second,":[81],"investigate":[83],"settings":[85],"regarding":[86,98],"with":[89],"aim":[91],"providing":[93],"new":[94],"insights":[95],"results":[97,139,161,171,207,228,247],"best":[100,188,199,218],"approach.":[101],"In":[102,179],"study,":[104],"three":[105,154],"composite":[106],"algorithms,":[107],"namely":[108],"AvgVoting,":[109],"MaxVoting":[110,184],"Bagging":[112],"These":[115],"algorithms":[116],"integrate":[117],"multiple":[118],"machine":[119],"classifiers":[120],"improve":[122],"prediction.":[125],"use":[128],"pre-processed":[129],"methods":[130],"(normalization":[131],"standardization)":[133],"also":[135],"feature":[136,175,252],"selection.":[137,253],"replicated":[142],"confirm":[144],"findings":[147],"when":[148,174,239,248],"using":[149,240,249],"raw":[150,241],"for":[152],"all":[153],"methods.":[155],"When":[156],"normalization":[157],"applied,":[159],"better":[160,170,246],"than":[162],"obtained.":[168],"Even":[169],"obtained":[173,213,232,245],"selection":[176],"paper,":[182],"approach":[185],"shows":[186,197],"performance":[189,200],"terms":[191,202,209],"F-measure,":[194],"BaggingJ48":[196],"cost-effectiveness.":[204],"same":[206],"F-measure":[211],"were":[212],"current":[216],"experiments:":[217],"MaxVoting,":[219],"followed":[220],"by":[221,225],"AvgVoting":[222],"then":[224],"BaggingJ48.":[226],"Our":[227],"emphasize":[229],"previously":[231],"outcome;":[233],"study":[236],"confirmed":[238],"data.":[242],"Moreover,":[243],"we":[244],"preprocessing":[250]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}