{"id":"https://openalex.org/W2768038010","doi":"https://doi.org/10.1109/access.2017.2771460","title":"Evaluating Data Filter on Cross-Project Defect Prediction: Comparison and Improvements","display_name":"Evaluating Data Filter on Cross-Project Defect Prediction: Comparison and Improvements","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2768038010","doi":"https://doi.org/10.1109/access.2017.2771460","mag":"2768038010"},"language":"en","primary_location":{"id":"doi:10.1109/access.2017.2771460","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2771460","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":null,"license_id":null,"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.2017.2771460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114911009","display_name":"Yong Li","orcid":"https://orcid.org/0000-0002-2281-5652"},"institutions":[{"id":"https://openalex.org/I1334729051","display_name":"Xinjiang Normal University","ror":"https://ror.org/00ndrvk93","country_code":"CN","type":"education","lineage":["https://openalex.org/I1334729051"]},{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","Data Security Key Laboratory, Xinjiang Normal University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-2281-5652","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Data Security Key Laboratory, Xinjiang Normal University, Urumqi, China","institution_ids":["https://openalex.org/I1334729051"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025184050","display_name":"Zhiqiu Huang","orcid":"https://orcid.org/0000-0001-6843-1892"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiu Huang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003067300","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0002-2719-1017"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2719-1017","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006153212","display_name":"Bingwu Fang","orcid":"https://orcid.org/0000-0002-5010-0611"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingwu Fang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":8.9283,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97825932,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"5","issue":null,"first_page":"25646","last_page":"25656"},"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":0.9980000257492065,"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":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.7714838981628418},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5980403423309326},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5831623077392578},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5561239123344421},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47702452540397644},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4681297540664673},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4394637942314148},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4192640781402588},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.3966488838195801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35439401865005493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7714838981628418},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5980403423309326},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5831623077392578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5561239123344421},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47702452540397644},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4681297540664673},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4394637942314148},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4192640781402588},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3966488838195801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35439401865005493},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2017.2771460","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2771460","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:265a0b5b6d7b495aa9e155ef6b892fff","is_oa":true,"landing_page_url":"https://doaj.org/article/265a0b5b6d7b495aa9e155ef6b892fff","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 5, Pp 25646-25656 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2017.2771460","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2771460","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1969570155","display_name":"\u591a\u6e90\u6570\u636e\u9a71\u52a8\u7684\u8f6f\u4ef6\u7f3a\u9677\u9884\u6d4b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61562087","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3263025281","display_name":null,"funder_award_id":"CXLX13_160","funder_id":"https://openalex.org/F4320335769","funder_display_name":"Graduate Research and Innovation Projects of Jiangsu Province"},{"id":"https://openalex.org/G7951788037","display_name":"\u7ef4\u543e\u5c14\u6587\u81ea\u7136\u573a\u666f\u6587\u672c\u68c0\u6d4b\u4e0e\u8bc6\u522b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61662082","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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/F4320335769","display_name":"Graduate Research and Innovation Projects of Jiangsu Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W168970045","https://openalex.org/W1663973292","https://openalex.org/W1964062576","https://openalex.org/W1964544799","https://openalex.org/W1989354793","https://openalex.org/W1994719586","https://openalex.org/W2008596407","https://openalex.org/W2010398592","https://openalex.org/W2012319196","https://openalex.org/W2025700486","https://openalex.org/W2029277954","https://openalex.org/W2036055923","https://openalex.org/W2046830558","https://openalex.org/W2050496630","https://openalex.org/W2062020999","https://openalex.org/W2066477694","https://openalex.org/W2078692096","https://openalex.org/W2081025867","https://openalex.org/W2084085041","https://openalex.org/W2090854192","https://openalex.org/W2094764356","https://openalex.org/W2099919734","https://openalex.org/W2101227285","https://openalex.org/W2104789242","https://openalex.org/W2105776892","https://openalex.org/W2118283821","https://openalex.org/W2119016061","https://openalex.org/W2120457925","https://openalex.org/W2122702470","https://openalex.org/W2127623179","https://openalex.org/W2136706100","https://openalex.org/W2137235241","https://openalex.org/W2138900513","https://openalex.org/W2151666086","https://openalex.org/W2160958420","https://openalex.org/W2165698076","https://openalex.org/W2167926541","https://openalex.org/W2312398278","https://openalex.org/W3141218678","https://openalex.org/W3141989311","https://openalex.org/W4212863985","https://openalex.org/W4238859253"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2394466068","https://openalex.org/W1987683558","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W2012353789","https://openalex.org/W2530420969"],"abstract_inverted_index":{"Cross-project":[0],"defect":[1,25,135,155],"prediction":[2,136],"(CPDP)":[3],"is":[4,60,67,81],"a":[5,10,46,92,114],"field":[6],"of":[7,48,55,78,87,105,133],"study":[8],"where":[9],"software":[11],"project":[12],"lacking":[13],"enough":[14],"local":[15],"data":[16,19,32,50,64,89,127,151,160],"can":[17,161],"use":[18,110],"from":[20,158],"other":[21],"projects":[22],"to":[23,82],"build":[24],"predictors.":[26],"To":[27],"support":[28,115],"CPDP,":[29],"the":[30,53,119,126,131,139,154,163],"cross-project":[31,134,159],"must":[33],"be":[34],"carefully":[35],"filtered":[36],"before":[37],"being":[38],"applied":[39],"locally.":[40],"Researchers":[41],"have":[42],"devised":[43,95],"and":[44,72,91,109,113,138],"implemented":[45],"plethora":[47],"various":[49],"filters":[51,90],"for":[52],"improvement":[54],"CPDP":[56],"performance.":[57],"However,":[58],"it":[59],"still":[61],"unclear":[62],"what":[63],"filter":[65,94,128,142,152],"strategy":[66,129],"most":[68],"effective,":[69],"both":[70],"generally":[71],"specifically,":[73],"in":[74,96],"CPDP.":[75],"The":[76,122],"objective":[77],"this":[79,97],"paper":[80],"provide":[83],"an":[84],"extensive":[85],"comparison":[86],"well-known":[88],"novel":[93],"paper.":[98],"We":[99],"perform":[100],"experiments":[101],"on":[102],"44":[103],"releases":[104],"14":[106],"open-source":[107],"projects,":[108],"Naive":[111],"Bayes":[112],"vector":[116],"machine":[117],"as":[118],"underlying":[120],"classifier.":[121],"results":[123],"demonstrate":[124],"that":[125],"improves":[130],"performance":[132],"significantly,":[137],"hierarchical":[140],"select-based":[141],"proposed":[143],"performs":[144],"significantly":[145],"better.":[146],"Moreover,":[147],"when":[148],"using":[149,167],"appropriate":[150],"strategy,":[153],"predictor":[156,164],"built":[157],"outperform":[162],"learned":[165],"by":[166],"within-project":[168],"data.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
