{"id":"https://openalex.org/W2790044077","doi":"https://doi.org/10.1109/apsec.2017.76","title":"Impact of the Distribution Parameter of Data Sampling Approaches on Software Defect Prediction Models","display_name":"Impact of the Distribution Parameter of Data Sampling Approaches on Software Defect Prediction Models","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2790044077","doi":"https://doi.org/10.1109/apsec.2017.76","mag":"2790044077"},"language":"en","primary_location":{"id":"doi:10.1109/apsec.2017.76","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsec.2017.76","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 24th Asia-Pacific Software Engineering Conference (APSEC)","raw_type":"proceedings-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/A5012394915","display_name":"Kwabena Ebo Bennin","orcid":"https://orcid.org/0000-0001-9140-9271"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Kwabena Ebo Bennin","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051403641","display_name":"Jacky Keung","orcid":"https://orcid.org/0000-0002-3803-9600"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jacky Keung","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078686662","display_name":"Akito Monden","orcid":"https://orcid.org/0000-0003-4295-207X"},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akito Monden","raw_affiliation_strings":["Graduate School of Natural Science and Technology, Okayama University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Natural Science and Technology, Okayama University, Japan","institution_ids":["https://openalex.org/I163770644"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012394915"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":2.4181,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91903482,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"630","last_page":"635"},"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":0.9966999888420105,"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":0.9871000051498413,"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/sampling","display_name":"Sampling (signal processing)","score":0.7103532552719116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6788821220397949},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5570691227912903},{"id":"https://openalex.org/keywords/parameter-space","display_name":"Parameter space","score":0.5296278595924377},{"id":"https://openalex.org/keywords/tweaking","display_name":"Tweaking","score":0.5090658068656921},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.48676419258117676},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47703737020492554},{"id":"https://openalex.org/keywords/sampling-distribution","display_name":"Sampling distribution","score":0.4767664074897766},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.46981173753738403},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance prediction","score":0.4549228549003601},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4157487452030182},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37908899784088135},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.36749327182769775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.324921190738678},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.28247660398483276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1821253001689911},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.17710912227630615},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09836289286613464}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7103532552719116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6788821220397949},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5570691227912903},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.5296278595924377},{"id":"https://openalex.org/C2780200862","wikidata":"https://www.wikidata.org/wiki/Q4453309","display_name":"Tweaking","level":2,"score":0.5090658068656921},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.48676419258117676},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47703737020492554},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.4767664074897766},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.46981173753738403},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.4549228549003601},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4157487452030182},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37908899784088135},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.36749327182769775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.324921190738678},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.28247660398483276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1821253001689911},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.17710912227630615},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09836289286613464},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsec.2017.76","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsec.2017.76","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 24th Asia-Pacific Software Engineering Conference (APSEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1496056137","https://openalex.org/W1975040830","https://openalex.org/W1986515506","https://openalex.org/W1992331847","https://openalex.org/W2009786711","https://openalex.org/W2014455254","https://openalex.org/W2019338079","https://openalex.org/W2025700486","https://openalex.org/W2103715428","https://openalex.org/W2104933073","https://openalex.org/W2105776892","https://openalex.org/W2120457925","https://openalex.org/W2125999269","https://openalex.org/W2126626812","https://openalex.org/W2130883460","https://openalex.org/W2132791018","https://openalex.org/W2139164805","https://openalex.org/W2141051748","https://openalex.org/W2146338950","https://openalex.org/W2148143831","https://openalex.org/W2160958420","https://openalex.org/W2171824022","https://openalex.org/W2424693453","https://openalex.org/W2493218965","https://openalex.org/W2510312579","https://openalex.org/W2528160956","https://openalex.org/W2582743722","https://openalex.org/W2586292313","https://openalex.org/W2612584574","https://openalex.org/W2737319015","https://openalex.org/W2987883775","https://openalex.org/W3141989311","https://openalex.org/W4245807786","https://openalex.org/W6675634716","https://openalex.org/W6680366005","https://openalex.org/W6717489403","https://openalex.org/W6723357538","https://openalex.org/W6769764061","https://openalex.org/W6827285116"],"related_works":["https://openalex.org/W4286900966","https://openalex.org/W3206336800","https://openalex.org/W4389728957","https://openalex.org/W2129381159","https://openalex.org/W1606274310","https://openalex.org/W2950783152","https://openalex.org/W2081167087","https://openalex.org/W2767269462","https://openalex.org/W4309593098","https://openalex.org/W3121734743"],"abstract_inverted_index":{"Sampling":[0],"methods":[1,11,58,97,108],"are":[2,98],"known":[3,71],"to":[4,26,51,158],"impact":[5,176],"defect":[6,88,183],"prediction":[7,20,89,111,184],"performance.":[8,21],"These":[9],"sampling":[10,45,57,96,107,197],"have":[12,173],"configurable":[13],"parameters":[14],"that":[15,122,167],"can":[16,172],"significantly":[17],"affect":[18],"the":[19,28,32,37,42,60,63,69,85,92,126,138,148,168,178,192,196,200],"It":[22],"is":[23,59,133,150,156],"however,":[24],"impractical":[25],"assess":[27,84],"effect":[29],"of":[30,62,75,87,95,105,116,182,195,202],"all":[31,41,56],"possible":[33],"different":[34,161],"settings":[35],"in":[36,55,68],"parameter":[38,53,94,170,194],"space":[39],"for":[40],"several":[43],"existing":[44],"methods.":[46],"A":[47],"constant":[48],"and":[49,65,83,103],"easy":[50],"tweak":[52],"present":[54],"distribution":[61,201],"defective":[64],"non-defective":[66],"modules":[67],"dataset":[70],"as":[72,147],"Pfp":[73,93,139,149,162,169,193],"(%":[74],"fault-prone":[76],"modules).":[77],"In":[78],"this":[79],"paper,":[80],"we":[81,165],"investigate":[82],"performance":[86,132,145,179],"models":[90,112],"where":[91],"tweaked.":[99],"An":[100],"empirical":[101],"experiment":[102,190],"assessment":[104],"seven":[106],"on":[109,177],"five":[110],"over":[113],"20":[114],"releases":[115],"10":[117],"static":[118],"metric":[119],"projects":[120],"indicate":[121],"(1)":[123],"Area":[124],"Under":[125],"Receiver":[127],"Operating":[128],"Characteristics":[129],"Curve":[130],"(AUC)":[131],"not":[134],"improved":[135],"after":[136],"tweaking":[137],"parameter,":[140],"(2)":[141],"pf":[142],"(false":[143],"alarms)":[144],"degrades":[146],"increased.":[151],"(3)":[152],"a":[153,174],"stable":[154],"predictor":[155],"difficult":[157],"achieve":[159],"across":[160],"rates.":[163],"Hence,":[164],"conclude":[166],"setting":[171],"large":[175],"(except":[180],"AUC)":[181],"models.":[185],"We":[186],"thus":[187],"recommend":[188],"researchers":[189],"with":[191],"method":[198],"since":[199],"training":[203],"datasets":[204],"vary.":[205]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}