{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T10:46:52Z","timestamp":1785322012213,"version":"3.55.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2014,2,1]],"date-time":"2014-02-01T00:00:00Z","timestamp":1391212800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1016\/j.ins.2010.12.016","type":"journal-article","created":{"date-parts":[[2011,1,10]],"date-time":"2011-01-10T09:05:26Z","timestamp":1294650326000},"page":"571-595","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":114,"special_numbering":"C","title":["An empirical study of the classification performance of learners on imbalanced and noisy software quality data"],"prefix":"10.1016","volume":"259","author":[{"given":"Chris","family":"Seiffert","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Van Hulse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andres","family":"Folleco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2010.12.016_b0005","series-title":"On Measures of Information and Their Characterizations","author":"Aczel","year":"1975"},{"key":"10.1016\/j.ins.2010.12.016_b0010","series-title":"Lazy Learning","author":"Aha","year":"1997"},{"key":"10.1016\/j.ins.2010.12.016_b0015","unstructured":"R. Barandela, R.M. Valdovinos, J.S. Sanchez, F.J. Ferri, The imbalanced training sample problem: under or over sampling? in: Joint IAPR International Workshops on Structural, Syntactic, and Statistical Pattern Recognition (SSPR\/SPR\u201904), Lecture Notes in Computer Science, vol. 3138, 3138\/2004, 2004, pp. 806\u2013814."},{"key":"10.1016\/j.ins.2010.12.016_b0020","series-title":"Intermediate Statistical Methods and Applications: A Computer Package Approach","author":"Berenson","year":"1983"},{"issue":"2","key":"10.1016\/j.ins.2010.12.016_b0025","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"26","author":"Breiman","year":"1996","journal-title":"Machine Learning"},{"issue":"1","key":"10.1016\/j.ins.2010.12.016_b0030","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"10.1016\/j.ins.2010.12.016_b0035","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1613\/jair.606","article-title":"Identifying mislabeled training data","volume":"11","author":"Brodley","year":"1999","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.ins.2010.12.016_b0040","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority oversampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"1","key":"10.1016\/j.ins.2010.12.016_b0045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1007730.1007733","article-title":"Editorial: special issue on learning from imbalanced data sets","volume":"6","author":"Chawla","year":"2004","journal-title":"SIGKDD Explorations"},{"issue":"16","key":"10.1016\/j.ins.2010.12.016_b0050","doi-asserted-by":"crossref","first-page":"3214","DOI":"10.1016\/j.ins.2008.03.018","article-title":"An information granulation based data mining approach for classifying imbalanced data","volume":"178","author":"Chen","year":"2008","journal-title":"Information Sciences"},{"key":"10.1016\/j.ins.2010.12.016_b0055","series-title":"Proceedings of the 12th International Conference on Machine Learning","first-page":"115","article-title":"Fast effective rule induction","author":"Cohen","year":"1995"},{"issue":"2\u20133","key":"10.1016\/j.ins.2010.12.016_b0060","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1023\/A:1007413511361","article-title":"On the optimality of the simple bayesian classifier under zero-one loss","volume":"29","author":"Domingos","year":"1997","journal-title":"Machine Learning"},{"key":"10.1016\/j.ins.2010.12.016_b0065","unstructured":"C. Drummond, R.C. Holte, C4.5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling, in: Workshop on Learning from Imbalanced Data Sets II, International Conference on Machine Learning, 2003."},{"key":"10.1016\/j.ins.2010.12.016_b0070","unstructured":"C. Elkan, The foundations of cost-sensitive learning, in: Proceedings of the Seventeenth International Conference on Machine Learning, 2001, pp. 239\u2013246."},{"key":"10.1016\/j.ins.2010.12.016_b0075","series-title":"second ed.","article-title":"Software Metrics: A Rigorous and Practical Approach","author":"Fenton","year":"1997"},{"key":"10.1016\/j.ins.2010.12.016_b0080","doi-asserted-by":"crossref","unstructured":"J. Furnkranz, G. Widmer, Incremental reduced error pruning, in: International Conference on Machine Learning, 1994, pp. 70\u201377.","DOI":"10.1016\/B978-1-55860-335-6.50017-9"},{"key":"10.1016\/j.ins.2010.12.016_b0085","series-title":"Proceedings of the 16th International Conference on Machine Learning","first-page":"143","article-title":"Experiments with noise filtering in a medical domain","author":"Gamberger","year":"1999"},{"key":"10.1016\/j.ins.2010.12.016_b0090","series-title":"International Conference on Intelligent Computing (ICIC\u201905)","first-page":"878","article-title":"Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning","volume":"vol. 3644","author":"Han","year":"2005"},{"key":"10.1016\/j.ins.2010.12.016_b0095","series-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"Hastie","year":"2001"},{"issue":"8","key":"10.1016\/j.ins.2010.12.016_b0100","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1109\/34.709601","article-title":"The random subspace method for constructing decision forests","volume":"20","author":"Ho","year":"1998","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"10.1016\/j.ins.2010.12.016_b0105","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3233\/IDA-2002-6504","article-title":"The class imbalance problem: a systematic study","volume":"6","author":"Japkowicz","year":"2002","journal-title":"Intelligent Data Analysis"},{"issue":"1","key":"10.1016\/j.ins.2010.12.016_b0110","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/1007730.1007737","article-title":"Class imbalances versus small disjuncts","volume":"6","author":"Jo","year":"2004","journal-title":"SIGKDD Explorations"},{"issue":"3","key":"10.1016\/j.ins.2010.12.016_b0115","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1023\/A:1009736205722","article-title":"Classification of fault-prone software modules: prior probabilities, costs and model evaluation","volume":"3","author":"Khoshgoftaar","year":"1998","journal-title":"Empirical Software Engineering"},{"issue":"4","key":"10.1016\/j.ins.2010.12.016_b0120","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1142\/S0218539399000292","article-title":"Logistic regression modeling of software quality","volume":"6","author":"Khoshgoftaar","year":"1999","journal-title":"International Journal of Reliability, Quality, and Safety Engineering"},{"issue":"2","key":"10.1016\/j.ins.2010.12.016_b0125","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/B:EMSE.0000027781.18360.9b","article-title":"Comparative assessment of software quality classification techniques: an empirical case study","volume":"9","author":"Khoshgoftaar","year":"2004","journal-title":"Empirical Software Engineering Journal"},{"key":"10.1016\/j.ins.2010.12.016_b0130","doi-asserted-by":"crossref","unstructured":"T.M. Khoshgoftaar, J. Van Hulse, C. Seiffert, A hybrid approach to cleansing software measurement data, in: Proceedings of the 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2006), Washington, DC, 2006, pp. 713\u2013722.","DOI":"10.1109\/ICTAI.2006.11"},{"issue":"1","key":"10.1016\/j.ins.2010.12.016_b0135","doi-asserted-by":"crossref","first-page":"3","DOI":"10.3233\/IDA-2005-9102","article-title":"Enhancing software quality estimation using ensemble-classifier based noise filtering","volume":"6","author":"Khoshgoftaar","year":"2005","journal-title":"Intelligent Data Analysis: An International Journal"},{"key":"10.1016\/j.ins.2010.12.016_b0140","unstructured":"A. Kolcz, A. Chowdhury, J. Alspector, Data duplication: an imbalance problem?, in: ICML\u20192003 Workshop on Learning from Imbalanced Datasets, 2003."},{"key":"10.1016\/j.ins.2010.12.016_b0145","series-title":"Proceedings of the Fourteenth International Conference on Machine Learning","first-page":"179","article-title":"Addressing the curse of imbalanced training sets: one sided selection","author":"Kubat","year":"1997"},{"key":"10.1016\/j.ins.2010.12.016_b0150","unstructured":"M. Maloof, Learning when data sets are imbalanced and when costs are unequal and unknown, in: Proceedings of the ICML\u201903 Workshop on Learning from Imbalanced Data Sets, 2003."},{"key":"10.1016\/j.ins.2010.12.016_b0155","series-title":"Machine Learning","author":"Mitchell","year":"1997"},{"issue":"2","key":"10.1016\/j.ins.2010.12.016_b0160","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1162\/neco.1989.1.2.281","article-title":"Fast learning in networks of locally tuned processing units","volume":"1","author":"Moody","year":"1989","journal-title":"Neural Computation"},{"key":"10.1016\/j.ins.2010.12.016_b0165","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1023\/A:1007601015854","article-title":"Robust classification for imprecise environments","volume":"42","author":"Provost","year":"2001","journal-title":"Machine Learning"},{"key":"10.1016\/j.ins.2010.12.016_b0170","series-title":"C4.5: Programs For Machine Learning","author":"Quinlan","year":"1993"},{"key":"10.1016\/j.ins.2010.12.016_b0175","series-title":"Pattern Recognition and Neural Networks","author":"Ripley","year":"1996"},{"key":"10.1016\/j.ins.2010.12.016_b0180","unstructured":"SAS Institute, SAS\/STAT User\u2019s Guide, SAS Institute Inc., 2004."},{"key":"10.1016\/j.ins.2010.12.016_b0185","series-title":"Advances in Kernel Methods: Support Vector Learning","year":"1999"},{"key":"10.1016\/j.ins.2010.12.016_b0190","unstructured":"C.M. Teng, Correcting noisy data, in: Proceedings of the Sixteenth International Conference on Machine Learning, 1999, pp. 239\u2013248."},{"key":"10.1016\/j.ins.2010.12.016_b0195","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1613\/jair.1199","article-title":"Learning when training data are costly: the effect of class distribution on tree induction","volume":"19","author":"Weiss","year":"2003","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.ins.2010.12.016_b0200","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1109\/TSMC.1972.4309137","article-title":"Asymptotic properties of nearest neighbor rules using edited data sets","volume":"2","author":"Wilson","year":"1972","journal-title":"IEEE Transactions on Systems, Man and Cybernetics"},{"key":"10.1016\/j.ins.2010.12.016_b0205","series-title":"Data Mining: Practical Machine Learning Tools and Techniques","author":"Witten","year":"2005"},{"key":"10.1016\/j.ins.2010.12.016_b0210","series-title":"Experimentation in Software Engineering: An Introduction","author":"Wohlin","year":"2000"},{"issue":"3\u20134","key":"10.1016\/j.ins.2010.12.016_b0215","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s10462-004-0751-8","article-title":"Class noise vs attribute noise: a quantitative study of their impacts","volume":"22","author":"Zhu","year":"2004","journal-title":"Artificial Intelligence Review"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0020025511000065?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0020025511000065?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T18:46:32Z","timestamp":1559933192000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025511000065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2]]},"references-count":43,"alternative-id":["S0020025511000065"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.ins.2010.12.016","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2014,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An empirical study of the classification performance of learners on imbalanced and noisy software quality data","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.ins.2010.12.016","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"Copyright \u00a9 2011 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}