{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:30:34Z","timestamp":1777696234959,"version":"3.51.4"},"reference-count":31,"publisher":"SAGE Publications","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2022,9,5]]},"abstract":"<jats:p>Label noise detection has been widely studied in Machine Learning because of its importance in improving training data quality. Satisfactory noise detection has been achieved by adopting ensembles of classifiers. In this approach, an instance is assigned as mislabeled if a high proportion of members in the pool misclassifies it. Previous authors have empirically evaluated this approach; nevertheless, they mostly assumed that label noise is generated completely at random in a dataset. This is a strong assumption since other types of label noise are feasible in practice and can influence noise detection results. This work investigates the performance of ensemble noise detection under two different noise models: the Noisy at Random (NAR), in which the probability of label noise depends on the instance class, in comparison to the Noisy Completely at Random model, in which the probability of label noise is entirely independent. In this setting, we investigate the effect of class distribution on noise detection performance since it changes the total noise level observed in a dataset under the NAR assumption. Further, an evaluation of the ensemble vote threshold is conducted to contrast with the most common approaches in the literature. In many performed experiments, choosing a noise generation model over another can lead to different results when considering aspects such as class imbalance and noise level ratio among different classes.<\/jats:p>","DOI":"10.3233\/ida-215980","type":"journal-article","created":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T11:46:48Z","timestamp":1662464808000},"page":"1119-1138","source":"Crossref","is-referenced-by-count":3,"title":["Label noise detection under the noise at random model with ensemble filters"],"prefix":"10.1177","volume":"26","author":[{"given":"Kecia G.","family":"Moura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ricardo B.C.","family":"Prud\u00eancio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George D.C.","family":"Cavalcanti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-215980_ref1","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1007\/978-3-642-11829-6_17","article-title":"Bagging decision trees on data sets with classification noise","author":"Abell\u00e1n","year":"2010","journal-title":"Foundations of Information and Knowledge Systems"},{"issue":"2-3","key":"10.3233\/IDA-215980_ref2","first-page":"255","article-title":"Keel data-mining software tool: Data set repository, integration of algorithms and experimental analysis framework","volume":"17","author":"AlcalA-Fdez","year":"2011","journal-title":"Journal of Multiple-Valued Logic and Soft Computing"},{"key":"10.3233\/IDA-215980_ref3","unstructured":"D.G.B. Sluban and N. Lavra, Advances in class noise detection, In European Conference on Artificial Intelligence, 2015, pp.\u00a01105\u20131106."},{"key":"10.3233\/IDA-215980_ref4","unstructured":"B. Biggio, B. Nelson and P. Laskov, Support vector machines under adversarial label noise, In C.-N. Hsu and W.S. Lee, editors, Proceedings of the Asian Conference on Machine Learning, volume 20 of Proceedings of Machine Learning Research, South Garden Hotels and Resorts, Taoyuan, Taiwain, 14\u201315 Nov 2011. PMLR, pp.\u00a097\u2013112."},{"key":"10.3233\/IDA-215980_ref5","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.neucom.2015.12.106","article-title":"A generalised label noise model for classification in the presence of annotation errors","volume":"192","author":"Bootkrajang","year":"2016","journal-title":"Neurocomputing"},{"issue":"11","key":"10.3233\/IDA-215980_ref6","doi-asserted-by":"crossref","first-page":"3641","DOI":"10.1016\/j.patcog.2014.05.007","article-title":"Learning kernel logistic regression in the presence of class label noise","volume":"47","author":"Bootkrajang","year":"2014","journal-title":"Pattern Recognition"},{"key":"10.3233\/IDA-215980_ref7","first-page":"131","article-title":"Identifying mislabeled training data","author":"Brodley","year":"1999","journal-title":"Artifficial Intelligence Review"},{"issue":"5","key":"10.3233\/IDA-215980_ref9","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1109\/TNNLS.2013.2292894","article-title":"Classification in the presence of label noise: A survey","volume":"25","author":"Frenay","year":"2014","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"10.3233\/IDA-215980_ref10","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1214\/aos\/1176344722","article-title":"Multivariate generalizations of the wald-wolfowitz and smirnov two-sample tests","volume":"7","author":"Friedman","year":"1979","journal-title":"Ann Statist"},{"key":"10.3233\/IDA-215980_ref11","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1016\/j.knosys.2018.09.031","article-title":"New label noise injection methods for the evaluation of noise filters","volume":"163","author":"Garcia","year":"2019","journal-title":"Knowledge-Based Systems"},{"key":"10.3233\/IDA-215980_ref12","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.ins.2018.12.002","article-title":"Enabling smart data: Noise filtering in big data classification","volume":"479","author":"Garcia-Gil","year":"2019","journal-title":"Information Sciences"},{"issue":"5","key":"10.3233\/IDA-215980_ref13","doi-asserted-by":"crossref","first-page":"2377","DOI":"10.1177\/0962280214523192","article-title":"Misclassification of outcome in case\u00e2\u0080\u0093control studies: Methods for sensitivity analysis","volume":"25","author":"Gilbert","year":"2016","journal-title":"Statistical Methods in Medical Research"},{"key":"10.3233\/IDA-215980_ref14","doi-asserted-by":"crossref","first-page":"11154","DOI":"10.1109\/ACCESS.2018.2807779","article-title":"Improving label noise filtering by exploiting unlabeled data","volume":"6","author":"Guan","year":"2018","journal-title":"IEEE Access"},{"key":"10.3233\/IDA-215980_ref15","unstructured":"J. Han, M. Kamber and J. Pei, Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers, 2012."},{"issue":"1","key":"10.3233\/IDA-215980_ref16","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/s10044-015-0452-8","article-title":"Editing training data for multi-label classification with the k-nearest neighbor rule","volume":"19","author":"Kanj","year":"2016","journal-title":"Pattern Analysis and Applications"},{"issue":"1","key":"10.3233\/IDA-215980_ref17","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":"9","author":"Khoshgoftaar","year":"2005","journal-title":"Intell Data Anal"},{"key":"10.3233\/IDA-215980_ref18","unstructured":"N.D. Lawrence and B. Scholkopf, Estimating a kernel fisher discriminant in the presence of label noise, In Proceedings of the Eighteenth International Conference on Machine Learning, San Francisco, CA, USA, 2001. Morgan Kaufmann Publishers Inc, pp.\u00a0306\u2013313."},{"key":"10.3233\/IDA-215980_ref19","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1590\/S1415-47572004000400031","article-title":"Evaluation of noise reduction techniques in the splice junction recognition problem","volume":"27","author":"Lorena","year":"2004","journal-title":"Genetics and Molecular Biology"},{"issue":"17","key":"10.3233\/IDA-215980_ref20","doi-asserted-by":"crossref","first-page":"2114","DOI":"10.1093\/bioinformatics\/btl346","article-title":"Detecting potential labeling errors in microarrays by data perturbation","volume":"22","author":"Malossini","year":"2006","journal-title":"Bioinformatics"},{"key":"10.3233\/IDA-215980_ref21","doi-asserted-by":"crossref","first-page":"2374","DOI":"10.1016\/j.neucom.2017.11.012","article-title":"A two-stage ensemble method for the detection of class-label noise","volume":"275","author":"Sabzevari","year":"2018","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-215980_ref22","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.ins.2014.08.051","article-title":"Smote\u00e2\u0080\u0093ipf: Addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering","volume":"291","author":"Saez","year":"2015","journal-title":"Information Sciences"},{"issue":"2","key":"10.3233\/IDA-215980_ref23","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/s10618-012-0299-1","article-title":"Ensemble-based noise detection: noise ranking and visual performance evaluation","volume":"28","author":"Sluban","year":"2014","journal-title":"Data Mining and Knowledge Discovery"},{"key":"10.3233\/IDA-215980_ref24","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.neucom.2014.10.086","article-title":"Relating ensemble diversity and performance: a study in class noise detection","author":"Sluban","year":"2015","journal-title":"Neurocomputing"},{"issue":"2","key":"10.3233\/IDA-215980_ref25","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s10994-013-5422-z","article-title":"An instance level analysis of data complexity","volume":"95","author":"Smith","year":"2014","journal-title":"Machine Learning"},{"key":"10.3233\/IDA-215980_ref26","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1109\/FGCN.2007.146","article-title":"Identifying and correcting mislabeled training instances","author":"Sun","year":"2007","journal-title":"Future Generation Communication and Networking (FGCN 2007)"},{"issue":"2","key":"10.3233\/IDA-215980_ref27","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1145\/2641190.2641198","article-title":"Openml: Networked science in machine learning","volume":"15","author":"Vanschoren","year":"2013","journal-title":"SIGKDD Explorations"},{"key":"10.3233\/IDA-215980_ref28","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/3-540-44938-8_32","article-title":"Ensemble methods for noise elimination in classification problems","author":"Verbaeten","year":"2003","journal-title":"Multiple Classifier Systems"},{"issue":"3","key":"10.3233\/IDA-215980_ref29","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1023\/A:1007626913721","article-title":"Reduction techniques for instance-based learning algorithms","volume":"38","author":"Wilson","year":"2000","journal-title":"Machine Learning"},{"key":"10.3233\/IDA-215980_ref30","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.inffus.2017.08.007","article-title":"Classification with class noises through probabilistic sampling","volume":"41","author":"Yuan","year":"2018","journal-title":"Information Fusion"},{"key":"10.3233\/IDA-215980_ref31","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s10462-004-0751-8","article-title":"Class noise vs. attribute noise: A quantitative study","author":"Zhu","year":"2004","journal-title":"Artifficial Intelligence Review"},{"key":"10.3233\/IDA-215980_ref32","unstructured":"X. Zhu, X. Wu and Q. Chen, Eliminating class noise in large datasets, In In 20th International Conference on Machine Learning (ICML), 2003, pp.\u00a0920\u2013927."}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-215980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:19:37Z","timestamp":1777454377000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-215980"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,5]]},"references-count":31,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/ida-215980","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,5]]}}}