{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T18:02:55Z","timestamp":1729620175756,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,8]]},"DOI":"10.1109\/iri.2010.5558968","type":"proceedings-article","created":{"date-parts":[[2010,8,27]],"date-time":"2010-08-27T14:37:14Z","timestamp":1282919834000},"page":"31-36","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating the impact of data quality on sampling"],"prefix":"10.1109","author":[{"given":"Jason","family":"Van Hulse","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amri","family":"Napolitano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273614"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2009.08.005"},{"key":"ref12","first-page":"143","article-title":"Experiments with noise filtering in a medical domain","author":"gamberger","year":"1999","journal-title":"Proceedings of the 16th International Conference on Machine Learning"},{"key":"ref13","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":"ref14","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":"ref15","doi-asserted-by":"crossref","first-page":"487","DOI":"10.3233\/IDA-2006-10602","article-title":"Class noise detection using frequent itemsets","volume":"10","author":"van hulse","year":"2006","journal-title":"Intelligent Data Analysis An International Journal"},{"key":"ref16","first-page":"239","article-title":"Correcting noisy data","author":"teng","year":"1999","journal-title":"Proceedings of the Sixteenth International Conference on Machine Learning"},{"article-title":"UCI machine learning repository","year":"2007","author":"asuncion","key":"ref17"},{"key":"ref18","first-page":"297","article-title":"Cost-guided class noise handling for effective cost-sensitive learning","author":"zhu","year":"2004","journal-title":"Proc 4th IEEE Int Conf Data Mining (ICDM 2004)"},{"journal-title":"Data Mining Practical Machine Learning Tools and Techniques","year":"2005","author":"witten","key":"ref19"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"Smote: Synthetic minority oversampling technique","author":"chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref3","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","author":"wilson","year":"1972","journal-title":"IEEE Trans on Systems Man and Cybernetics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007734"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IRI.2007.4296694"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"193","DOI":"10.3233\/ICA-2009-0314","article-title":"Hybrid sampling for imbalanced data","volume":"16","author":"seiffert","year":"2009","journal-title":"Journal of Integrated Computer-Aided Engineering"},{"key":"ref7","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"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2007.34"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-004-0751-8"},{"key":"ref9","article-title":"C4.5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling","author":"drummond","year":"2003","journal-title":"in Workshop on Learning from Imbalanced Data Sets II International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1007\/978-3-540-27868-9_88","article-title":"The imbalanced training sample problem: Under or over sampling?","volume":"3138","author":"barandela","year":"2004","journal-title":"Joint IAPR International Workshops on Structural Syntactic and Statistical Pattern Recognition (SSPRlSPR'04) Lecture Notes in Computer Science"}],"event":{"name":"Integration (2010 IRI)","start":{"date-parts":[[2010,8,4]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2010,8,6]]}},"container-title":["2010 IEEE International Conference on Information Reuse & Integration"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5550513\/5558895\/05558968.pdf?arnumber=5558968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,2]],"date-time":"2019-06-02T11:04:38Z","timestamp":1559473478000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5558968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,8]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iri.2010.5558968","relation":{},"subject":[],"published":{"date-parts":[[2010,8]]}}}