{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:33:21Z","timestamp":1787013201874,"version":"build-2736575974"},"reference-count":121,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003093","name":"Ministry of Higher Education Malaysia","doi-asserted-by":"publisher","award":["FRGS\/1\/2019\/ICT02\/UUM\/02\/2"],"award-info":[{"award-number":["FRGS\/1\/2019\/ICT02\/UUM\/02\/2"]}],"id":[{"id":"10.13039\/501100003093","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tkde.2022.3179381","type":"journal-article","created":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T15:47:59Z","timestamp":1654098479000},"page":"1-1","source":"Crossref","is-referenced-by-count":64,"title":["An Investigation of SMOTE based Methods for Imbalanced Datasets with Data Complexity Analysis"],"prefix":"10.1109","author":[{"given":"Nur Athirah","family":"Azhar","sequence":"first","affiliation":[{"name":"Malaysian Investment Development Authority, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Syafiq","family":"Mohd Pozi","sequence":"additional","affiliation":[{"name":"Institute for Advanced and Smart Digital Opportunities, School of Computing, Universiti Utara Malaysia, and the Institute of IR 4.0, Universiti Kebangsaan Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aniza","family":"Mohamed Din","sequence":"additional","affiliation":[{"name":"Data Science Research Lab, School of Computing, Universiti Utara Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Jatowt","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Digital Science Center at the University of Innsbruck, Innsbruck, Tirol, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/GRC.2006.1635905"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34223-4_23"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.05.008"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.09.012"},{"key":"ref53","first-page":"141","article-title":"On relationships between imbalance and overlapping of datasets","author":"almutairi","year":"2020","journal-title":"Proc 35th Int Conf Comput Appl"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065720500434"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-018-0151-6"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19390-8_42"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.10.007"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05256-0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106631"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.10.031"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.04.052"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.08.043"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-0694-9_38"},{"key":"ref41","article-title":"Data poisoning attacks on factorization-based collaborative filtering","author":"li","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/rs9020173"},{"key":"ref43","article-title":"Improving medical image classification with label noise using dual-uncertainty estimation","author":"ju","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-015-0368-1"},{"key":"ref8","article-title":"HuggingFace's transformers: State-of-the-art natural language processing","author":"wolf","year":"2019"},{"key":"ref7","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref9","author":"qui\u00f1onero-candela","year":"2009","journal-title":"Dataset Shift in Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2902431"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1206-1565"},{"key":"ref6","article-title":"word2vec explained: Deriving mikolov et al.'s negative-sampling word-embedding method","author":"goldberg","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31456-9_15"},{"key":"ref100","first-page":"359","article-title":"A dynamic decision-making method based on ensemble methods for complex unbalanced data","author":"chen","year":"2020","journal-title":"Proc Int Conf Web Inf Syst Eng"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206601"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106223"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11192"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105662"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1088\/1755-1315\/58\/1\/012031"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2017.8125820"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.04.089"},{"key":"ref30","article-title":"SMOTE variants for imbalanced binary classification: Heart disease prediction","author":"zheng","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.10.013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01852-8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.10.085"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI44817.2019.9002679"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107150"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2345380"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/11941439_30"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2013.12.013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-021-00260-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.30534\/ijatcse\/2020\/104932020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18178\/ijmlc.2016.6.3.599"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/EI2.2017.8245530"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICREST.2019.8644161"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCNI.2017.8123782"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-016-0094-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2019.03708"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/MLDS.2017.21"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2016.7743445"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106759"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.04.046"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2015.08.060"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.10.041"},{"key":"ref17","first-page":"2123","article-title":"Optimizing F-measures by cost-sensitive classification","author":"parambath","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.12.035"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2002909"},{"key":"ref18","first-page":"1130","article-title":"Optimizing the F-measure in multi-label classification: Plug-in rule approach versus structured loss minimization","author":"dembczynski","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-017-1578-z"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-8055-5_28"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45378-1_4"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.02.028"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2017.11.006"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-019-04336-1"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/2857546.2857648"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106116"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.232"},{"key":"ref88","article-title":"Geometric SMOTE: Effective oversampling for imbalanced learning through a geometric extension of SMOTE","author":"douzas","year":"2017"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2899467"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007735"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3003346"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.08.051"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0465-6"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.07.014"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20847-8_26"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.06.022"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2016EDP7130"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CIDM.2011.5949434"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/JCSSE.2016.7748928"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105845"},{"key":"ref104","first-page":"1","article-title":"SMOTE-LOF for noise identification in imbalanced data classification","author":"asniar","year":"2021","journal-title":"J King Saud Univ -Comput Inf Sci"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.100"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"ref77","article-title":"Fuzzy rough and evolutionary approaches to instance selection","author":"verbiest","year":"2014"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3018911"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-6602-3_3"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.01.031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018628609742"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007662407062"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.07.024"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3068335"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00178"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-016-0957-5"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty995"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2017.2731766"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-011-0287-y"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2955086"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1002\/widm.8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/app10155164"},{"key":"ref117","author":"mitchell","year":"1997","journal-title":"Machine Learning"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.03.073"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1985.6313426"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCTCT.2018.8551020"},{"key":"ref115","article-title":"NI-MWMOTE: An improving noise-immunity majority weighted minority oversampling technique for imbalanced classification problems","volume":"158","author":"jianan","year":"2020","journal-title":"Expert Syst Appl"},{"key":"ref63","article-title":"Diversifying support vector machines for boosting using kernel perturbation: Applications to class imbalance and small disjuncts","author":"datta","year":"2017"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.98"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.12.024"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/8460934"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103966"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.06.056"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489661"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/34.990132"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(87)90114-1"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/4358933\/09786661.pdf?arnumber=9786661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T21:22:19Z","timestamp":1686086539000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9786661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":121,"URL":"https:\/\/doi.org\/10.1109\/tkde.2022.3179381","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}