{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:51:57Z","timestamp":1778824317200,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2011,12,4]],"date-time":"2011-12-04T00:00:00Z","timestamp":1322956800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1007\/s10115-011-0465-6","type":"journal-article","created":{"date-parts":[[2011,12,3]],"date-time":"2011-12-03T21:54:21Z","timestamp":1322949261000},"page":"245-265","source":"Crossref","is-referenced-by-count":410,"title":["SMOTE-RSB *: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data-sets using SMOTE and rough sets theory"],"prefix":"10.1007","volume":"33","author":[{"given":"Enislay","family":"Ramentol","sequence":"first","affiliation":[]},{"given":"Yail\u00e9","family":"Caballero","sequence":"additional","affiliation":[]},{"given":"Rafael","family":"Bello","sequence":"additional","affiliation":[]},{"given":"Francisco","family":"Herrera","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,12,4]]},"reference":[{"issue":"3","key":"465_CR1","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1007\/s00500-008-0323-y","volume":"13","author":"J Alcal\u00e1-Fdez","year":"2009","unstructured":"Alcal\u00e1-Fdez J, S\u00e1nchez L, Garc\u00eda S, del Jesus MJ, Ventura S, Garrell JM, Otero J, Romero C, Bacardit J, Rivas VM, Fern\u00e1ndez JC, Herrera F (2009) KEEL: a software tool to assess evolutionary algorithms to data mining problems. Soft Comput 13(3): 307\u2013318","journal-title":"Soft Comput"},{"issue":"2\u20133","key":"465_CR2","first-page":"255","volume":"17","author":"J Alcal\u00e1-Fdez","year":"2011","unstructured":"Alcal\u00e1-Fdez J, Fern\u00e1ndez A, Luengo J, Derrac J, Garc\u00eda S, S\u00e1nchez L, Herrera F (2011) KEEL data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. J Multiple-Valued Log Soft Comput 17(2\u20133): 255\u2013287","journal-title":"J Multiple-Valued Log Soft Comput"},{"key":"465_CR3","unstructured":"Asuncion A, Newman D (2007) UCI Machine learning repository. http:\/\/mlearn.ics.uci.edu\/MLRepository.html"},{"issue":"1","key":"465_CR4","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1145\/1007730.1007735","volume":"6","author":"GEAPA Batista","year":"2004","unstructured":"Batista GEAPA, Prati RC, Monard MC (2004) A study of the behaviour of several methods for balancing machine learning training data. SIGKDD Explor 6(1): 20\u201329","journal-title":"SIGKDD Explor"},{"key":"465_CR5","doi-asserted-by":"crossref","unstructured":"Bello, R, Falcon, R, Pedrycz, W, Kacprzyk, J (eds) (2008) Granular computing: at the junction of rough sets and fuzzy sets. Springer","DOI":"10.1007\/978-3-540-76973-6"},{"issue":"7","key":"465_CR6","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley AP (1997) The use of the Area Under the ROC Curve in the evaluation of machine learning algorithms. Pattern Recognit 30(7): 1145\u20131159","journal-title":"Pattern Recognit"},{"key":"465_CR7","doi-asserted-by":"crossref","unstructured":"Bunkhumpornpat C, Sinapiromsaran K, Lursinsap C (2009) \u2018Safe-Level-SMOTE: safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem\u2019. Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD09). LNCS 3644. Springer, pp 475\u2013482","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"465_CR8","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res 16: 321\u2013357","journal-title":"J Artif Intell Res"},{"issue":"1","key":"465_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1007730.1007733","volume":"6","author":"NV Chawla","year":"2004","unstructured":"Chawla NV, Japkowicz N, Kolcz A (2004) Editorial: special issue on learning from imbalanced data sets. SIGKDD Explor 6(1): 1\u20136","journal-title":"SIGKDD Explor"},{"issue":"2","key":"465_CR10","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s10618-008-0087-0","volume":"17","author":"NV Chawla","year":"2008","unstructured":"Chawla NV, Cieslak D, Hall L, Joshi A (2008) Automatically countering imbalance and its empirical relationship to cost. Data Min Knowl Discov 17(2): 225\u2013252","journal-title":"Data Min Knowl Discov"},{"issue":"1","key":"465_CR11","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/s10115-009-0260-9","volume":"25","author":"Y-S Chen","year":"2010","unstructured":"Chen Y-S, Cheng C-H (2010) Forecasting PGR of the financial industry using a rough sets classifier based on attribute-granularity. Knowl Inf Syst 25(1): 57\u201379","journal-title":"Knowl Inf Syst"},{"key":"465_CR12","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7: 1\u201330","journal-title":"J Mach Learn Res"},{"issue":"18","key":"465_CR13","doi-asserted-by":"crossref","first-page":"2378","DOI":"10.1016\/j.fss.2007.12.023","volume":"159","author":"A Fern\u00e1ndez","year":"2008","unstructured":"Fern\u00e1ndez A, Garc\u00eda S, del Jesus MJ, Herrera F (2008) A study of the behaviour of linguistic fuzzy rule based classification systems in the framework of imbalanced data-sets. Fuzzy Sets Syst 159(18): 2378\u20132398","journal-title":"Fuzzy Sets Syst"},{"key":"465_CR14","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez A, del Jesus MJ, Herrera F (2010) Multi-class imbalanced data-sets with linguistic fuzzy rule based classification systems based on pairwise learning. 13th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU2010) LNAI 6178. pp 89\u201398. 159(18):2378\u20132398","DOI":"10.1007\/978-3-642-14049-5_10"},{"key":"465_CR15","first-page":"721","volume":"2","author":"J F\u00fcrnkranz","year":"2002","unstructured":"F\u00fcrnkranz J (2002) Round robin classification. J Mach Learn Res 2: 721\u2013747","journal-title":"J Mach Learn Res"},{"key":"465_CR16","first-page":"2677","volume":"9","author":"S Garc\u00eda","year":"2008","unstructured":"Garc\u00eda S, Herrera F (2008) An extension on \u201cStatistical comparisons of classifiers over multiple data sets\u201d for all pairwise comparisons. J Mach Learn Res 9: 2677\u20132694","journal-title":"J Mach Learn Res"},{"issue":"3","key":"465_CR17","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1162\/evco.2009.17.3.275","volume":"17","author":"S Garc\u00eda","year":"2009","unstructured":"Garc\u00eda S, Herrera F (2009) Evolutionary under-sampling for classification with imbalanced data sets: proposals and taxonomy. Evol Comput 17(3): 275\u2013306","journal-title":"Evol Comput"},{"issue":"10","key":"465_CR18","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1007\/s00500-008-0392-y","volume":"13","author":"S Garc\u00eda","year":"2009","unstructured":"Garc\u00eda S, Fern\u00e1ndez A, Luengo J, Herrera F (2009) A study of statistical techniques and performance measures for genetics-based machine learning: accuracy and interpretability. Soft Comput 13(10): 959\u2013977","journal-title":"Soft Comput"},{"key":"465_CR19","doi-asserted-by":"crossref","first-page":"2044","DOI":"10.1016\/j.ins.2009.12.010","volume":"180","author":"S Garc\u00eda","year":"2010","unstructured":"Garc\u00eda S, Fern\u00e1ndez A, Luengo J, Herrera F (2010) Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: experimental analysis of power. Inf Sci 180: 2044\u20132064","journal-title":"Inf Sci"},{"key":"465_CR20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0377-2217(00)00167-3","volume":"129","author":"S Greco","year":"2001","unstructured":"Greco S (2001) Rough sets theory for multicriteria decision analysis. Eur J Oper Res 129: 1\u201347","journal-title":"Eur J Oper Res"},{"issue":"6","key":"465_CR21","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1007\/s10845-005-4362-2","volume":"16","author":"JW Grzymala-Busse","year":"2005","unstructured":"Grzymala-Busse JW, Stefanowski J, Wilk S (2005) A comparison of two approaches to data mining from imbalanced data. J Intell Manuf 16(6): 565\u2013573","journal-title":"J Intell Manuf"},{"key":"465_CR22","doi-asserted-by":"crossref","unstructured":"Han H, Wang WY, Mao BH (2005) Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. International conference on intelligent computing (ICIC05) LNCS 3644. Springer, pp 878\u2013887","DOI":"10.1007\/11538059_91"},{"issue":"9","key":"465_CR23","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garc\u00eda EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9): 1263\u20131284","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"465_CR24","first-page":"65","volume":"6","author":"S Holm","year":"1979","unstructured":"Holm S (1979) A simple sequentially rejective multiple test procedure, Scandinavian. J Stat 6: 65\u201370","journal-title":"J Stat"},{"issue":"3","key":"465_CR25","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1109\/TKDE.2005.50","volume":"17","author":"J Huang","year":"2005","unstructured":"Huang J, Ling CX (2005) Using AUC and accuracy in evaluating learning algorithms. IEEE Trans Knowl Data Eng 17(3): 299\u2013310","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"4","key":"465_CR26","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1016\/j.nonrwa.2005.04.006","volume":"7","author":"YM Huan","year":"2006","unstructured":"Huan YM, Hung CM, Jiau HC (2006) Evaluation of neural networks and data mining methods on a credit assessment task for class imbalance problem. Nonlinear Anal Real World Appl 7(4): 720\u2013747","journal-title":"Nonlinear Anal Real World Appl"},{"key":"465_CR27","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1080\/03610928008827904","volume":"9","author":"R Iman","year":"1980","unstructured":"Iman R, Davenport J (1980) Approximations of the critical region of the Friedman statistic. Commun Stat Part A Theory Methods 9: 571\u2013595","journal-title":"Commun Stat Part A Theory Methods"},{"issue":"8","key":"465_CR28","doi-asserted-by":"crossref","first-page":"1055","DOI":"10.1109\/TKDE.2006.131","volume":"18","author":"C Ling","year":"2006","unstructured":"Ling C, Sheng V (2006) Test strategies for cost-sensitive decision trees. IEEE Trans Knowl Data Eng 18(8): 1055\u20131057","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2-3","key":"465_CR29","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.neunet.2007.12.031","volume":"21","author":"M Mazurowski","year":"2008","unstructured":"Mazurowski M, Habas P, Zurada J, Lo J, Baker J, Tourassi G (2008) Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance. Neural Netw 21(2-3): 427\u2013436","journal-title":"Neural Netw"},{"key":"465_CR30","first-page":"155","volume":"53","author":"H Midelfar","year":"2003","unstructured":"Midelfar H, Komorowski J, N\u00f8rsett K, Yadetie F, Sandvik A, L\u00e6greid A (2003) Learning rough set classifiers from gene expression and clinical data. Fundam Inf 53: 155\u2013183","journal-title":"Fundam Inf"},{"issue":"3","key":"465_CR31","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s00500-008-0319-7","volume":"13","author":"A Orriols-Puig","year":"2009","unstructured":"Orriols-Puig A, Bernad\u00f3-Mansilla E (2009) Evolutionary rule-based systems for imbalanced datasets. Soft Comput 13(3): 213\u2013225","journal-title":"Soft Comput"},{"key":"465_CR32","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/BF01001956","volume":"11","author":"Z Pawlak","year":"1982","unstructured":"Pawlak Z (1982) Rough sets. Int J Comput Inf Sci 11: 145\u2013172","journal-title":"Int J Comput Inf Sci"},{"key":"465_CR33","volume-title":"C4.5 programs for machine learning","author":"J Quinlan","year":"1993","unstructured":"Quinlan J (1993) C4.5 programs for machine learning. Morgan Kaufmann, CA"},{"key":"465_CR34","doi-asserted-by":"crossref","unstructured":"Sheskin D (2003) Handbook of parametric and nonparametric statistical procedures. chapman & hall, CRC Press","DOI":"10.1201\/9781420036268"},{"key":"465_CR35","first-page":"17","volume":"4","author":"R Slowinski","year":"1997","unstructured":"Slowinski R, Vanderpooten D (1997) Similarity relation as a basis for rough approximations. Adv Mach Intell Soft-Comput 4: 17\u201333","journal-title":"Adv Mach Intell Soft-Comput"},{"key":"465_CR36","doi-asserted-by":"crossref","first-page":"3358","DOI":"10.1016\/j.patcog.2007.04.009","volume":"40","author":"Y Sun","year":"2007","unstructured":"Sun Y, Kamel MS, Wong AK, Wang Y (2007) Cost-sensitive boosting for classification of imbalanced data. Pattern Recognit 40: 3358\u20133378","journal-title":"Pattern Recognit"},{"issue":"4","key":"465_CR37","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1142\/S0218001409007326","volume":"23","author":"Y Sun","year":"2009","unstructured":"Sun Y, Wong AK, Kamel MS (2009) Classification of imbalanced data: a review. Int J Pattern Recognit Artif Intell 23(4): 687\u2013719","journal-title":"Int J Pattern Recognit Artif Intell"},{"issue":"12","key":"465_CR38","doi-asserted-by":"crossref","first-page":"2621","DOI":"10.1016\/j.ins.2008.02.009","volume":"178","author":"S Suresh","year":"2008","unstructured":"Suresh S, Sundararajan N, Saratchandran P (2008) Risk-sensitive loss functions for sparse multi-category classification problems. Inf Sci 178(12): 2621\u20132638","journal-title":"Inf Sci"},{"key":"465_CR39","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1109\/TSMC.1976.4309452","volume":"6","author":"I Tomek","year":"1976","unstructured":"Tomek I (1976) Two modifications of CNN. IEEE Trans Syst Man Commun 6: 769\u2013772","journal-title":"IEEE Trans Syst Man Commun"},{"key":"465_CR40","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/S0957-4174(02)00142-2","volume":"24","author":"S Tsumoto","year":"2003","unstructured":"Tsumoto S (2003) Automated extraction of hierarchical decision rules from clinical databases using rough set model. Expert Syst Appl 24: 189\u2013197","journal-title":"Expert Syst Appl"},{"issue":"1","key":"465_CR41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10115-009-0198-y","volume":"25","author":"BX Wang","year":"2010","unstructured":"Wang BX, Japkowicz N (2010) Boosting support vector machines for imbalanced data sets. Knowl Inf Syst 25(1): 1\u201320","journal-title":"Knowl Inf Syst"},{"issue":"5","key":"465_CR42","first-page":"1355","volume":"178","author":"X Wei-hua","year":"2008","unstructured":"Wei-hua X, Xiao-yan Z, Jian-min Z, Wen-xiu Z (2008) Attribute reduction in ordered information systems based on evidence theory. Knowl Inf Syst 178(5): 1355\u20131371","journal-title":"Knowl Inf Syst"},{"key":"465_CR43","unstructured":"Weiss GM, Hirsh H (2000) A quantitative study of small disjuncts, In: Proceedings of the 17th national conference on artificial inteligence. pp 665\u2013670"},{"key":"465_CR44","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1613\/jair.1199","volume":"19","author":"GM Weiss","year":"2003","unstructured":"Weiss GM, Provost F (2003) Learning when training data are costly: the effect of class distribution on tree induction. J Artif Intell Res 19: 315\u2013354","journal-title":"J Artif Intell Res"},{"issue":"3","key":"465_CR45","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1109\/TSMC.1972.4309137","volume":"2","author":"DL Wilson","year":"1972","unstructured":"Wilson DL (1972) Asymptotic properties of nearest neighbor rules using edited data. IEEE Trans Syst Man Commun 2(3): 408\u2013421","journal-title":"IEEE Trans Syst Man Commun"},{"issue":"1","key":"465_CR46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10115-007-0114-2","volume":"14","author":"X Wu","year":"2008","unstructured":"Wu X, Kumar V, Quinlan JR, Ghosh J, Yang Q, Motoda H, McLachlan GJ, Ng A, Liu B, Yu PS, Zhou Z-H, Steinbach M, Hand DJ, Steinberg D (2008) Top 10 algorithms in data mining. Knowl Inf Syst 14(1): 1\u201337","journal-title":"Knowl Inf Syst"},{"issue":"1","key":"465_CR47","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s10115-009-0248-5","volume":"25","author":"W Xu","year":"2010","unstructured":"Xu W, Zhang X, Zhong J, Zhang W (2010) Attribute reduction in ordered information systems based on evidence theory. Knowl Inf Syst 25(1): 169\u2013184","journal-title":"Knowl Inf Syst"},{"issue":"4","key":"465_CR48","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1142\/S0219622006002258","volume":"5","author":"Q Yang","year":"2006","unstructured":"Yang Q, Wu X (2006) 10 challenging problems in data mining research. Int J Inf Technol Decis Mak 5(4): 597\u2013604","journal-title":"Int J Inf Technol Decis Mak"},{"issue":"1","key":"465_CR49","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1109\/TKDE.2006.17","volume":"18","author":"Z-H Zhou","year":"2006","unstructured":"Zhou Z-H, Liu X-Y (2006) Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Trans Knowl Data Eng 18(1): 63\u201377","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-011-0465-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-011-0465-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-011-0465-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,20]],"date-time":"2019-06-20T08:00:27Z","timestamp":1561017627000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-011-0465-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,12,4]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,11]]}},"alternative-id":["465"],"URL":"https:\/\/doi.org\/10.1007\/s10115-011-0465-6","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,12,4]]}}}