{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T06:04:27Z","timestamp":1762409067580},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,10,24]],"date-time":"2014-10-24T00:00:00Z","timestamp":1414108800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2016,1]]},"DOI":"10.1007\/s00500-014-1488-1","type":"journal-article","created":{"date-parts":[[2014,10,23]],"date-time":"2014-10-23T16:51:33Z","timestamp":1414083093000},"page":"173-188","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["ur-CAIM: improved CAIM discretization for unbalanced and balanced data"],"prefix":"10.1007","volume":"20","author":[{"given":"Alberto","family":"Cano","sequence":"first","affiliation":[]},{"given":"Dat T.","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Sebasti\u00e1n","family":"Ventura","sequence":"additional","affiliation":[]},{"given":"Krzysztof J.","family":"Cios","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,10,24]]},"reference":[{"key":"1488_CR1","unstructured":"Alcal\u00e1-Fdez J, Fernandez 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. Analysis framework. J Mult Valued Logic Soft Comput 17:255\u2013287"},{"key":"1488_CR2","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 M, Ventura S, Garrell J, Otero J, Romero C, Bacardit J, Rivas V, Fern\u00e1ndez J, Herrera F (2009) KEEL: a software tool to assess evolutionary algorithms for data mining problems. Soft Comput 13:307\u2013318","journal-title":"Soft Comput"},{"key":"1488_CR3","unstructured":"Bache K, Lichman M (2013) UCI machine learning repository (University of California, School of Information and Computer Science). Irvine, CA. http:\/\/archive.ics.uci.edu\/ml"},{"key":"1488_CR4","doi-asserted-by":"crossref","unstructured":"Ben-David A (2008a) About the relationship between ROC curves and Cohen\u2019s kappa. Eng Appl Artif Intell 21(6):874\u2013882","DOI":"10.1016\/j.engappai.2007.09.009"},{"key":"1488_CR5","doi-asserted-by":"crossref","unstructured":"Ben-David A (2008b) Comparison of classification accuracy using Cohen\u2019s weighted kappa. Expert Syst Appl 34(2):825\u2013832","DOI":"10.1016\/j.eswa.2006.10.022"},{"issue":"1","key":"1488_CR6","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/s10994-006-8364-x","volume":"65","author":"M Boull\u00e9","year":"2006","unstructured":"Boull\u00e9 M (2006) MODL: a Bayes optimal discretization method for continuous attributes. Mach Learn 65(1):131\u2013165","journal-title":"Mach Learn"},{"issue":"7","key":"1488_CR7","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":"1488_CR8","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45:5\u201332","journal-title":"Mach Learn"},{"key":"1488_CR9","doi-asserted-by":"crossref","unstructured":"Catlett J (1991) On changing continuous attributes into ordered discrete attributes. In: Proceedings of machine learning, EWSL91, Lecture notes in computer science, vol 482. pp 164\u2013178","DOI":"10.1007\/BFb0017012"},{"key":"1488_CR10","doi-asserted-by":"crossref","first-page":"27:1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:27:1\u201327:27","journal-title":"ACM Trans Intell Syst Technol"},{"key":"1488_CR11","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. Artif Intell Res 16:321\u2013357","journal-title":"Artif Intell Res"},{"key":"1488_CR12","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/S0888-613X(96)00074-6","volume":"15","author":"MR Chmielewski","year":"1996","unstructured":"Chmielewski MR, Grzymala-Busse JW (1996) Global discretization of continuous attributes as preprocessing for machine learning. Int J Approx Reason 15:319\u2013331","journal-title":"Int J Approx Reason"},{"key":"1488_CR13","volume-title":"Data mining: a knowledge discovery approach","author":"KJ Cios","year":"2007","unstructured":"Cios KJ, Pedrycz W, Swiniarski RW, Kurgan LA (2007) Data mining: a knowledge discovery approach. Springer, New York"},{"key":"1488_CR14","doi-asserted-by":"crossref","unstructured":"Cohen WW (1995) Fast effective rule induction. In: Proceedings of the 12th international conference on machine learning, pp 115\u2013123","DOI":"10.1016\/B978-1-55860-377-6.50023-2"},{"key":"1488_CR15","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"TM Cover","year":"1967","unstructured":"Cover TM, Hart PE (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13:21\u201327","journal-title":"IEEE Trans Inf Theory"},{"key":"1488_CR16","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":"1","key":"1488_CR17","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.swevo.2011.02.002","volume":"1","author":"J Derrac","year":"2011","unstructured":"Derrac J, Garc\u00eda S, Molina D, Herrera F (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm Evolut Comput 1(1):3\u201318","journal-title":"Swarm Evolut Comput"},{"key":"1488_CR18","doi-asserted-by":"crossref","unstructured":"Dougherty J, Kohavi R, Sahami M (1995) Supervised and unsupervised discretization of continuous features. In: Proceedings of the 12th international conference machine learning, pp 194\u2013202","DOI":"10.1016\/B978-1-55860-377-6.50032-3"},{"issue":"3","key":"1488_CR19","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1023\/A:1007674919412","volume":"36","author":"T Elomaa","year":"1999","unstructured":"Elomaa T, Rousu J (1999) General and efficient multisplitting of numerical attributes. Mach Learn 36(3):201\u2013244","journal-title":"Mach Learn"},{"key":"1488_CR20","first-page":"87","volume":"8","author":"U Fayyad","year":"1992","unstructured":"Fayyad U, Irani K (1992) On the handling of continuous-valued attributes in decision tree generation. Mach Learn 8:87\u2013102","journal-title":"Mach Learn"},{"key":"1488_CR21","unstructured":"Fayyad UM, Irani KB (1993) Multi-interval discretization of continuous-valued attributes for classification learning. In: Proceedings of the 13th international joint conference on uncertainly in artificial intelligence, pp 1022\u20131029"},{"issue":"8","key":"1488_CR22","doi-asserted-by":"crossref","first-page":"1268","DOI":"10.1016\/j.ins.2009.12.014","volume":"180","author":"A Fern\u00e1ndez","year":"2010","unstructured":"Fern\u00e1ndez A, del Jesus MJ, Herrera F (2010) On the 2-tuples based genetic tuning performance for fuzzy rule based classification systems in imbalanced data-sets. Inf Sci 180(8):1268\u20131291","journal-title":"Inf Sci"},{"key":"1488_CR23","unstructured":"Frank E, Witten IH (1998) Generating accurate rule sets without global optimization. In: Proceedings of the 15th international conference on machine learning, pp 144\u2013151"},{"key":"1488_CR24","unstructured":"Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: Proceedings of the 13th international conference on machine learning, pp 148\u2013156"},{"issue":"200","key":"1488_CR25","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","volume":"32","author":"M Friedman","year":"1937","unstructured":"Friedman M (1937) The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc 32(200):675\u2013701","journal-title":"J Am Stat Assoc"},{"key":"1488_CR26","doi-asserted-by":"crossref","unstructured":"Galar M, Fern\u00e1ndez A, Barrenechea E, Bustince H, Herrera F (2012) A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid- based approaches. IEEE Trans Syst Man Cybern Part C Appl Revi 42(4):463\u2013484","DOI":"10.1109\/TSMCC.2011.2161285"},{"issue":"10","key":"1488_CR27","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(10):2044\u20132064","journal-title":"Inf Sci"},{"key":"1488_CR28","first-page":"2677","volume":"9","author":"S Garc\u00eda","year":"2008","unstructured":"Garc\u00eda S, Herrera F (2008) An extension on statistical comparisons of classifiers over multiple data sets for all pairwise comparisons. J Mach Learn Res 9:2677\u20132694","journal-title":"J Mach Learn Res"},{"issue":"4","key":"1488_CR29","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1109\/TKDE.2012.35","volume":"25","author":"S Garc\u00eda","year":"2013","unstructured":"Garc\u00eda S, Luengo J, Saez J, Lopez V, Herrera F (2013) A survey of discretization techniques: taxonomy and empirical analysis in supervised learning. IEEE Trans Knowl Data Eng 25(4):734\u2013750","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"1488_CR30","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.knosys.2011.06.013","volume":"25","author":"V Garc\u00eda","year":"2012","unstructured":"Garc\u00eda V, S\u00e1nchez JS, Mollineda RA (2012) On the effectiveness of preprocessing methods when dealing with different levels of class imbalance. Knowl Based Syst 25(1):13\u201321","journal-title":"Knowl Based Syst"},{"key":"1488_CR31","doi-asserted-by":"crossref","first-page":"5327","DOI":"10.1016\/j.eswa.2008.06.063","volume":"36","author":"L Gonzalez-Abril","year":"2009","unstructured":"Gonzalez-Abril L, Cuberos FJ, Velasco F, Ortega JA (2009) Ameva: an autonomous discretization algorithm. Expert Syst Appl 36:5327\u20135332","journal-title":"Expert Syst Appl"},{"key":"1488_CR32","doi-asserted-by":"crossref","unstructured":"Grzymala-Busse JW (2009) A multiple scanning strategy for entropy based discretization. In: Proceedings of foundations of intelligent systems, Lecture notes in computer science, vol 5722. pp 25\u201334","DOI":"10.1007\/978-3-642-04125-9_6"},{"key":"1488_CR33","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.3390\/e15051486","volume":"15","author":"JW Grzymala-Busse","year":"2013","unstructured":"Grzymala-Busse JW (2013) Discretization based on entropy and multiple scanning. Entropy 15:1486\u20131502","journal-title":"Entropy"},{"key":"1488_CR34","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemannr P, Witten IH (2009) The WEKA data mining software: an update. SIGKDD Explor 11:10\u201318","journal-title":"SIGKDD Explor"},{"issue":"9","key":"1488_CR35","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263\u20131284","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1488_CR36","first-page":"65","volume":"6","author":"S Holm","year":"1979","unstructured":"Holm S (1979) A simple sequentially rejective multiple test procedure. Scand J Stat 6:65\u201370","journal-title":"Scand J Stat"},{"issue":"3","key":"1488_CR37","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"},{"key":"1488_CR38","unstructured":"Huang W (1997) Discretization of continuous attributes for inductive machine learning. University of Toledo"},{"issue":"11","key":"1488_CR39","doi-asserted-by":"crossref","first-page":"3107","DOI":"10.1016\/j.cor.2005.01.022","volume":"33","author":"D Janssens","year":"2006","unstructured":"Janssens D, Brijs T, Vanhoof K, Wets G (2006) Evaluating the performance of cost-based discretization versus entropy- and error-based discretization. Comput Op Res 33(11):3107\u20133123","journal-title":"Comput Op Res"},{"key":"1488_CR40","unstructured":"John G, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: Proceedings of the eleventh conference on uncertainty in artificial intelligence, pp 338\u2013345"},{"issue":"4","key":"1488_CR41","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1109\/TSMCB.2006.870610","volume":"36","author":"H Kaizhu","year":"2006","unstructured":"Kaizhu H, Haiqin Y, Irwinng K, Lyu MR (2006) Imbalanced learning with a biased minimax probability machine. IEEE Trans Syst Man Cybern Part B Cybernetics 36(4):913\u2013923","journal-title":"IEEE Trans Syst Man Cybern Part B Cybernetics"},{"key":"1488_CR42","unstructured":"Kerber R (1992) ChiMerge: discretization of numeric attributes. In: Proceedings of the 10th national conference on artificial intelligence, pp 123\u2013128"},{"key":"1488_CR43","unstructured":"Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence, vol 2. pp 1137\u20131143"},{"issue":"1","key":"1488_CR44","first-page":"47","volume":"32","author":"S Kotsiantis","year":"2006","unstructured":"Kotsiantis S, Kanellopoulos D (2006) Discretization techniques: a recent survey. GESTS Int Trans Comput Sci Eng 32(1):47\u201358","journal-title":"GESTS Int Trans Comput Sci Eng"},{"issue":"2","key":"1488_CR45","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1109\/TKDE.2004.1269594","volume":"16","author":"LA Kurgan","year":"2004","unstructured":"Kurgan LA, Cios KJ (2004) CAIM discretization algorithm. IEEE Trans Knowl Data Eng 16(2):145\u2013153","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"1488_CR46","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/TSMCB.2005.852983","volume":"36","author":"LA Kurgan","year":"2006","unstructured":"Kurgan LA, Cios KJ, Dick S (2006) Highly scalable and robust rule learner: performance evaluation and comparison. IEEE Trans Syst Man Cybern Part B Cybern 36(1):32\u201353","journal-title":"IEEE Trans Syst Man Cybern Part B Cybern"},{"key":"1488_CR47","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1007\/978-3-540-27868-9_83","volume":"3138","author":"T Landgrebe","year":"2004","unstructured":"Landgrebe T, Paclik P, Tax D, Verzakov S, Duin R (2004) Cost-based classifier evaluation for imbalanced problems. Lect Notes Comput Sci 3138:762\u2013770","journal-title":"Lect Notes Comput Sci"},{"key":"1488_CR48","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1109\/69.617056","volume":"9","author":"H Liu","year":"1997","unstructured":"Liu H, Setiono R (1997) Feature selection via discretization. IEEE Trans Knowl Data Eng 9:642\u2013645","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1488_CR49","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.ins.2013.07.007","volume":"250","author":"V L\u00f3pez","year":"2013","unstructured":"L\u00f3pez V, Fern\u00e1ndez A, Garc\u00eda S, Palade V, Herrera F (2013) An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics. Inf Sci 250:113\u2013141","journal-title":"Inf Sci"},{"key":"1488_CR50","doi-asserted-by":"crossref","unstructured":"Luengo J, Fern\u00e1ndez A, Garc\u00eda S, Herrera F (2011) Addressing data complexity for imbalanced data sets: analysis of smote-based oversampling and evolutionary undersampling. Soft Comput 15:1909\u20131936","DOI":"10.1007\/s00500-010-0625-8"},{"key":"1488_CR51","unstructured":"Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kauffman Publishers, Burlington"},{"issue":"9","key":"1488_CR52","doi-asserted-by":"crossref","first-page":"1230","DOI":"10.1109\/TKDE.2008.66","volume":"20","author":"FJ Ruiz","year":"2008","unstructured":"Ruiz FJ, Angulo C, Agell N (2008) IDD: a supervised interval distance-based method for discretization. IEEE Trans Knowl Data Eng 20(9):1230\u20131238","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"1488_CR53","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1109\/TKDE.2002.1000349","volume":"14","author":"F Tay","year":"2002","unstructured":"Tay F, Shen L (2002) A modified Chi2 algorithm for discretization. IEEE Trans Knowl Data Eng 14(2):666\u2013670","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"1488_CR54","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1016\/j.ins.2007.09.004","volume":"178","author":"CJ Tsai","year":"2008","unstructured":"Tsai CJ, Lee CI, Yang WP (2008) A discretization algorithm based on class-attribute contingency coefficient. Inf Sci 178(3):714\u2013731","journal-title":"Inf Sci"},{"issue":"3\u20134","key":"1488_CR55","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.ecolmodel.2007.10.005","volume":"212","author":"TS Wiens","year":"2008","unstructured":"Wiens TS, Dale BC, Boyce MS, Kershaw GP (2008) Three way $$k$$ k -fold cross-validation of resource selection functions. Ecol Model 212(3\u20134):244\u2013255","journal-title":"Ecol Model"},{"issue":"6","key":"1488_CR56","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon F (1945) Individual comparisons by ranking methods. Biom Bull 1(6):80\u201383","journal-title":"Biom Bull"},{"issue":"2","key":"1488_CR57","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1109\/T-C.1975.224183","volume":"24","author":"A Wong","year":"1975","unstructured":"Wong A, Liu TS (1975) Typicality, diversity, and feature pattern of an ensemble. IEEE Trans Comput 24(2):158\u2013181","journal-title":"IEEE Trans Comput"},{"issue":"4","key":"1488_CR58","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1080\/00207720903572455","volume":"42","author":"P Yang","year":"2011","unstructured":"Yang P, Li JS, Huang YX (2011) HDD: a hypercube division-based algorithm for discretisation. Int J Syst Sci 42(4):557\u2013566","journal-title":"Int J Syst Sci"},{"key":"1488_CR59","unstructured":"Yang Y, Webb GI, Wu X (2010) Discretization methods. In: Proceedings of data mining and knowledge discovery handbook, pp 101\u2013116"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-014-1488-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00500-014-1488-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-014-1488-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,16]],"date-time":"2019-08-16T15:08:37Z","timestamp":1565968117000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00500-014-1488-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10,24]]},"references-count":59,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,1]]}},"alternative-id":["1488"],"URL":"https:\/\/doi.org\/10.1007\/s00500-014-1488-1","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,10,24]]}}}