{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:34:16Z","timestamp":1776278056261,"version":"3.50.1"},"reference-count":96,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,3,2]],"date-time":"2019-03-02T00:00:00Z","timestamp":1551484800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,3,2]],"date-time":"2019-03-02T00:00:00Z","timestamp":1551484800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Adv Data Anal Classif"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s11634-019-00354-x","type":"journal-article","created":{"date-parts":[[2019,3,2]],"date-time":"2019-03-02T03:30:26Z","timestamp":1551497426000},"page":"677-745","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Enhancing techniques for learning decision trees from imbalanced data"],"prefix":"10.1007","volume":"14","author":[{"given":"Ikram","family":"Chaabane","sequence":"first","affiliation":[]},{"given":"Radhouane","family":"Guermazi","sequence":"additional","affiliation":[]},{"given":"Mohamed","family":"Hammami","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,3,2]]},"reference":[{"issue":"2\u20133","key":"354_CR1","first-page":"255","volume":"17","author":"J Alcala-Fdez","year":"2011","unstructured":"Alcala-Fdez J, Fernandez A, Luengo J, Derrac J, Garcia S (2011) KEEL data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. Multiple-Valued Logic Soft Comput 17(2\u20133):255\u2013287","journal-title":"Multiple-Valued Logic Soft Comput"},{"issue":"1","key":"354_CR2","doi-asserted-by":"publisher","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 behavior of several methods for balancing machine learning training data. SIGKDD Explor 6(1):20\u201329. \n                  https:\/\/doi.org\/10.1145\/1007730.1007735","journal-title":"SIGKDD Explor"},{"issue":"5","key":"354_CR3","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1016\/j.patcog.2014.10.032","volume":"48","author":"C Beyan","year":"2015","unstructured":"Beyan C, Fisher R (2015) Classifying imbalanced data sets using similarity based hierarchical decomposition. Pattern Recognit 48(5):1653\u20131672","journal-title":"Pattern Recognit"},{"issue":"1","key":"354_CR4","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/1471-2105-14-106","volume":"14","author":"R Blagus","year":"2013","unstructured":"Blagus R, Lusa L (2013) SMOTE for high-dimensional class-imbalanced data. BMC Bioinformatics 14(1):106. \n                  https:\/\/doi.org\/10.1186\/1471-2105-14-106","journal-title":"BMC Bioinformatics"},{"key":"354_CR5","doi-asserted-by":"publisher","unstructured":"Blaszczynski J, Stefanowski J (2015) Neighbourhood sampling in bagging for imbalanced data. Neurocomputing 150:529\u2013542. \n                  https:\/\/doi.org\/10.1016\/j.neucom.2014.07.064\n                  \n                . \n                  http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0925231214012296","DOI":"10.1016\/j.neucom.2014.07.064"},{"key":"354_CR6","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1007\/978-3-642-13529-3_17","volume-title":"Rough sets and current trends in computing","author":"J Blaszczynski","year":"2010","unstructured":"Blaszczynski J, Deckert M, Stefanowski J, Wilk S (2010) Integrating selective pre-processing of imbalanced data with ivotes ensemble. In: Szczuka M, Kryszkiewicz M, Ramanna S, Jensen R, Hu Q (eds) Rough sets and current trends in computing. Springer, Berlin, pp 148\u2013157"},{"key":"354_CR7","unstructured":"Blaszczynski J, Stefanowski J, Idkowiak L (2013) Extending bagging for imbalanced data. In: Burduk R, Jackowski K, Kurzynski M, Wozniak M, Zolnierek A (eds) Proceedings of the 8th international conference on computer recognition systems CORES 2013, Springer International Publishing, Heidelberg, pp 269\u2013278"},{"key":"354_CR8","doi-asserted-by":"publisher","unstructured":"Bosch A, Zisserman A, Munoz X (2007) Image classification using random forests and ferns. In: 11th International conference on computer vision, IEEE, pp 1\u20138. \n                  https:\/\/doi.org\/10.1109\/ICCV.2007.4409066","DOI":"10.1109\/ICCV.2007.4409066"},{"key":"354_CR9","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/BFb0026682","volume-title":"Machine learning: ECML-98","author":"JP Bradford","year":"1998","unstructured":"Bradford JP, Kunz C, Kohavi R, Brunk C, Brodley CE (1998) Pruning decision trees with misclassification costs. In: Nedellec C, Rouveirol C (eds) Machine learning: ECML-98. Springer, Berlin, pp 131\u2013136"},{"issue":"2","key":"354_CR10","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1023\/A:1018054314350","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predictors. Mach Learn 24(2):123\u2013140. \n                  https:\/\/doi.org\/10.1023\/A:1018054314350","journal-title":"Mach Learn"},{"issue":"1","key":"354_CR11","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332. \n                  https:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"key":"354_CR12","volume-title":"Classification and regression trees","author":"L Breiman","year":"1984","unstructured":"Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth and Brooks, Monterey"},{"key":"354_CR13","doi-asserted-by":"publisher","unstructured":"Bressoux P (2010) Mod\u00e9lisation statistique appliqu\u00e9e aux sciences sociales. M\u00e9thodes en sciences humaines, De Boeck Sup\u00e9rieur. \n                  https:\/\/doi.org\/10.3917\/dbu.bress.2010.01\n                  \n                . \n                  https:\/\/www.cairn.info\/modelisation-statistique-appliquee-aux-sciences-so--9782804157142.htm","DOI":"10.3917\/dbu.bress.2010.01"},{"issue":"1","key":"354_CR14","first-page":"75","volume":"8","author":"W Buntine","year":"1992","unstructured":"Buntine W, Niblett T (1992) A further comparison of splitting rules for decision-tree induction. Mach Learn 8(1):75\u201385","journal-title":"Mach Learn"},{"issue":"C","key":"354_CR15","doi-asserted-by":"publisher","first-page":"1542","DOI":"10.1016\/j.procs.2017.08.060","volume":"112","author":"I Chaabane","year":"2017","unstructured":"Chaabane I, Guermazi R, Hammami M (2017) Adapted pruning scheme for the framework of imbalanced data-sets. Procedia Comput Sci 112(C):1542\u20131553","journal-title":"Procedia Comput Sci"},{"key":"354_CR16","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1007\/0-387-25465-X_40","volume-title":"Data mining and knowledge discovery handbook","author":"NV Chawla","year":"2005","unstructured":"Chawla NV (2005) Data mining for imbalanced datasets: an overview. In: Maimon O, Rokach L (eds) Data mining and knowledge discovery handbook. Springer, Boston, pp 853\u2013867. \n                  https:\/\/doi.org\/10.1007\/0-387-25465-X_40"},{"key":"354_CR17","unstructured":"Chawla NV (2003) C4.5 and imbalanced data sets: investigating the effect of sampling method, probabilistic estimate, and decision tree structure. In: Proceedings of the ICML\u201903 workshop on class imbalances"},{"key":"354_CR18","doi-asserted-by":"publisher","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"},{"key":"354_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-540-39804-2_12","volume-title":"Knowledge discovery in databases: PKDD 2003","author":"NV Chawla","year":"2003","unstructured":"Chawla NV, Lazarevic A, Hall L, Bowyer K (2003) SMOTEBoost: improving prediction of the minority class in boosting. In: Lavrac N, Gamberger D, Todorovski L, Blockeel H (eds) Knowledge discovery in databases: PKDD 2003, vol 2838. Lecture Notes in Computer Science. Springer, Berlin, pp 107\u2013119"},{"issue":"3","key":"354_CR20","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1080\/10659360600787700","volume":"17","author":"J Chen","year":"2006","unstructured":"Chen J, Tsai C, Moon H, Ahn H, Young J, Chen C (2006) Decision threshold adjustment in class prediction. SAR QSAR Environ Res 17(3):337\u2013352. \n                  https:\/\/doi.org\/10.1080\/10659360600787700","journal-title":"SAR QSAR Environ Res"},{"issue":"6","key":"354_CR21","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1007\/s40846-015-0093-9","volume":"35","author":"LS Chen","year":"2015","unstructured":"Chen LS, Cai SJ (2015) Neural-network-based resampling method for detecting diabetes mellitus. J Med Biol Eng 35(6):824\u2013832. \n                  https:\/\/doi.org\/10.1007\/s40846-015-0093-9","journal-title":"J Med Biol Eng"},{"issue":"1","key":"354_CR22","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/s10618-011-0222-1","volume":"24","author":"DA Cieslak","year":"2012","unstructured":"Cieslak DA, Hoens TR, Chawla NV, Kegelmeyer WP (2012) Hellinger distance decision trees are robust and skew-insensitive. Data Min Knowl Discov 24(1):136\u2013158","journal-title":"Data Min Knowl Discov"},{"key":"354_CR23","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"Demsar 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":"354_CR24","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.swevo.2011.02.002","volume":"1","author":"J Derrac","year":"2011","unstructured":"Derrac J, Garcia 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 Evol Comput 1(1):3\u201318","journal-title":"Swarm Evol Comput"},{"issue":"C","key":"354_CR25","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.ins.2015.07.025","volume":"325","author":"Diez-Pastor Jf","year":"2015","unstructured":"Jf Diez-Pastor, Rodriguez JJ, Garcia-Osorio CI, Kuncheva LI (2015) Diversity techniques improve the performance of the best imbalance learning ensembles. Information Sci 325(C):98\u2013117. \n                  https:\/\/doi.org\/10.1016\/j.ins.2015.07.025","journal-title":"Information Sci"},{"key":"354_CR26","unstructured":"Elkan C (2001) The foundations of cost-sensitive learning. In: Proceedings of the 17th international joint conference on artificial intelligence, vol 2. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, IJCAI\u201901, pp 973\u2013978"},{"issue":"1","key":"354_CR27","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119\u2013139. \n                  https:\/\/doi.org\/10.1006\/jcss.1997.1504","journal-title":"J Comput Syst Sci"},{"issue":"4","key":"354_CR28","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1109\/TSMCC.2011.2161285","volume":"42","author":"M Galar","year":"2012","unstructured":"Galar M, Fernandez 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 C Appl Rev 42(4):463\u2013484","journal-title":"IEEE Trans Syst Man Cybern C Appl Rev"},{"key":"354_CR29","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.ins.2016.02.056","volume":"354","author":"M Galar","year":"2016","unstructured":"Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F (2016) Ordering-based pruning for improving the performance of ensembles of classifiers in the framework of imbalanced datasets. Information Sci 354:178\u2013196","journal-title":"Information Sci"},{"issue":"4","key":"354_CR30","first-page":"42","volume":"2","author":"V Ganganwar","year":"2012","unstructured":"Ganganwar V (2012) An overview of classification algorithms for imbalanced datasets. Int J Emerg Technol Adv Eng 2(4):42\u201347","journal-title":"Int J Emerg Technol Adv Eng"},{"key":"354_CR31","doi-asserted-by":"publisher","unstructured":"Garcia S, Fernandez 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. Information Sci 180(10):2044\u20132064. \n                  https:\/\/doi.org\/10.1016\/j.ins.2009.12.010\n                  \n                . \n                  http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0020025509005404","DOI":"10.1016\/j.ins.2009.12.010"},{"key":"354_CR32","doi-asserted-by":"crossref","unstructured":"Garcia V, Mollineda RA, Sanchez JS (2009) Pattern recognition and image analysis: 4th Iberian conference, IbPRIA 2009 Povoa de Varzim, Portugal, June 10\u201312, 2009 Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, chap Index of Balanced Accuracy: A Performance Measure for Skewed Class Distributions, pp 441\u2013448","DOI":"10.1007\/978-3-642-02172-5_57"},{"key":"354_CR33","unstructured":"Geddes K, Gonnet G (1981\u20132014) Maplesoft (18.02), a division of Waterloo Maple Inc., Waterloo, Ontario. \n                  www.maplesoft.com"},{"issue":"1","key":"354_CR34","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3\u201342. \n                  https:\/\/doi.org\/10.1007\/s10994-006-6226-1","journal-title":"Mach Learn"},{"key":"354_CR35","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1007\/978-3-642-04962-0_53","volume-title":"Computational intelligence and intelligent systems, communications in computer and information science","author":"Q Gu","year":"2009","unstructured":"Gu Q, Zhu L, Cai Z (2009) Evaluation measures of the classification performance of imbalanced data sets. In: Cai Z, Li Z, Kang Z, Liu Y (eds) Computational intelligence and intelligent systems, communications in computer and information science, vol 51. Springer, Berlin, pp 461\u2013471"},{"key":"354_CR36","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.ins.2018.07.076","volume":"467","author":"R Guermazi","year":"2018","unstructured":"Guermazi R, Chaabane I, Hammami M (2018) AECID: asymmetric entropy for classifying imbalanced data. Information Sci 467:373\u2013397","journal-title":"Information Sci"},{"key":"354_CR37","doi-asserted-by":"crossref","unstructured":"Han H, Wang W, Mao B (2005) Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: Huang DS, Zhang XP, Huang GB (eds) ICIC (1), Springer, Lecture Notes in Computer Science, vol 3644, pp 878\u2013887","DOI":"10.1007\/11538059_91"},{"key":"354_CR38","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1109\/TIT.1968.1054155","volume":"14","author":"P Hart","year":"1968","unstructured":"Hart P (1968) The condensed nearest neighbor rule. IEEE Trans Inf Theory 14:515\u2013516","journal-title":"IEEE Trans Inf Theory"},{"issue":"9","key":"354_CR39","doi-asserted-by":"publisher","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. \n                  https:\/\/doi.org\/10.1109\/TKDE.2008.239","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"354_CR40","unstructured":"Hettich S, Bay SD (1999) The uci kdd archive. [\n                  http:\/\/kdd.ics.uci.edu\n                  \n                ]"},{"issue":"56","key":"354_CR41","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1002\/sam.10061","volume":"2","author":"S Hido","year":"2009","unstructured":"Hido S, Kashima H, Takahashi Y (2009) Roughly balanced bagging for imbalanced data. Stat Anal Data Min 2(56):412\u2013426. \n                  https:\/\/doi.org\/10.1002\/sam.10061","journal-title":"Stat Anal Data Min"},{"key":"354_CR42","doi-asserted-by":"crossref","unstructured":"Japkowicz N, Stephen S (2002) The class imbalance problem: a systematic study. Intell Data Anal 6(5):429\u2013449. \n                  http:\/\/dl.acm.org\/citation.cfm?id=1293951.1293954","DOI":"10.3233\/IDA-2002-6504"},{"key":"354_CR43","unstructured":"Kang S, Ramamohanarao K (2014) Advances in knowledge discovery and data mining: 18th Pacific-Asia conference, PAKDD 2014, Tainan, Taiwan, May 13\u201316, 2014. Proceedings, Part I, Springer International Publishing, Cham, chap A Robust Classifier for Imbalanced Datasets, pp 212\u2013223"},{"key":"354_CR44","unstructured":"Kraiem MS, Moreno MN (2017) Effectiveness of basic and advanced sampling strategies on the classification of imbalanced data. A comparative study using classical and novel metrics. In: Martinez\u00a0de Pison FJ, Urraca R, Quintien H, Corchado E (eds) Hybrid artificial intelligent systems, Springer International Publishing, Cham, pp 233\u2013245"},{"key":"354_CR45","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1016\/j.asoc.2013.08.014","volume":"14","author":"B Krawczyk","year":"2014","unstructured":"Krawczyk B, Wozniak M, Schaefer G (2014) Cost-sensitive decision tree ensembles for effective imbalanced classification. Appl Soft Comput 14:554\u2013562. \n                  https:\/\/doi.org\/10.1016\/j.asoc.2013.08.014","journal-title":"Appl Soft Comput"},{"key":"354_CR46","unstructured":"Lallich S, Lenca P, Vaillant B (2007) Construction d\u2019une entropie d\u00e9centr\u00e9e pour l\u2019apprentissage supervis\u00e9. In: EGC 2007 : 7\u00e8mes journ\u00e9es francophones \u201dExtraction et gestion des connaissances\u201d, Atelier Qualit\u00e9 des Donn\u00e9es et des Connaissances, Namur, Belgique, pp 45\u201354"},{"key":"354_CR47","doi-asserted-by":"publisher","unstructured":"Lango M, Stefanowski J (2018) Multi-class and feature selection extensions of roughly balanced bagging for imbalanced data. J Intell Inf Syst pp 97\u2013127. \n                  https:\/\/doi.org\/10.1007\/s10844-017-0446-7","DOI":"10.1007\/s10844-017-0446-7"},{"key":"354_CR48","unstructured":"Lemaitre G, Nogueira F, Aridas CK (2017) Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. J Mach Learn Res 18(17):1\u20135. \n                  http:\/\/jmlr.org\/papers\/v18\/16-365.html"},{"key":"354_CR49","doi-asserted-by":"crossref","unstructured":"Lenca P, Lallich S, Do TN, Pham NK (2008) A comparison of different off-centered entropies to deal with class imbalance for decision trees. In: Advances in knowledge discovery and data mining. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 634\u2013643","DOI":"10.1007\/978-3-540-68125-0_59"},{"issue":"3","key":"354_CR50","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1080\/03610920903140247","volume":"39","author":"P Lenca","year":"2010","unstructured":"Lenca P, Lallich S, Vaillant B (2010) Construction of an off-centered entropy for the supervised learning of imbalanced classes: some first results. Commun Stat Theory Methods 39(3):493\u2013507","journal-title":"Commun Stat Theory Methods"},{"key":"354_CR51","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1007\/978-3-319-03680-9_38","volume-title":"AI 2013: Adv Artif Intell","author":"G Liang","year":"2013","unstructured":"Liang G (2013) An effective method for imbalanced time series classification: hybrid sampling. In: Cranefield S, Nayak A (eds) AI 2013: Adv Artif Intell. Springer International Publishing, Cham, pp 374\u2013385"},{"issue":"Supplement C","key":"354_CR52","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.ins.2017.05.008","volume":"409","author":"W Lin","year":"2017","unstructured":"Lin W, Tsai CF, Hu Y, Jhang J (2017) Clustering-based undersampling in class-imbalanced data. Information Sci 409(Supplement C):17\u201326","journal-title":"Information Sci"},{"key":"354_CR53","doi-asserted-by":"publisher","unstructured":"Ling CX, Sheng VS (2010) Cost-sensitive learning. In: Encyclopedia of machine learning. pp 231\u2013235. \n                  https:\/\/doi.org\/10.1007\/978-0-387-30164-8_181","DOI":"10.1007\/978-0-387-30164-8_181"},{"key":"354_CR54","doi-asserted-by":"crossref","unstructured":"Ling CX, Yang Q, Wang J, Zhang S (2004) Decision trees with minimal costs. In: Proceedings of the twenty-first international conference on machine learning. ACM, New York, NY, USA, ICML \u201904, pp 69\u201376","DOI":"10.1145\/1015330.1015369"},{"issue":"1","key":"354_CR55","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1023\/A:1022609119415","volume":"15","author":"W Liu","year":"1994","unstructured":"Liu W, White A (1994) The importance of attribute selection measures in decision tree induction. Mach Learn 15(1):25\u201341. \n                  https:\/\/doi.org\/10.1023\/A:1022609119415","journal-title":"Mach Learn"},{"key":"354_CR56","doi-asserted-by":"crossref","unstructured":"Liu W, Chawla S, Cieslak DA, Chawla NV (2010) A robust decision tree algorithm for imbalanced data sets, pp 766\u2013777","DOI":"10.1137\/1.9781611972801.67"},{"key":"354_CR57","unstructured":"Liu XY, Zhou ZH (2013) Imbalanced learning: foundations, algorithms, and applications. Wiley-IEEE Press, chap Ensemble Methods for Class Imbalance Learning, pp 61\u201382"},{"issue":"2","key":"354_CR58","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TSMCB.2008.2007853","volume":"39","author":"XY Liu","year":"2009","unstructured":"Liu XY, Wu J, Zhou ZH (2009) Exploratory undersampling for class-imbalance learning. IEEE Trans Syst Man Cybern B 39(2):539\u2013550. \n                  https:\/\/doi.org\/10.1109\/TSMCB.2008.2007853","journal-title":"IEEE Trans Syst Man Cybern B"},{"key":"354_CR59","doi-asserted-by":"publisher","unstructured":"Lyon R, Brooke J, Knowles J, Stappers B (2014) Hellinger distance trees for imbalanced streams. In: 22nd International conference on pattern recognition. pp 1969\u20131974. \n                  https:\/\/doi.org\/10.1109\/ICPR.2014.344","DOI":"10.1109\/ICPR.2014.344"},{"key":"354_CR60","unstructured":"Marcellin S, Zighed DA, Ritschard G (2006a) An asymmetric entropy measure for decision trees. In: 11th Conference on information processing and management of uncertainty in knowledge-based systems. IPMU 2006, pp 1292 \u2013 1299"},{"key":"354_CR61","first-page":"975","volume-title":"Computional statistics (COMPSTAT 06)","author":"S Marcellin","year":"2006","unstructured":"Marcellin S, Zighed DA, Ritschard G (2006) Detection of breast cancer using an asymmetric entropy measure. In: Rizzi A, Vichi M (eds) Computional statistics (COMPSTAT 06), vol XXV. Springer, Heidelberg, pp 975\u2013982"},{"key":"354_CR62","doi-asserted-by":"crossref","unstructured":"Marcellin S, Zighed DA, Ritschard G (2008) Evaluating decision trees grown with asymmetric entropies. In: Foundations of intelligent systems, 17th international symposium, ISMIS 2008, Toronto, Canada, May 20\u201323, pp 58\u201367","DOI":"10.1007\/978-3-540-68123-6_6"},{"key":"354_CR63","doi-asserted-by":"publisher","unstructured":"Meng YA, Yu Y, Cupples LA, Farrer LA, Lunetta KL (2009) Performance of random forest when SNPs are in linkage disequilibrium. BMC Bioinformatics 10(1). \n                  https:\/\/doi.org\/10.1186\/1471-2105-10-78","DOI":"10.1186\/1471-2105-10-78"},{"issue":"3","key":"354_CR64","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1007\/s10844-015-0368-1","volume":"46","author":"K Napierala","year":"2016","unstructured":"Napierala K, Stefanowski J (2016) Types of minority class examples and their influence on learning classifiers from imbalanced data. J Intell Inf Syst 46(3):563\u2013597. \n                  https:\/\/doi.org\/10.1007\/s10844-015-0368-1","journal-title":"J Intell Inf Syst"},{"key":"354_CR65","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-642-13529-3_18","volume-title":"Rough Sets Current Trends Comput","author":"K Napierala","year":"2010","unstructured":"Napierala K, Stefanowski J, Wilk S (2010) Learning from imbalanced data in presence of noisy and borderline examples. In: Szczuka M, Kryszkiewicz M, Ramanna S, Jensen R, Hu Q (eds) Rough Sets Current Trends Comput. Springer, Berlin Heidelberg, pp 158\u2013167"},{"issue":"1","key":"354_CR66","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TKDE.2012.255","volume":"26","author":"Y Park","year":"2014","unstructured":"Park Y, Ghosh J (2014) Ensembles of $$({\\alpha })$$-trees for imbalanced classification problems. IEEE Trans Knowl Data Eng 26(1):131\u2013143","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"354_CR67","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"354_CR68","unstructured":"Pham NK, Do TN, Lenca P, Lallich S (2008) Using local node information in decision trees: coupling a local labeling rule with an off-centered entropy. In: Proceedings of the international conference on data mining, July 14\u201317, 2008, Las Vegas, USA, pp 117\u2013123"},{"key":"354_CR69","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1613\/jair.1199","volume":"19","author":"FJ Provost","year":"2003","unstructured":"Provost FJ, Weiss GM (2003) Learning when training data are costly: the effect of class distribution on tree induction. J Artif Intell Res 19:315\u2013354 \n                  arXiv:1106.4557","journal-title":"J Artif Intell Res"},{"key":"354_CR70","doi-asserted-by":"crossref","unstructured":"Rayhan F, Ahmed S, Mahbub A, Jani MR, Shatabda S, Farid DM, Rahman CM (2017) MEBoost: mixing estimators with boosting for imbalanced data classification. In: International conference on software, knowledge, information management and applications (SKIMA), vol 11. IEEE, pp 1\u20136","DOI":"10.1109\/SKIMA.2017.8294128"},{"key":"354_CR71","unstructured":"Ritschard G, Zighed DA, Marcellin S (2007) Donn\u00e9es d\u00e9s\u00e9quilibr\u00e9es, entropie d\u00e9centr\u00e9e et indice d\u2019implication. In: Nouveaux apports th\u00e9oriques \u00e0 l\u2019analyse statistique implicative et applications, ASI4, Departament de Matematiques, Universitat Jaume I, pp 315\u2013327"},{"key":"354_CR72","doi-asserted-by":"publisher","unstructured":"Rodriguez-Fdez I, Canosa A, Mucientes M, Bugarin A (2015) STAC: a web platform for the comparison of algorithms using statistical tests. In: 2015 IEEE international conference on fuzzy systems, pp 1\u20138. \n                  https:\/\/doi.org\/10.1109\/FUZZ-IEEE.2015.7337889","DOI":"10.1109\/FUZZ-IEEE.2015.7337889"},{"key":"354_CR73","unstructured":"Ryan\u00a0Hoens T, Chawla N (2013) Imbalanced learning: foundations, algorithms, and applications. Wiley-IEEE Press, chap Imbalanced Datasets: From Sampling to Classifiers, pp 43\u201359"},{"issue":"Supplement C","key":"354_CR74","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.ins.2014.08.051","volume":"291","author":"JA Saez","year":"2015","unstructured":"Saez JA, Luengo J, Stefanowsk J, Herrera F (2015) SMOTE\u2013IPF: addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering. Information Sci 291(Supplement C):184\u2013203","journal-title":"Information Sci"},{"issue":"379\u2013423","key":"354_CR75","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1002\/j.1538-7305.1948.tb00917.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27(379\u2013423):623\u2013656","journal-title":"Bell Syst Tech J"},{"key":"354_CR76","doi-asserted-by":"crossref","unstructured":"Shen A, Tong R, Deng Y (2007) Application of classification models on credit card fraud detection. In: 2007 International conference on service systems and service management. pp 1\u20134","DOI":"10.1109\/ICSSSM.2007.4280163"},{"key":"354_CR77","unstructured":"Sheng VS, Ling CX (2006) Thresholding for making classifiers cost-sensitive. In: Proceedings of the 21st national conference on artificial intelligence, vol 1. AAAI Press, pp 476\u2013481"},{"key":"354_CR78","first-page":"324","volume":"2009","author":"W Shuo","year":"2009","unstructured":"Shuo W, Xin Y (2009) Diversity analysis on imbalanced data sets by using ensemble models. IEEE Symp Comput Intell Data Min 2009:324\u2013331","journal-title":"IEEE Symp Comput Intell Data Min"},{"key":"354_CR79","unstructured":"Singh A, Liu J, Guttag J (2010) Discretization of continuous ECG based risk metrics using asymmetric and warped entropy measures. In: 2010 Computing in cardiology. pp 473\u2013476"},{"key":"354_CR80","doi-asserted-by":"publisher","unstructured":"Son\u00a0Lam P, Abdesselam B, Giang HN (2009) Pattern recognition, chap Learning pattern classification tasks with imbalanced data sets, pp 193\u2013208. \n                  https:\/\/doi.org\/10.5772\/7544","DOI":"10.5772\/7544"},{"key":"354_CR81","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/978-3-642-28699-5_11","volume-title":"Overlapping, rare examples and class decomposition in learning classifiers from imbalanced data","author":"J Stefanowski","year":"2013","unstructured":"Stefanowski J (2013) Overlapping, rare examples and class decomposition in learning classifiers from imbalanced data. Springer, Berlin, pp 277\u2013306. \n                  https:\/\/doi.org\/10.1007\/978-3-642-28699-5_11"},{"key":"354_CR82","first-page":"333","volume-title":"Dealing with data difficulty factors while learning from imbalanced data","author":"J Stefanowski","year":"2016","unstructured":"Stefanowski J (2016) Dealing with data difficulty factors while learning from imbalanced data. Springer International Publishing, Cham, pp 333\u2013363"},{"key":"354_CR83","doi-asserted-by":"publisher","unstructured":"Sun Y, Kamel MS, Wong A, Wang Y (2007) Cost-sensitive boosting for classification of imbalanced data. Pattern Recognit 40(12):3358\u20133378. \n                  https:\/\/doi.org\/10.1016\/j.patcog.2007.04.009\n                  \n                . \n                  http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320307001835","DOI":"10.1016\/j.patcog.2007.04.009"},{"key":"354_CR84","doi-asserted-by":"crossref","unstructured":"Thai-Nghe N, Gantner Z, Schmidt-Thieme L (2011) A new evaluation measure for learning from imbalanced data. In: The 2011 international joint conference on neural networks (IJCNN). pp 537\u2013542","DOI":"10.1109\/IJCNN.2011.6033267"},{"issue":"6","key":"354_CR85","first-page":"448","volume":"SMC\u20136","author":"I Tomek","year":"1976","unstructured":"Tomek I (1976) An experiment with the edited nearest-neighbor rule. IEEE Trans Syst Man Cybern SMC\u20136(6):448\u2013452","journal-title":"IEEE Trans Syst Man Cybern"},{"issue":"1","key":"354_CR86","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1613\/jair.120","volume":"2","author":"PD Turney","year":"1995","unstructured":"Turney PD (1995) Cost-sensitive classification: empirical evaluation of a hybrid genetic decision tree induction algorithm. J Artif Intell Res 2(1):369\u2013409","journal-title":"J Artif Intell Res"},{"issue":"2","key":"354_CR87","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/2641190.2641198","volume":"15","author":"J Vanschoren","year":"2013","unstructured":"Vanschoren J, van Rijn JN, Bischl B, Torgo L (2013) Openml: networked science in machine learning. SIGKDD Explor 15(2):49\u201360. \n                  https:\/\/doi.org\/10.1145\/2641190.2641198","journal-title":"SIGKDD Explor"},{"issue":"1","key":"354_CR88","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/1007730.1007734","volume":"6","author":"GM Weiss","year":"2004","unstructured":"Weiss GM (2004) Mining with rarity: a unifying framework. SIGKDD Explor 6(1):7\u201319","journal-title":"SIGKDD Explor"},{"key":"354_CR89","first-page":"193","volume-title":"The impact of small disjuncts on classifier learning, annals of information systems","author":"GM Weiss","year":"2010","unstructured":"Weiss GM (2010) The impact of small disjuncts on classifier learning, annals of information systems, vol 8. Springer, Boston, pp 193\u2013226"},{"key":"354_CR90","doi-asserted-by":"crossref","unstructured":"Wilson DL (1972) Asymptotic properties of nearest neighbor rules using edited data. IEEE Trans Syst Man Cybern 2(3):408\u2013421. \n                  http:\/\/dblp.uni-trier.de\/db\/journals\/tsmc\/tsmc2.html#Wilson72","DOI":"10.1109\/TSMC.1972.4309137"},{"issue":"3","key":"354_CR91","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1023\/A:1007626913721","volume":"38","author":"DR Wilson","year":"2000","unstructured":"Wilson DR, Martinez TR (2000) Reduction techniques for instance-based learning algorithms. Mach Learn 38(3):257\u2013286","journal-title":"Mach Learn"},{"key":"354_CR92","doi-asserted-by":"publisher","unstructured":"Yagci AM, Aytekin T, Gurgen FS (2016) Balanced random forest for imbalanced data streams. In: 24th Signal processing and communication application conference (SIU). pp 1065\u20131068. \n                  https:\/\/doi.org\/10.1109\/SIU.2016.7495927","DOI":"10.1109\/SIU.2016.7495927"},{"issue":"3","key":"354_CR93","doi-asserted-by":"publisher","first-page":"5718","DOI":"10.1016\/j.eswa.2008.06.108","volume":"36","author":"SJ Yen","year":"2009","unstructured":"Yen SJ, Lee YS (2009) Cluster-based under-sampling approaches for imbalanced data distributions. Expert Syst Appl 36(3):5718\u20135727. \n                  https:\/\/doi.org\/10.1016\/j.eswa.2008.06.108","journal-title":"Expert Syst Appl"},{"key":"354_CR94","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1016\/j.procs.2016.04.216","volume":"83","author":"P Yildirim","year":"2016","unstructured":"Yildirim P (2016) Pattern classification with imbalanced and multiclass data for the prediction of albendazole adverse event outcomes. Procedia Comput Sci 83:1013\u20131018","journal-title":"Procedia Comput Sci"},{"key":"354_CR95","doi-asserted-by":"crossref","unstructured":"Zadrozny B, Langford J, Abe N (2003) Cost-sensitive learning by cost-proportionate example weighting. In: Proceedings of the third IEEE international conference on data mining. IEEE Computer Society, Washington, DC, USA, ICDM \u201903","DOI":"10.1109\/ICDM.2003.1250950"},{"key":"354_CR96","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/978-3-642-05183-8_2","volume-title":"Advances in intelligent information systems, studies in computational intelligence","author":"DA Zighed","year":"2010","unstructured":"Zighed DA, Ritschard G, Marcellin S (2010) Asymmetric and sample size sensitive entropy measures for supervised learning. In: Ras Z, Tsay L (eds) Advances in intelligent information systems, studies in computational intelligence, vol 265. Springer, Berlin, pp 27\u201342"}],"container-title":["Advances in Data Analysis and Classification"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11634-019-00354-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11634-019-00354-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11634-019-00354-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T09:13:55Z","timestamp":1602407635000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11634-019-00354-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,2]]},"references-count":96,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["354"],"URL":"https:\/\/doi.org\/10.1007\/s11634-019-00354-x","relation":{},"ISSN":["1862-5347","1862-5355"],"issn-type":[{"value":"1862-5347","type":"print"},{"value":"1862-5355","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,2]]},"assertion":[{"value":"20 January 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}