{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T18:29:53Z","timestamp":1716661793302},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,11,4]],"date-time":"2012-11-04T00:00:00Z","timestamp":1351987200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1007\/s13042-012-0125-5","type":"journal-article","created":{"date-parts":[[2012,11,3]],"date-time":"2012-11-03T01:25:39Z","timestamp":1351905939000},"page":"63-71","source":"Crossref","is-referenced-by-count":3,"title":["The effect of varying levels of class distribution on bagging for different algorithms: An empirical study"],"prefix":"10.1007","volume":"5","author":[{"given":"Guohua","family":"Liang","sequence":"first","affiliation":[]},{"given":"Xingquan","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Chengqi","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,11,4]]},"reference":[{"issue":"1","key":"125_CR1","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1145\/1007730.1007735","volume":"6","author":"GE Batista","year":"2004","unstructured":"Batista GE, Prati RC, Monard MC (2004) A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD Explor Newsl 6(1):20\u201329","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"125_CR2","doi-asserted-by":"crossref","unstructured":"Boehm O, Hardoon DR, Manevitz LM (2011) Classifying cognitive states of brain activity via one-class neural networks with feature selection by genetic algorithms. Int J Mach Learn Cybern 2:1\u201310","DOI":"10.1007\/s13042-011-0030-3"},{"issue":"7","key":"125_CR3","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 Recogn 30(7):1145\u20131159","journal-title":"Pattern Recogn"},{"issue":"2","key":"125_CR4","first-page":"123","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predictors. Mach Learn 24(2):123\u2013140","journal-title":"Mach Learn"},{"key":"125_CR5","doi-asserted-by":"crossref","unstructured":"Bunkhumpornpat C, Sinapiromsaran K, Lursinsap C (2009) Safe-level-SMOTE: Safe-Level-Synthetic Minority Over-Sampling Technique for handling the class imbalanced problem. In: Advances in Knowledge Discovery and Data Mining, vol 5476, pp 475\u2013482","DOI":"10.1007\/978-3-642-01307-2_43"},{"issue":"1","key":"125_CR6","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(1):321\u2013357","journal-title":"J Artif Intell Res"},{"key":"125_CR7","first-page":"107","volume":"2003","author":"NV Chawla","year":"2003","unstructured":"Chawla NV, Lazarevic A, Hall LO, Bowyer KW (2003) SMOTEBoost: improving prediction of the minority class in boosting. Paper presented at the PKDD 2003:107\u2013119","journal-title":"Paper presented at the PKDD"},{"issue":"1","key":"125_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1007730.1007733","volume":"6","author":"NV Chawla","year":"2004","unstructured":"Chawla NV, Japkowicz N, Kotcz A (2004) Editorial: special issue on learning from imbalanced data sets. ACM SIGKDD Explor Newsl 6(1):1\u20136","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"125_CR9","doi-asserted-by":"crossref","unstructured":"Cieslak D, Chawla N (2008) Learning decision trees for unbalanced data. Paper presented at the ECML PKDD 2008, pp 241\u2013256","DOI":"10.1007\/978-3-540-87479-9_34"},{"key":"125_CR10","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":"125_CR11","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1111\/j.0824-7935.2004.t01-1-00228.x","volume":"20","author":"A Estabrooks","year":"2004","unstructured":"Estabrooks A, Jo T, Japkowicz N (2004) A multiple resampling method for learning from imbalanced data sets. Comput Intell 20(1):18\u201336","journal-title":"Comput Intell"},{"key":"125_CR12","unstructured":"Fawcett T (2004) ROC graphs: Notes and practical considerations for researchers. Mach Learn 31 (HPL-2003-4):1\u201338"},{"issue":"8","key":"125_CR13","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861\u2013874","journal-title":"Pattern Recogn Lett"},{"key":"125_CR14","unstructured":"Guoxun H, Hui H, Wenyuan W (2005) An Over-sampling expert system for learning from imbalanced data sets. Paper presented at the International Conference on Neural Networks and Brain, 13\u201315 Oct, 537\u2013541"},{"key":"125_CR15","doi-asserted-by":"crossref","unstructured":"Han H, Wang WY, Mao BH (2005) Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. In: Advances in Intelligent Computing, vol 3644. Lecture notes in Computer Science, pp 878\u2013887","DOI":"10.1007\/11538059_91"},{"issue":"9","key":"125_CR16","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia AE (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263\u20131284","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"5\u20136","key":"125_CR17","doi-asserted-by":"crossref","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(5\u20136):412\u2013426","journal-title":"Stat Anal Data Min"},{"key":"125_CR18","doi-asserted-by":"crossref","unstructured":"Jun W, Shitong W, Chung F (2011) Positive and negative fuzzy rule system, extreme learning machine and image classification. Int J Mach Learn Cybern: 1\u201311","DOI":"10.1007\/s13042-011-0024-1"},{"key":"125_CR19","doi-asserted-by":"crossref","unstructured":"Kang P, Cho S (2006) EUS SVMs: Ensemble of under-sampled SVMs for data imbalance problems. Paper presented at the Neural Information Processing, pp 837\u2013846","DOI":"10.1007\/11893028_93"},{"key":"125_CR20","doi-asserted-by":"crossref","unstructured":"Koknar-Tezel S, Latecki LJ (2009) Improving SVM classification on imbalanced data sets in distance spaces. Paper presented at the 9th IEEE International Conference on Data Mining, 6\u20139 Dec, pp 259\u2013267","DOI":"10.1109\/ICDM.2009.59"},{"issue":"1","key":"125_CR21","first-page":"25","volume":"30","author":"S Kotsiantis","year":"2006","unstructured":"Kotsiantis S, Kanellopoulos D, Pintelas P (2006) Handling imbalanced datasets: a review. Int Trans Comput Sci Eng 30(1):25\u201336","journal-title":"Int Trans Comput Sci Eng"},{"key":"125_CR22","unstructured":"Liang G (2012) An investigation of sensitivity on bagging predictors: An empirical approach. Paper presented at the 26th AAAI Conference on Artificial Intelligence, AAAI 2012, Toronto, 22\u201326 July, 2439\u20132440"},{"key":"125_CR23","unstructured":"Liang G, Zhang C (2011) Empirical study of bagging predictors on medical data. Paper presented at the 9th Australian Data Mining Conference, AusDM 2011, Ballarat, Australia, pp 31\u201340"},{"key":"125_CR24","unstructured":"Liang G, Zhang C (2011) An empirical evaluation of bagging with different learning algorithms on imbalanced data. In: Proceedings of the 7th International Conference on Advanced Data Mining and Applications, ADMA 2011. 339\u2013352"},{"key":"125_CR25","doi-asserted-by":"crossref","unstructured":"Liang G, Zhang C (2012) An efficient and simple under-sampling technique for imbalanced time series classification. Paper presented at the ACM 21st Conference on Information and Knowledge Management, CIKM 2012, Maui Hawaii, 29th October \u2013 2nd November","DOI":"10.1145\/2396761.2398635"},{"key":"125_CR26","unstructured":"Liang G, Zhang C (2012) A comparative study of sampling methods and algorithms for imbalanced time series classification. Paper presented at the 25th Australasian Joint Conference on Artificial Intelligence, AI 2012, Sydney, 4th\u20137th December"},{"key":"125_CR27","doi-asserted-by":"crossref","unstructured":"Liang G, Zhu X, Zhang C (2011a) An empirical study of bagging predictors for different learning algorithms. Paper presented at the 25th AAAI Conference on Artificial Intelligence, AAAI 2011, San Francisco, 7\u201311 August, 1802\u20131803","DOI":"10.1609\/aaai.v25i1.8026"},{"key":"125_CR28","doi-asserted-by":"crossref","unstructured":"Liang G, Zhu X, Zhang C (2011b) An empirical study of bagging predictors for imbalanced data with different levels of class distribution. Paper presented at the 24th Australasian Joint Conference on Artificial Intelligence, AI 2011, Perth, 5th\u20138th December, 213\u2013222","DOI":"10.1007\/978-3-642-25832-9_22"},{"key":"125_CR29","doi-asserted-by":"crossref","unstructured":"Ling C, Huang J, Zhang H (2003) AUC: A better measure than accuracy in comparing learning algorithms. Paper presented at the AI 2003, pp 329\u2013341","DOI":"10.1007\/3-540-44886-1_25"},{"issue":"2","key":"125_CR30","doi-asserted-by":"crossref","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 Cybern 39(2):539\u2013550","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"125_CR31","doi-asserted-by":"crossref","unstructured":"Liu W, Chawla S, Cieslak DA, Chawla NV (2010) A robust decision tree algorithm for imbalanced data sets. Paper presented at the SIAM International Conference on Data Mining, SDM 2010, Columbus, Ohio, USA, April 29\u2013May 1, pp 766\u2013777","DOI":"10.1137\/1.9781611972801.67"},{"key":"125_CR32","unstructured":"Maloof M (2003) Learning when data sets are imbalanced and when costs are unequal and unknown. In: Proceedings of the ICML-2003 Workshop on Learning from Imbalanced Data Sets II, Washington"},{"issue":"2\u20133","key":"125_CR33","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.neunet.2007.12.031","volume":"21","author":"MA Mazurowski","year":"2008","unstructured":"Mazurowski MA, Habas PA, Zurada JM, Lo JY, Baker JA, Tourassi GD (2008) Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance. Neural Netw 21(2\u20133):427\u2013436","journal-title":"Neural Netw"},{"issue":"1","key":"125_CR34","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.inffus.2004.04.001","volume":"6","author":"P Melville","year":"2005","unstructured":"Melville P, Mooney RJ (2005) Creating diversity in ensembles using artificial data. Inform Fusion 6(1):99\u2013111","journal-title":"Inform Fusion"},{"key":"125_CR35","unstructured":"Mena L, Gonzalez J (2006) Machine learning for imbalanced datasets: Application in medical diagnostic. Paper presented at the Proceedings of the 19th International FLAIRS Conference, pp 574\u2013579"},{"key":"125_CR36","unstructured":"Merz C, Murphy P (2006) UCI Repository of Machine Learning Databases. http:\/\/archive.ics.uci.edu\/ml\/"},{"issue":"1","key":"125_CR37","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1145\/1007730.1007738","volume":"6","author":"C Phua","year":"2004","unstructured":"Phua C, Alahakoon D, Lee V (2004) Minority report in fraud detection: classification of skewed data. ACM SIGKDD Explor Newsl 6(1):50\u201359","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"125_CR38","unstructured":"Provost F, Fawcett T, Kohavi R (1998) The case against accuracy estimation for comparing induction algorithms. Paper presented at the 15th International Conference on Machine Learning, pp 445\u2013453"},{"issue":"1","key":"125_CR39","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/1147234.1147236","volume":"8","author":"RB Rao","year":"2006","unstructured":"Rao RB, Krishnan S, Niculescu RS (2006) Data mining for improved cardiac care. ACM SIGKDD Explor Newsl 8(1):3\u201310","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"125_CR40","doi-asserted-by":"crossref","unstructured":"Su CT, Hsiao YH (2007) An evaluation of the robustness of MTS for imbalanced data. IEEE Trans Knowl Data Eng:1321\u20131332","DOI":"10.1109\/TKDE.2007.190623"},{"issue":"12","key":"125_CR41","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 M, Wong A, Wang Y (2007) Cost-sensitive boosting for classification of imbalanced data. Pattern Recogn 40(12):3358\u20133378","journal-title":"Pattern Recogn"},{"issue":"3","key":"125_CR42","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/S0165-0114(01)00002-1","volume":"123","author":"X Wang","year":"2001","unstructured":"Wang X, Wang Y, Xu X, Ling W, Yeung DS (2001) A new approach to fuzzy rule generation: fuzzy extension matrix. Fuzzy Sets Syst 123(3):291\u2013306","journal-title":"Fuzzy Sets Syst"},{"key":"125_CR43","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.neucom.2005.05.006","volume":"68","author":"XZ Wang","year":"2005","unstructured":"Wang XZ, He Q, Chen DG, Yeung D (2005) A genetic algorithm for solving the inverse problem of support vector machines. Neurocomputing 68:225\u2013238","journal-title":"Neurocomputing"},{"issue":"1","key":"125_CR44","doi-asserted-by":"crossref","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. ACM SIGKDD Explor Newsl 6(1):7\u201319","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"125_CR45","volume-title":"Data mining: practical machine learning tools and techniques","author":"IH Witten","year":"2005","unstructured":"Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San Francisco","edition":"2"},{"issue":"1","key":"125_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, Ross Quinlan J, Ghosh J, Yang Q, Motoda H, McLachlan GJ, Ng A, Liu B, Yu PS (2008) Top 10 algorithms in data mining. Knowl Inf Syst 14(1):1\u201337","journal-title":"Knowl Inf Syst"},{"issue":"4","key":"125_CR47","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 Inform Technol Decis Mak 5(4):597\u2013604","journal-title":"Int J Inform Technol Decis Mak"},{"key":"125_CR48","doi-asserted-by":"crossref","unstructured":"Zeng-Chang Q (2005) ROC analysis for predictions made by probabilistic classifiers. Paper presented at the International Conference on Machine Learning and Cybernetics 18\u201321 Aug. 2005, pp 3119\u20133124","DOI":"10.1109\/ICMLC.2005.1527478"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-012-0125-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13042-012-0125-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-012-0125-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T14:24:23Z","timestamp":1687789463000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13042-012-0125-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,4]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,2]]}},"alternative-id":["125"],"URL":"https:\/\/doi.org\/10.1007\/s13042-012-0125-5","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,11,4]]}}}