论文信息 - The Bagging and n2-Classifiers Based on Rules Induced by MODLEM

The Bagging and n2-Classifiers Based on Rules Induced by MODLEM

An application of the rule induction algorithm MODLEM to construct multiple classifiers is studied. Two different such classifiers are considered: the bagging approach, where classifiers are generated from different samples of the learning set, and the n 2-classifier, which is specialized for solving multiple class learning problems. This paper reports results of an experimental comparison of these multiple classifiers and the single, MODLEM based, classifier performed on several data sets.

Jerzy Stefanowski | J. Stefanowski

[1] Céline Rouveirol,et al. Machine Learning: ECML-98 , 1998, Lecture Notes in Computer Science.

[2] Jerzy Stefanowski,et al. Experiments on Solving Multiclass Learning Problems by n2-classifier , 1998, ECML.

[3] Jan M. Zytkow,et al. Handbook of Data Mining and Knowledge Discovery , 2002 .

[4] João Gama,et al. Combining classification algorithms , 2000 .

[5] Jerzy Stefanowski,et al. Bagging and Induction of Decision Rules , 2002, Intelligent Information Systems.

[6] Robert Tibshirani,et al. Classification by Pairwise Coupling , 1997, NIPS.

[7] J. Ross Quinlan,et al. Bagging, Boosting, and C4.5 , 1996, AAAI/IAAI, Vol. 1.

[8] J. Grzymala-Busse,et al. Three discretization methods for rule induction , 2001 .

[9] Thomas G. Dietterich. Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[10] Leo Breiman,et al. Bagging Predictors , 1996, Machine Learning.

[11] Christopher M. Bishop,et al. Advances in Neural Information Processing Systems 8 (NIPS 1995) , 1991 .

[12] Eric Bauer,et al. An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants , 1999, Machine Learning.

[13] R. Tibshirani,et al. Classi cation by Pairwise Coupling , 1998 .