An Empirical Evaluation of Boosting-BAN and Boosting-MultiTAN

Abstract:

An ensemble consists of a set of independently trained classifiers whose predictions are combined when classifying novel instances. Previous research has shown that an ensemble as a whole is often more accurate than any of the single classifiers in the ensemble. Boosting-BAN classifier is considered stronger than Boosting-MultiTAN on noise-free data. However, there are strong empirical indications that Boosting-MultiTAN is much more robust than Boosting-BAN in noisy settings. For this reason, in this paper we built an ensemble using a voting methodology of Boosting-BAN and Boosting-MultiTAN ensembles with 10 sub-classifiers in each one. We performed a comparison with Boosting-BAN and Boosting-MultiTAN ensembles with 25 sub-classifiers on standard benchmark datasets and the proposed technique was the most accurate.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 506-509
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.506
• Online since: February 2014
• Authors: Xiao Wei Sun*, Hong Bo Zhou
• Keywords: Bayesian Network Classifier, Boosting, Combination Method, Data Mining (DM)

References

[1] Breiman L. Bias, variance, and arcing classifiers Tech. rep. 460, Department of Statistics, University of California, Berkeley, CA. (1996).

[2] Kohavi R, Kunz C. Option decision trees with majority votes. In Proc. 14th International Conference on Machine Learning, 1997, 161-169.

[3] Bauer E, Kohavi R. An empirical comparison of voting classification algorithms: Bagging, boosting, and variants. Machine Learning, 1999, 36 (1/2), 105-139.

[4] Dietterich T.G. Ensemble methods in machine learning. In Kittler, J., Roli, F., eds.: Multiple Classifier Systems. Lecture Notes Computer Sciences, Vol. 1857, 2001, 1-15.

DOI: 10.1007/3-540-45014-9_1

[5] Xiaowei Sun, Hongbo Zhou. An Empirical Comparison of Two Boosting Algorithms on Real Data Sets based on Analysis of Scientific Materials. Springer, Advances in Intelligent and Soft Computing, 2011, vol. 105, 324-327.

DOI: 10.1007/978-3-642-23756-0_53

[6] Hongbo Shi, Houkuan Huang, Zhihai Wang. Boosting-Based TAN ComZbination Classifier. Journal of Computer research and development, 2004, 41(2): 340-345.

[7] Freund Y, Robert S. Experiments with a New Boosting Algorithm. Proceedings of ICML'96, 148-156.

[8] Wu Qinghua, Liu Hanmin, Sun yuxin, Xie Fang, Zhang Jin, Yan Xuesong. Research of function optimization algorithm. TELKOMNIKA , 2012, Vol. 10, 4, 858-863.

[9] Srikanth Pullabhatla, Ashwani Kumar Chandel, Anil Naik Kanasottu. Inverse S-Transform Based Decision Tree for Power System Faults Identification. TELKOMNIKA , 2011, Vol. 9, 1, 99-106.

DOI: 10.12928/telkomnika.v9i1.674

[10] UCI Machine Learning Repository. http: /www. ics. uci. edu/~mlearn/ML Repository html.