A Multi-Class Cost Sensitivity AdaBoost Algorithm Using Multi-Class Cost Exponential Loss Function

被引：0
|
作者：
Zhai X. [1 ]
Wang X. [1 ]
Li R. [1 ]
Jia Q. [1 ]
机构：
[1] Institute of Air Defense and Anti-Missile, Air Force Engineering University, Xi'an
来源：
Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University | 2017年 / 51卷 / 08期
关键词：
AdaBoost; Bayes decision; Cost sensitive; Loss function; Multi-class;
D O I：
10.7652/xjtuxb201708006
中图分类号：
学科分类号：
摘要：
A multi-class cost sensitivity AdaBoost algorithm is proposed to solve the problems of high time complexity and indistinguishable cost among different classes in using the existing multi-class algorithm, which is an extension of some binary cost sensitive AdaBoost algorithms. The new algorithm uses a multi-class exponential loss function, and is named as MCCSADA. A cost sensitive multi-class exponential loss function is designed to satisfy design guidelines of cost-sensitive loss function and to ensure the cost-sensitive characteristic. Then, the loss function is used as a criterion for the evaluation of basis classifiers and the optimal weighted coefficients of base classifiers are obtained by using the forward stack model to minimize the cost loss function. Subsequently, MCCSADA is obtained by using the new loss function and weighted coefficients to replace the original loss function and coefficients in AdaBoost algorithm. MCCSADA is verified by using UCI dataset, and the results and a comparison with the CSOVO expanding from binary algorithm show that MCCSADA has lower cost and lower time complexity in most cases. The time complexity reduces by about 40% when the dataset contains three classes and reduces more with increasing number of data categories. Moreover, the stability of the algorithm is promoted, and the degeneration is weakened. © 2017, Editorial Office of Journal of Xi'an Jiaotong University. All right reserved.
引用
收藏
页码：33 / 39
页数：6
相关论文
共 16 条
  • [1] Lopez V., Fernandez A., Moreno-Torres J.G., Et al., Analysis of preprocessing vs. cost-sensitive learning for imbalanced classification, Expert Systems with Applications, 39, 7, pp. 6585-6608, (2012)
  • [2] Freund Y., Schapire R.E., A decision theoretic generalization of on-line learning and an application to boosting, Lecture Notes in Computer Science: Vol 904, pp. 23-37, (1995)
  • [3] Ting K.M., Zheng Z., Boosting trees for cost-sensitive classification, Lecture Notes in Computer Science: Vol 1398, pp. 190-195, (1999)
  • [4] Fan W., Stolfo S.J., Zhang J., Et al., AdaCost: misclassification cost-sensitive boosting, Proceedings of the 16th International Conference on Machine Learning, pp. 97-105, (1999)
  • [5] Sun Y., Wong A., Wang Y., Parameter inference of cost-sensitive boosting algorithms, Proceedings of the 4th International Conference on Machine Learning and Data Mining in Pattern Recognition, pp. 21-30, (2005)
  • [6] Sun Y., Kamel M.S., Wong A., Et al., Cost-sensitive boosting for classification of imbalanced data, Pattern Recognition, 40, 12, pp. 3358-3378, (2007)
  • [7] Masnadi-Shirazi H., Vasconcelos N., Asymmetric boosting, Proceedings of the 24th International Conference on Machine Learning, pp. 609-619, (2007)
  • [8] Masnadi-Shirazi H., Vasconcelos N., Cost-sensitive boosting, Pattern Analysis and Machine Intelligence, 33, 2, pp. 294-309, (2010)
  • [9] Fu Z., Cost-sensitive ensemble learning algorithm for multi-label classification problems, Acta Auto Matica Sinica, 40, 6, pp. 1075-1080, (2014)
  • [10] Fu Z., Cost-sensitive AdaBoost algorithm for multi-class classification problems, Acta Auto Matica Sinica, 37, 8, pp. 973-983, (2011)
12