Multi-class probability SVM fusion using fuzzy integral for fault diagnosis

Authors:
Zhonghui Hu;Yunze Cai;Xing He;Ye Li;Xiaoming Xu
Affiliations:
Department of Automation, Shanghai Jiaotong University, Shanghai, China;Department of Automation, Shanghai Jiaotong University, Shanghai, China;Department of Automation, Shanghai Jiaotong University, Shanghai, China;Department of Automation, Shanghai Jiaotong University, Shanghai, China;Department of Automation, Shanghai Jiaotong University, Shanghai, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part III
Year:
2005

Citing 6
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Fault diagnosis using Rough Sets Theory

Computers in Industry
Evidence Theory and Its Applications

Evidence Theory and Its Applications
Combination of Multiple Classifiers Using Adaptive Fuzzy Integral

ICAIS '02 Proceedings of the 2002 IEEE International Conference on Artificial Intelligence Systems (ICAIS'02)
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks
Multiple network fusion using fuzzy logic

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A multi-class probability support vector machine (MPSVM) is designed by training the sigmoid function to mapping the outputs of standard SVMs into posterior probabilities and then combining these learned probability SVMs. The method of using fuzzy integral to combine multiple MPSVMs is proposed to deal with distributed multi-source multi-class problems. The proposed method considers both the evidence provided by each MPSVM and the empirical degree of importance of these MPSVMs in combination process. It is applied to fault diagnosis for a diesel engine. The experimental results show the performance of fault diagnosis can be improved.