Decision Tree Support Vector Machine based on Genetic Algorithm for fault diagnosis
Qiang Wang, Huanhuan Chen, Yiming Shen · 2008
Decision tree support vector machine (DTSVM), which combines SVM and decision tree using the concept of dichotomy, is proposed to solve the multi-class fault diagnosis tasks. Since the classification performance of DTSVM is closely related to its structure, genetic algorithm is introduced into the formation of decision tree, to cluster the multi-classes with maximum distance between the clustering centers of the two sub-classes, so that the most separable classes would be separated at each node of decision tree. The results of numerical simulations conducted on three datasets compared with ldquoone-against-allrdquo and ldquoone-against-onerdquo, show that the proposed method has better performance and higher generalization ability than the two conventional methods.