Weighted multi-class support vector machine based on binary tree

A classification algorithm of the multi-class SVM based on binary tree is inducted in this paper and its advantages and defections are analyzed. To overcome its defections, a new weighted multi-class SVM based on binary tree is proposed. Furthermore the proposed method can be applied to the case of regarding small sort of classification accuracy, such as fault diagnosis. Finally the experiment results show that it has higher classification accuracy than that of the traditional multi-class SVM based on the binary tree.