An improved binary tree SVM for multi-classification

When we use binary tree support vector machine (SVM) to work the multi-classification problems out, we always find that the structure of the binary tree has a large chance and it has a great influence on the classification efficiency of the classification model. To solve this problem, according to the idea of separating the most widely distributed class first, an improved binary tree SVM multiple classification algorithm is proposed in this paper. The algorithm considers the characteristics of small sample distribution fully, and constructs the binary tree based on the geometric distribution of the training samples in the attributed space, so as to establish the classification model. Experiments on different small sample standard data sets prove that the improved binary tree SVM improves the accuracy of classification and has better generalization.