关键词: 多分类问题, 三分类问题, 最小二乘支持向量机, 分类回归机, 一对一对多方法

Abstract: Tri-class classification method based on Support Vector Machine (SVM) is a kind of method for solving multi-class classification problems. Least Square Support Vector Classification-Regression (LSSVCR) was proposed, which considered the effects of all the sample points by using least squares objective function. Even if there were wrongly marked sample points in the training set, the result would not be affected largely by them. LSSVCR was more accurate and faster, and it was efficient for the problems that there are large differences among the number of sample points in different classes. The numerical experiments show that the proposed method raises the accuracy by 2.57% on average compared to the existing tri-classification methods.

Key words: multi-class classification problem, tri-class classification problem, Least Square Support Vector Machine (LSSVM), classification-regression machine, one versus one versus rest (1-v-1-v-r) method