一种改进的1-v-1 SVM多类分类算法

Improved 1-v-1 SVM Multi-class Classification Algorithm

针对传统的1-v-1 SVM算法测试未知样本速度较慢的缺点提出了一种改进的1-v-1 SVM算法。该方法采用多轮投票策略减少测试过程中使用分类器的次数从而提高分类未知样本的速度。实验证明改进的算法是有效的。

An improved algorithm for 1-v-1 SVM is presented aims at the long time cost in me process of testing unclassified data.This method can reduce the number of classifiers used in the test process by using multi-vote strategy,so the time cost for testing unclassified data is reduced.The experiment proved that the improved algorithm is effective.