非线性支持向量机判别阈值的设置

Discrimination threshold setting for nonlinear support vector machine

非线性支持向量机通过核函数将低维输入空间的数据映射到高维空间,从而将原低维空间的线性不可分问题转化为高维空间上的线性可分问题。分析了非线性支持向量机中核函数的引入可造成分类阈值的偏移问题,提出了非线性支持向量机分类阈值的优化设置方法。实验表明,所提出的阈值优化设置方法能有效提高非线性支持向量机的分类精度。

The nonlinear SVM map the input data of dimension to the high dimension space by the kernel function that can transform the inseparable problem into the linear divided problem. It is analyzed that classification value is deviated by introducing the kernel function into nonlinear SVM. The optimal setting of the classification threshold is proposed. The experimental results show that the proposed method can improve the classification accuracy of nonlinear SVM efficiently.