一种基于数据分布的SVM回归方法

A Kind of SVM Regression Method based on Data Distribution

核函数参数选择是支撑向量机(Support Vector Machine,SVM)研究的主要问题之一。提出了检验样本是否呈高斯分布的方法,确定最优核参数选择的依据。采用人工数据集进行回归实验,验证了文中方法的有效性。

The kernel parameter selection is one of the key problems for support vector machine （SVM）. In this paper, a new way to select the kernel function and its parameter, is presented. It is based on the characteristics of data distribu- tion. The paper presents an approach to determine Gauss distribution. And then on the basis of determining Gauss distri- bution, this paper discusses how to select the kernel function and its parameter. The simulation experiments demonstrate the feasibility and the effectiveness of the presented approach.