结合ReliefF与支持向量机的特征选择方法研究  

RESEARCH INTO THE FEATURE SELECTION METHOD BY COMBINING RELIEFF AND SUPPORT VECTOR MACHINE

作　　者：韦娜[1] 王涛[2] 

机构地区：[1]长安大学信息工程学院,陕西西安710064 [2]西安武警工程学院,陕西西安710086

出　　处：《计算机应用与软件》2008年第1期283-285,共3页Computer Applications and Software

摘　　要：利用ReliefF作为特征选择方法,采用基于支持向量机的分类准确率作为特征子集的评估准则,进而决定删除的特征数目。用UCL数据集中Segmenatation数据集进行测试,通过实验研究证明,采用结合ReliefF与支持向量机的方法进行特征选择,能够有效地提高分类准确率。ReliefF is used as feature selection method,and the classification accuracy of support vector machine is taken as the evaluation criterion of feature subset to decide the number of features to delete. The test set is segmentation data set from UCL. The experimental results prove that combining ReliefF and support vector machine to perform the task of feature selection can improve the classification accuracy effectively.

关 键 词：特征选择 RELIEFF 支持向量机 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]