一种基于PCA和ReliefF的特征选择方法  

New feature selection approach by PCA and ReliefF

作　　者：蒋玉娇[1] 王晓丹[1] 王文军[2] 毕凯[1] 

机构地区：[1]空军工程大学导弹学院计算机工程系,陕西三原713800 [2]第四军医大学教育技术中心,西安710032

出　　处：《计算机工程与应用》2010年第26期170-172,共3页Computer Engineering and Applications

基　　金：国家自然科学基金No.60975026;陕西省自然科学研究计划项目(No.2007F19)~~

摘　　要：如何减少样本的训练测试时间、提高分类精度是有效特征选择方法研究的重要方面。提出了一种结合PCA和ReliefF的特征选择算法。该算法选择出了最具有代表性的特征,构成有效特征子集,实现了特征降维。同时,较PCA-GA方法,该算法具有简单、快速等优点。利用标准数据集进行的实验结果表明,文中算法是可行的、有效的,为模式识别的信息特征压缩提供了一种新的研究方法。How to decrease the time of training and testing the samples,and improve the classification accuracy are important aspects of the feature selection research.A new feature selection approach by PCA and ReliefF is presented in this paper. The algorithm can take out the most representative features which constitute the effective feature sets from the original fea- tures, thus the dimensions of the features are decreased.Moreover the algorithm is proven to be more advantageous than the approach of PCA-GA in its simplicity and speed.Experiments on a UCI dataset show that the method in this paper provides a new research approach for information feature compression in pattern recognition.

关 键 词：特征选择 主成分分析 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]