特征选择方法综述

被引:205
作者
姚旭
王晓丹
张玉玺
权文
机构
[1] 空军工程大学计算机工程系
关键词
特征选择; 搜索策略; 评价准则;
D O I
10.13195/j.cd.2012.02.4.yaox.013
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
特征选择是模式识别的关键问题之一,特征选择结果的好坏直接影响着分类器的分类精度和泛化性能.首先分析了特征选择方法的框架;然后从搜索策略和评价准则两个角度对特征选择方法进行了分析和总结;最后分析了对特征选择的影响因素,并指出了实际应用中需要解决的问题.
引用
收藏
页码:161 / 166+192 +192
页数:7
相关论文
共 18 条
  • [11] Object detection using feature subset selection
    Sun, ZH
    Bebis, G
    Miller, R
    [J]. PATTERN RECOGNITION, 2004, 37 (11) : 2165 - 2176
  • [12] Consistency-based search in feature selection[J] . Manoranjan Dash,Huan Liu.Artificial Intelligence . 2003 (1)
  • [13] An accelerated procedure for recursive feature ranking on microarray data[J] . C. Furlanello,M. Serafini,S. Merler,G. Jurman.Neural Networks . 2003 (5)
  • [14] Gene Selection for Cancer Classification using Support Vector Machines
    Isabelle Guyon
    Jason Weston
    Stephen Barnhill
    Vladimir Vapnik
    [J]. Machine Learning, 2002, 46 : 389 - 422
  • [15] Feature selection for classification[J] . M. Dash,H. Liu.Intelligent Data Analysis . 1997 (1)
  • [16] The feature selection problem: traditional methods and a new algorithm .2 Kira K,Rendell L A. Proceedings of the Tenth National Conference on Artificial Intelligence . 1992
  • [17] Comparison of Statistical Methods for Classification of Ovarian Cancer Using Mass Spectrometry Data .2 wu B L,Abbott T,Fishman D,et a. Bioinformatics . 2003
  • [18] Best first strategy for feature selection .2 Xu L,Yan P,Chang Z. Proceedings of 9th International Conference on Pattern Recognition . 1988