NONPARAMETRIC FEATURE SELECTION

被引：28

作者：

PATRICK, EA

FISCHER, FP

机构：

[1] School of Electrical Engineering, Purdue University, Lafayatte, Ind

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1969年 / 15卷 / 05期

关键词：

D O I：

10.1109/TIT.1969.1054354

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Two groups of L-dimensional observations of size N1 1 and N 2 are known to be random vector variables from two unknown probability distribution functions [1]. A method is discussed for obtaining an l-dimensional linear subspace of the observation space in which the i-variate marginal distributions are most separated, based on a nonparametric estimate of probability density functions and a distance criterion. The distance used essentially is the L2 norm of the difference between Parzen estimates of the two densi-ties. An algorithm is developed that determines the subspace for which the distance between the two densities is maximized. Computer simulations are performed. © 1969 IEEE. All rights reserved.

引用

页码：577 / +