Covariance matrix estimation and classification with limited training data

被引：188

作者：

Hoffbeck, JP ^{[1
]}

Landgrebe, DA ^{[1
]}

机构：

[1] PURDUE UNIV,SCH ELECT ENGN,W LAFAYETTE,IN 47907

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1996年 / 18卷 / 07期

基金：

美国国家航空航天局;

关键词：

covariance matrix; estimation; leave-one-out method; cross validation; classification; high dimensional data;

D O I：

10.1109/34.506799

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new covariance matrix estimator useful for designing classifiers with limited training data is developed. In experiments, this estimator achieved higher classification accuracy than the sample covariance matrix and common covariance matrix estimates. In about half of the experiments, it achieved higher accuracy than regularized discriminant analysis, but required much less computation.

引用

页码：763 / 767

页数：5