Selection of number of principal components for de-noising signals

被引：7

作者：

Koutsogiannis, GS ^{[1
]}

Soraghan, JJ

机构：

[1] Xidian Univ, Grad Sch, Xian, Peoples R China

[2] Shenzhen Univ, President Off, Shen Zhen, Peoples R China

来源：

ELECTRONICS LETTERS | 2002年 / 38卷 / 13期

关键词：

D O I：

10.1049/el:20020424

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Principal component anal si, (PCA) is a tran transformation technique Used to reduce the dimensionality of a data,et. Using delay embedding, it is possible to know a priori how many principal components to choose to obtain the optimum reconstruction. A novel nonlinear PCA-based scheme employing delay embedding is presented for the de-noising, of communication signals.

引用

页码：664 / 666

页数：3