Overcomplete Blind Source Separation Based on Second Order Statistics

被引：0

作者：

Huang, Gaoming ^{[1
]}

Bai, Zhimao ^{[2
]}

Gao, Jun ^{[1
]}

机构：

[1] Naval Univ Engn, Wuhan 430033, Peoples R China

[2] Southeast Univ, Nanjing 210096, Jiangsu, Peoples R China

来源：

PROCEEDINGS OF THE 2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOLS 1-9 | 2009年

基金：

中国博士后科学基金;

关键词：

BSS; overcomplete; second order statistics; IDENTIFICATION;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Overcomplete blind source separation (BSS) has been a difficult problem for a long time. This paper proposed a novel overcomplete BSS algorithm based on second statistics. The first step is complete decorrelation processing by principal component analysis (PCA), then one strong correlation signal chosen as one input signal by the first canonical correlation analysis (CCA). At last, source signal estimation can be completed by multi-steps CCA. Simulation results show that this novel overcomplete BSS algorithm can be simply realized and the computation burden is small. This overcomplete BSS algorithm may be have a broad project application.

引用

页码：3806 / +

页数：2

共 17 条

[1]

[Anonymous], MULTIVARIATE STAT AN

[2]

BOFILL P, 2001, NEURALCOMPUTING, V55, P627

[3]

Borga M, 1998, THESIS LINKOPING U S

[4]

CHEN XX, 1989, STAT COMPUTATION MET