On local convergence of a class of blind separation algorithms

被引：7

作者：

Lindgren, U ^{[1
]}

Wigren, T ^{[1
]}

Broman, H ^{[1
]}

机构：

[1] ERICSSON RADIO SYST AB,S-16480 STOCKHOLM,SWEDEN

来源：

IEEE TRANSACTIONS ON SIGNAL PROCESSING | 1995年 / 43卷 / 12期

关键词：

D O I：

10.1109/78.476456

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：

A class of recursive stochastic gradient algorithms for blind separation of dynamically mixed independent source signals are analyzed. The studied methods utilize correlations and high-order moments in order to enforce statistical independence of the separated signals. The local convergence properties of the schemes are investigated, and it is demonstrated that local convergence is tied to positive realness of certain mixing transfer functions.

引用

页码：3054 / 3058

页数：5

共 25 条

[21]

Delfosse N., Loubaton P., Adaptive separation of independent sources: A deflation approach, Proc. ICASSP, 4, (1994)

[22]

Narendra K.S., Taylor J.H., Frequency Domain Criteria for Absolute Stability., (1973)

[23]

Wigren T., Convergence analysis of recursive identification algorithms based on the nonlinear Wiener model, IEEE Trans. Automat. Contr., 39, 11, pp. 2191-2206, (1994)

[24]

Lindgren U., Wigren T., Broman H., Analysis of a blind separation algorithm, Tech. Rep. no. CTH-TE-21, CTH-TE-21, (1994)

[25]

Astrom K.J., Wittenmark B., Computer Controlled Systems., (1984)

← 1 2 3 →