Identifiability of post-nonlinear mixtures

被引：21

作者：

Achard, S ^{[1
]}

Jutten, C

机构：

[1] Univ Grenoble 1, UMR 5523, CNRS, Lab Computat & Modeling, F-38041 Grenoble, France

[2] Univ Cambridge, Dept Psychiat, Brain Mapping Unit, Cambridge CB3 3EB, England

[3] Inst Natl Polytech Grenoble, CNRS, UMR 5083, Images & Signals Lab, F-38031 Grenoble, France

[4] Univ Grenoble 1, F-38031 Grenoble, France

来源：

IEEE SIGNAL PROCESSING LETTERS | 2005年 / 12卷 / 05期

关键词：

blind source separation; identiflability; independent component analysis (ICA); post nonlinear mixture;

D O I：

10.1109/LSP.2005.845593

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：

This letter deals with the resolution of the blind source separation problem using the independent component analysis method in post-nonlinear mixtures. Using the sole hypothesis of the source independence is not obvious to reconstruct the sources in nonlinear mixtures. Here, we prove the identifiability under weak assumptions on the mixture matrix and density sources.

引用

页码：423 / 426

页数：4

共 10 条

[1]

Babaie-Zadeh M., 2002, P 11 EUR SIGN PROC C, VII, P11

[2] INDEPENDENT COMPONENT ANALYSIS, A NEW CONCEPT [J].

COMON, P .

SIGNAL PROCESSING, 1994, 36 (03) :287-314

[3]

DARMOIS G, 1948, P C INT CTR NAT RECH, V13, P19

[4]

Darmois G., 1953, Rev. Inst. Int. Stat, V21, P2, DOI [10.2307/1401511, DOI 10.2307/1401511]

[5]

Darmois G, 1951, PROC INT STAT C 1947, P231

[6] MAJORIZATION, RANDOMNESS AND DEPENDENCE FOR MULTIVARIATE DISTRIBUTIONS [J].

JOE, H .

ANNALS OF PROBABILITY, 1987, 15 (03) :1217-1225

[7]

Kagan AM., 1973, Characterization problems in mathematical statistics

[8]

KULLBACK S, 1959, INFORMATION THEORY S

[9] Source separation in post-nonlinear mixtures [J].

Taleb, A ;

Jutten, C .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1999, 47 (10) :2807-2820

[10]

THEIS FJ, 2004, P ESANN 2004 BRUG BE, P217

← 1 →