ICA techniques for more sources than sensors

被引：17

作者：

De Lathauwer, L ^{[1
]}

De Moor, B ^{[1
]}

Vandewalle, J ^{[1
]}

机构：

[1] Katholieke Univ Leuven, ESAT, EE Dept, SISTA,COSIC, B-3001 Louvain, Belgium

来源：

PROCEEDINGS OF THE IEEE SIGNAL PROCESSING WORKSHOP ON HIGHER-ORDER STATISTICS | 1999年

关键词：

D O I：

10.1109/HOST.1999.778707

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper we derive algorithms to identify the mixing matrix in the context of an Independent Component Analysis with more sources than sensors. First, by exploiting the fact that for complex-valued observations, depending on the type of complex symmetry, 2 different fourth-order cumulants are available, we develop a technique that can cope with N(N + 1)/2 sources for only N sensors. Secondly, the technique presented in [2], based on a single cumulant, is modified to take both cumulants into account as well.

引用

页码：121 / 124

页数：4

共 10 条

[1] Jacobi angles for simultaneous diagonalization [J].

Cardoso, JF ;

Souloumiac, A .

SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 1996, 17 (01) :161-164

[2] BLIND BEAMFORMING FOR NON-GAUSSIAN SIGNALS [J].

CARDOSO, JF ;

SOULOUMIAC, A .

IEE PROCEEDINGS-F RADAR AND SIGNAL PROCESSING, 1993, 140 (06) :362-370

[3]

CARDOSO JF, P ICASSP 91, V5, P3109

[4]

COMON P, 1999, P ICA 99 AUSS FRANC, P461

[5]

COMON P, 1998, P SPIE C 2 13 SAN DI

[6]

DELATHAUWER L, UNPUB ICA TECHNIQUES

[7]

DELATHAUWER L, 1997, THESIS KU LEUVEN BEL

[8]

DELATHAUWER L, P HOS 99

[9]

Horn R.A., 1991, TOPICS MATRIX ANAL

[10] An analytical constant modulus algorithm [J].

vanderVeen, AJ ;

Paulraj, A .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1996, 44 (05) :1136-1155

← 1 →