A new Jacobi-like method for joint diagonalization of arbitrary non-defective matrices

被引：34

作者：

Iferroudjene, R. ^{[1
]}

Meraim, K. Abed ^{[2
]}

Belouchrani, A. ^{[3
]}

机构：

[1] Ecole Mil Polytech, Algiers, Algeria

[2] Telecom Paris, TSI Dept, F-75014 Paris, France

[3] Ecole Natl Super Polytech, EE Dept, Algiers, Algeria

来源：

APPLIED MATHEMATICS AND COMPUTATION | 2009年 / 211卷 / 02期

关键词：

Joint diagonalization; Non-unitary transformation; Unitary transformation; Givens rotation; EIGENVALUES;

D O I：

10.1016/j.amc.2009.01.045

中图分类号：

O29 [应用数学];

学科分类号：

070104 [应用数学];

摘要：

This paper addresses the problem of joint diagonalization of a set of matrices. A new Jacobi-Like method that has the advantages of computational efficiency and of generality is presented. The proposed algorithm brings the general matrices into normal ones and performs a joint diagonalization by a combination of unitary and shears (non-unitary) transformations. It is based on the iterative minimization of an appropriate cost function using generalized Jacobi rotation matrices. (c) 2009 Elsevier Inc. All rights reserved.

引用

页码：363 / 373

页数：11

共 14 条

[1]

Abramowitz M., 1972, HDB MATH FUNCTIONS F, P17

[2]

[Anonymous], INT CONF ACOUST SPEE

[3]

A blind source separation technique using second-order statistics [J].