A new joint diagonalization algorithm with application in blind source separation

Fuxiang Wang; Zhongkan Liu; Jun Zhang

doi:10.1109/LSP.2005.860542

A new joint diagonalization algorithm with application in blind source separation

Fuxiang Wang^*
, Zhongkan Liu
, Jun Zhang

^*Corresponding author for this work

Beihang University

Research output: Contribution to journal › Article › peer-review

25 Citations (Scopus)

Abstract

In this letter, we present a new nonorthogonal algorithm for joint diagonalization of a set of symmetric matrices. The algorithm alternates between updates of individual demixing matrix rows, and the update of each row is transferred to solving the eigenvector problem. By using some blind source separation simulations, we show that the algorithm obviously obtains an improved performance when the signal-to-noise ratio of the observed signals is relatively low.

Original language	English
Pages (from-to)	41-44
Number of pages	4
Journal	IEEE Signal Processing Letters
Volume	13
Issue number	1
DOIs	https://doi.org/10.1109/LSP.2005.860542
Publication status	Published - Jan 2006
Externally published	Yes

Keywords

Blind source separation (BSS)
Eigenvalue and eigenvector
Interference-to-signal ratio (ISR)
Joint diagonalization

Access to Document

10.1109/LSP.2005.860542

Cite this

@article{738e1424b457438a90601840826a2fc5,

title = "A new joint diagonalization algorithm with application in blind source separation",

abstract = "In this letter, we present a new nonorthogonal algorithm for joint diagonalization of a set of symmetric matrices. The algorithm alternates between updates of individual demixing matrix rows, and the update of each row is transferred to solving the eigenvector problem. By using some blind source separation simulations, we show that the algorithm obviously obtains an improved performance when the signal-to-noise ratio of the observed signals is relatively low.",

keywords = "Blind source separation (BSS), Eigenvalue and eigenvector, Interference-to-signal ratio (ISR), Joint diagonalization",

author = "Fuxiang Wang and Zhongkan Liu and Jun Zhang",

year = "2006",

month = jan,

doi = "10.1109/LSP.2005.860542",

language = "English",

volume = "13",

pages = "41--44",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - A new joint diagonalization algorithm with application in blind source separation

AU - Wang, Fuxiang

AU - Liu, Zhongkan

AU - Zhang, Jun

PY - 2006/1

Y1 - 2006/1

N2 - In this letter, we present a new nonorthogonal algorithm for joint diagonalization of a set of symmetric matrices. The algorithm alternates between updates of individual demixing matrix rows, and the update of each row is transferred to solving the eigenvector problem. By using some blind source separation simulations, we show that the algorithm obviously obtains an improved performance when the signal-to-noise ratio of the observed signals is relatively low.

AB - In this letter, we present a new nonorthogonal algorithm for joint diagonalization of a set of symmetric matrices. The algorithm alternates between updates of individual demixing matrix rows, and the update of each row is transferred to solving the eigenvector problem. By using some blind source separation simulations, we show that the algorithm obviously obtains an improved performance when the signal-to-noise ratio of the observed signals is relatively low.

KW - Blind source separation (BSS)

KW - Eigenvalue and eigenvector

KW - Interference-to-signal ratio (ISR)

KW - Joint diagonalization

UR - https://www.scopus.com/pages/publications/30444446914

U2 - 10.1109/LSP.2005.860542

DO - 10.1109/LSP.2005.860542

M3 - Article

AN - SCOPUS:30444446914

SN - 1070-9908

VL - 13

SP - 41

EP - 44

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 1

ER -

A new joint diagonalization algorithm with application in blind source separation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this