A fast algorithm for one-unit ICA-R

Qiu Hua Lin; Yong Rui Zheng; Fu Liang Yin; Hualou Liang; Vince D. Calhoun

doi:10.1016/j.ins.2006.09.011

A fast algorithm for one-unit ICA-R

Qiu Hua Lin, Yong Rui Zheng, Fu Liang Yin, Hualou Liang, Vince D. Calhoun

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

Abstract

Independent component analysis (ICA) aims to recover a set of unknown mutually independent source signals from their observed mixtures without knowledge of the mixing coefficients. In some applications, it is preferable to extract only one desired source signal instead of all source signals, and this can be achieved by a one-unit ICA technique. ICA with reference (ICA-R) is a one-unit ICA algorithm capable of extracting an expected signal by using prior information. However, a drawback of ICA-R is that it is computationally expensive. In this paper, a fast one-unit ICA-R algorithm is derived. The reduction of the computational complexity for the ICA-R algorithm is achieved through (1) pre-whitening the observed signals; and (2) normalizing the weight vector. Computer simulations were performed on synthesized signals, a speech signal, and electrocardiograms (ECG). Results of these analyses demonstrate the efficiency and accuracy of the proposed algorithm.

Original language	English (US)
Pages (from-to)	1265-1275
Number of pages	11
Journal	Information Sciences
Volume	177
Issue number	5
DOIs	https://doi.org/10.1016/j.ins.2006.09.011
State	Published - Mar 1 2007
Externally published	Yes

Keywords

Constrained independent component analysis
Independent component analysis
One-unit independent component analysis
Reference signal

ASJC Scopus subject areas

Software
Control and Systems Engineering
Theoretical Computer Science
Computer Science Applications
Information Systems and Management
Artificial Intelligence

Access to Document

10.1016/j.ins.2006.09.011

Cite this

@article{0292f0a795ff46d69aca3a440586af2b,

title = "A fast algorithm for one-unit ICA-R",

abstract = "Independent component analysis (ICA) aims to recover a set of unknown mutually independent source signals from their observed mixtures without knowledge of the mixing coefficients. In some applications, it is preferable to extract only one desired source signal instead of all source signals, and this can be achieved by a one-unit ICA technique. ICA with reference (ICA-R) is a one-unit ICA algorithm capable of extracting an expected signal by using prior information. However, a drawback of ICA-R is that it is computationally expensive. In this paper, a fast one-unit ICA-R algorithm is derived. The reduction of the computational complexity for the ICA-R algorithm is achieved through (1) pre-whitening the observed signals; and (2) normalizing the weight vector. Computer simulations were performed on synthesized signals, a speech signal, and electrocardiograms (ECG). Results of these analyses demonstrate the efficiency and accuracy of the proposed algorithm.",

keywords = "Constrained independent component analysis, Independent component analysis, One-unit independent component analysis, Reference signal",

author = "Lin, {Qiu Hua} and Zheng, {Yong Rui} and Yin, {Fu Liang} and Hualou Liang and Calhoun, {Vince D.}",

note = "Funding Information: The authors would like to thank the editor-in-chief and the anonymous reviewers for valuable comments to improve the paper. We also thank Drs. Michael E. Brandt, Steven L. Bressler for English corrections and editing. This work was supported by the National Natural Science Foundation of China under Grant No. 60402013, No. 60372082, No. 60172073, the Liaoning Province Natural Science Foundation of China under Grant No. 20062174, and by the National Institutes of Health, under grants 1 R01 EB 000840 and 1 R01 EB 005846. ",

year = "2007",

month = mar,

day = "1",

doi = "10.1016/j.ins.2006.09.011",

language = "English (US)",

volume = "177",

pages = "1265--1275",

journal = "Information Sciences",

issn = "0020-0255",

publisher = "Elsevier Inc.",

number = "5",

}

TY - JOUR

T1 - A fast algorithm for one-unit ICA-R

AU - Lin, Qiu Hua

AU - Zheng, Yong Rui

AU - Yin, Fu Liang

AU - Liang, Hualou

AU - Calhoun, Vince D.

N1 - Funding Information: The authors would like to thank the editor-in-chief and the anonymous reviewers for valuable comments to improve the paper. We also thank Drs. Michael E. Brandt, Steven L. Bressler for English corrections and editing. This work was supported by the National Natural Science Foundation of China under Grant No. 60402013, No. 60372082, No. 60172073, the Liaoning Province Natural Science Foundation of China under Grant No. 20062174, and by the National Institutes of Health, under grants 1 R01 EB 000840 and 1 R01 EB 005846.

PY - 2007/3/1

Y1 - 2007/3/1

N2 - Independent component analysis (ICA) aims to recover a set of unknown mutually independent source signals from their observed mixtures without knowledge of the mixing coefficients. In some applications, it is preferable to extract only one desired source signal instead of all source signals, and this can be achieved by a one-unit ICA technique. ICA with reference (ICA-R) is a one-unit ICA algorithm capable of extracting an expected signal by using prior information. However, a drawback of ICA-R is that it is computationally expensive. In this paper, a fast one-unit ICA-R algorithm is derived. The reduction of the computational complexity for the ICA-R algorithm is achieved through (1) pre-whitening the observed signals; and (2) normalizing the weight vector. Computer simulations were performed on synthesized signals, a speech signal, and electrocardiograms (ECG). Results of these analyses demonstrate the efficiency and accuracy of the proposed algorithm.

AB - Independent component analysis (ICA) aims to recover a set of unknown mutually independent source signals from their observed mixtures without knowledge of the mixing coefficients. In some applications, it is preferable to extract only one desired source signal instead of all source signals, and this can be achieved by a one-unit ICA technique. ICA with reference (ICA-R) is a one-unit ICA algorithm capable of extracting an expected signal by using prior information. However, a drawback of ICA-R is that it is computationally expensive. In this paper, a fast one-unit ICA-R algorithm is derived. The reduction of the computational complexity for the ICA-R algorithm is achieved through (1) pre-whitening the observed signals; and (2) normalizing the weight vector. Computer simulations were performed on synthesized signals, a speech signal, and electrocardiograms (ECG). Results of these analyses demonstrate the efficiency and accuracy of the proposed algorithm.

KW - Constrained independent component analysis

KW - Independent component analysis

KW - One-unit independent component analysis

KW - Reference signal

UR - http://www.scopus.com/inward/record.url?scp=33845391465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845391465&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2006.09.011

DO - 10.1016/j.ins.2006.09.011

M3 - Article

AN - SCOPUS:33845391465

VL - 177

SP - 1265

EP - 1275

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

IS - 5

ER -

A fast algorithm for one-unit ICA-R

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this