Two-stage series-based neural network approach to nonlinear independent component analysis

P. Gao; L. C. Khor; W. L. Woo; S. S. Dlay

doi:10.1109/ISCAS.2006.1693644

Two-stage series-based neural network approach to nonlinear independent component analysis

P. Gao^*, L. C. Khor, W. L. Woo, S. S. Dlay

^*Corresponding author for this work

Computer Information Sciences Department

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Linear Independent Component Analysis (ICA) played an important role in the development of various signal processing techniques due to the inherent simplicity. However, the assumption of linear mixture is always violated in real life, which narrows down its applications. In this paper, the problem of nonlinear independent component analysis is considered. Based on a new type of nonlinear mixing model, we propose a two-stage series-based approach to recover the original source signals. The two-stage series-based algorithm offers significant advantages in terms of reduced computational complexity and better learning dynamics of the trajectory. Simulations have also been carried out to verify the efficacy of the proposed method.

Original language	English
Title of host publication	ISCAS 2006
Subtitle of host publication	2006 IEEE International Symposium on Circuits and Systems, Proceedings
Publisher	IEEE
Pages	4559-4562
Number of pages	4
ISBN (Print)	0-7803-9389-9
DOIs	https://doi.org/10.1109/ISCAS.2006.1693644
Publication status	Published - 11 Sept 2006
Event	ISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems - Kos, Greece Duration: 21 May 2006 → 24 May 2006

Conference

Conference	ISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems
Country/Territory	Greece
City	Kos
Period	21/05/06 → 24/05/06

Access to Document

10.1109/ISCAS.2006.1693644

Cite this

@inproceedings{f3fe0dee4f364459a0a92e0338673cfd,

title = "Two-stage series-based neural network approach to nonlinear independent component analysis",

abstract = "Linear Independent Component Analysis (ICA) played an important role in the development of various signal processing techniques due to the inherent simplicity. However, the assumption of linear mixture is always violated in real life, which narrows down its applications. In this paper, the problem of nonlinear independent component analysis is considered. Based on a new type of nonlinear mixing model, we propose a two-stage series-based approach to recover the original source signals. The two-stage series-based algorithm offers significant advantages in terms of reduced computational complexity and better learning dynamics of the trajectory. Simulations have also been carried out to verify the efficacy of the proposed method.",

author = "P. Gao and Khor, {L. C.} and Woo, {W. L.} and Dlay, {S. S.}",

year = "2006",

month = sep,

day = "11",

doi = "10.1109/ISCAS.2006.1693644",

language = "English",

isbn = "0-7803-9389-9",

pages = "4559--4562",

booktitle = "ISCAS 2006",

publisher = "IEEE",

address = "United States",

note = "ISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems ; Conference date: 21-05-2006 Through 24-05-2006",

}

Gao, P, Khor, LC, Woo, WL & Dlay, SS 2006, Two-stage series-based neural network approach to nonlinear independent component analysis. in ISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems, Proceedings. IEEE, pp. 4559-4562, ISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems, Kos, Greece, 21/05/06. https://doi.org/10.1109/ISCAS.2006.1693644

TY - GEN

T1 - Two-stage series-based neural network approach to nonlinear independent component analysis

AU - Gao, P.

AU - Khor, L. C.

AU - Woo, W. L.

AU - Dlay, S. S.

PY - 2006/9/11

Y1 - 2006/9/11

N2 - Linear Independent Component Analysis (ICA) played an important role in the development of various signal processing techniques due to the inherent simplicity. However, the assumption of linear mixture is always violated in real life, which narrows down its applications. In this paper, the problem of nonlinear independent component analysis is considered. Based on a new type of nonlinear mixing model, we propose a two-stage series-based approach to recover the original source signals. The two-stage series-based algorithm offers significant advantages in terms of reduced computational complexity and better learning dynamics of the trajectory. Simulations have also been carried out to verify the efficacy of the proposed method.

AB - Linear Independent Component Analysis (ICA) played an important role in the development of various signal processing techniques due to the inherent simplicity. However, the assumption of linear mixture is always violated in real life, which narrows down its applications. In this paper, the problem of nonlinear independent component analysis is considered. Based on a new type of nonlinear mixing model, we propose a two-stage series-based approach to recover the original source signals. The two-stage series-based algorithm offers significant advantages in terms of reduced computational complexity and better learning dynamics of the trajectory. Simulations have also been carried out to verify the efficacy of the proposed method.

U2 - 10.1109/ISCAS.2006.1693644

DO - 10.1109/ISCAS.2006.1693644

M3 - Conference contribution

AN - SCOPUS:34547305672

SN - 0-7803-9389-9

SP - 4559

EP - 4562

BT - ISCAS 2006

PB - IEEE

T2 - ISCAS 2006: 2006 IEEE International Symposium on Circuits and Systems

Y2 - 21 May 2006 through 24 May 2006

ER -

Two-stage series-based neural network approach to nonlinear independent component analysis

Abstract

Conference

Access to Document

Fingerprint

Cite this