A new demixer scheme for blind source separation using general neural network model

W. L. Woo; S. Sali

doi:10.1049/cp:20010077

A new demixer scheme for blind source separation using general neural network model

W. L. Woo, S. Sali

Computer Information Sciences Department

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

There has been a surge of interest in blind source separation (BSS) because of its potential applications in several areas of engineering and science such as wireless systems. We propose a new neural network demixing scheme using a general neural network structure for the BSS problem for the instantaneous mixtures. It is shown that the existing feedforward (FF) and feedback (FB) neural network schemes can be reduced from the new general model. The results demonstrate that the new scheme is more robust and offers superior convergence properties.

Original language	English
Pages	383-386
Number of pages	4
DOIs	https://doi.org/10.1049/cp:20010077
Publication status	Published - 7 Aug 2002
Event	Second International Conference on 3G Mobile Communication Technologies - IEE London, London, United Kingdom Duration: 26 Mar 2001 → 28 Mar 2001 https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=923494

Conference

Conference	Second International Conference on 3G Mobile Communication Technologies
Country/Territory	United Kingdom
City	London
Period	26/03/01 → 28/03/01
Internet address	https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=923494

Keywords

signal processing
neural net architecture
feedforward neural nets
feedback
convergence of numerical methods

Access to Document

10.1049/cp:20010077

Cite this

@conference{ef38699ed68f457daeb2f083e8a624e7,

title = "A new demixer scheme for blind source separation using general neural network model",

abstract = "There has been a surge of interest in blind source separation (BSS) because of its potential applications in several areas of engineering and science such as wireless systems. We propose a new neural network demixing scheme using a general neural network structure for the BSS problem for the instantaneous mixtures. It is shown that the existing feedforward (FF) and feedback (FB) neural network schemes can be reduced from the new general model. The results demonstrate that the new scheme is more robust and offers superior convergence properties.",

keywords = "signal processing, neural net architecture, feedforward neural nets, feedback, convergence of numerical methods",

author = "Woo, {W. L.} and S. Sali",

year = "2002",

month = aug,

day = "7",

doi = "10.1049/cp:20010077",

language = "English",

pages = "383--386",

note = "Second International Conference on 3G Mobile Communication Technologies ; Conference date: 26-03-2001 Through 28-03-2001",

url = "https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=923494",

}

TY - CONF

T1 - A new demixer scheme for blind source separation using general neural network model

AU - Woo, W. L.

AU - Sali, S.

PY - 2002/8/7

Y1 - 2002/8/7

N2 - There has been a surge of interest in blind source separation (BSS) because of its potential applications in several areas of engineering and science such as wireless systems. We propose a new neural network demixing scheme using a general neural network structure for the BSS problem for the instantaneous mixtures. It is shown that the existing feedforward (FF) and feedback (FB) neural network schemes can be reduced from the new general model. The results demonstrate that the new scheme is more robust and offers superior convergence properties.

AB - There has been a surge of interest in blind source separation (BSS) because of its potential applications in several areas of engineering and science such as wireless systems. We propose a new neural network demixing scheme using a general neural network structure for the BSS problem for the instantaneous mixtures. It is shown that the existing feedforward (FF) and feedback (FB) neural network schemes can be reduced from the new general model. The results demonstrate that the new scheme is more robust and offers superior convergence properties.

KW - signal processing

KW - neural net architecture

KW - feedforward neural nets

KW - feedback

KW - convergence of numerical methods

U2 - 10.1049/cp:20010077

DO - 10.1049/cp:20010077

M3 - Paper

SP - 383

EP - 386

T2 - Second International Conference on 3G Mobile Communication Technologies

Y2 - 26 March 2001 through 28 March 2001

ER -

A new demixer scheme for blind source separation using general neural network model

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this