Blind Source Separation by RBF Neural Network Optimized by GA

DOI

10.2991/wartia-16.2016.252How to use a DOI?

Keywords

Blind Separation, RBF Neural Network, GA, k-Mean Clustering

Abstract

This work proposed a blind source separation method by RBF neural network optimized by GA, which can improve the separation performance under low SNR condition. The center value and the width value of RBF can be determined by k-mean clustering algorithm and the cost function is set by maximum entropy. For RBF neural network is sensitive to noise, the blind source separation algorithm (BSS) is optimized by GA to obtain the optimal parameters of RBF neural network. This method can implement good separation results under low SNR condition and has better robustness compared with traditional RBF neural network. The computer simulation results show the effectiveness of the proposed method.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Peili Cong
PY  - 2016/05
DA  - 2016/05
TI  - Blind Source Separation by RBF Neural Network Optimized by GA
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 1193
EP  - 1198
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.252
DO  - 10.2991/wartia-16.2016.252
ID  - Cong2016/05
ER  -