International Journal of Computer Engineering Research
Subscribe to IJCER
Full Name*
Email Address*

Article Number - 08452468212


Vol.2(1), pp. 1 - 7 , February 2011

ISSN: 2141-6494



Full Length Research Paper

Blind signal separation based on generalized Laplace distribution


M. EL-Sayed Waheed, Osama Abdo Mohamed and M. E. Abd El-Aziz*




Department of Mathematics, Faculty of science, Zagazig University, Egypt.


Email: abd_el_aziz_m@yahoo.com






 Accepted: 18 September 2010  Published: 27 February 2011

Copyright © 2011 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0


Blind Signal Separation is the task of separating signals when only their mixtures are observed. Recently, Independent Component Analysis has become a favorite method of researchers for attacking this problem. We propose a new score function based on Generalized Laplace Distribution for the problem of blind signal separation for supergaussian and subgaussian. To estimate the parameters of such score function we used Nelder-Mead algorithm for optimizing the maximum likelihood function of Generalized Laplace Distribution. To blindly extract the independent source signals, we resort to FastICA approach. Simulation results show that the proposed approach is capable of separating mixture of signals.

 

Key words: Independent component analysis (ICA), generalized Laplace distribution (GLD), maximum likelihood (ML), Nelder-Mead (NM).


APA (2011). Blind signal separation based on generalized Laplace distribution. International Journal of Computer Engineering Research, 2(1), 1 - 7.
Chicago M. EL-Sayed Waheed, Osama Abdo Mohamed and M. E. Abd El-Aziz. "Blind signal separation based on generalized Laplace distribution." International Journal of Computer Engineering Research 2, no. 1 (2011): 1 - 7.
MLA M. EL-Sayed Waheed, Osama Abdo Mohamed and M. E. Abd El-Aziz. "Blind signal separation based on generalized Laplace distribution." International Journal of Computer Engineering Research 2.1 (2011): 1 - 7.
   
DOI
URL http://academicjournals.org/journal/IJCER/article-abstract/08452468212

Subscription Form