Advertisement

Implementation Issues in Blind Source Separation

Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 3)
Implementation Issues in Blind Source Separation In Chap. 5, we have derived BSS algorithms using Sylvester matrices. The Sylvester-based notation allows the separation process to be written very concisely as in (5.14):
$$y\left( p \right) = {\rm{Wx}}\left( p \right)$$
(5.14)

Paradoxically, the price for the conciseness of the Sylvester-based notation is its high redundancy. And unfortunately, consistency of this redundant representation of the separation system W is not guaranteed by the algorithms that are given in Chap. 5. For this reason, these algorithms cannot be directly implemented. In the first part of this chapter, our contribution is to propose a systematic and rigorous treatment of this redundancy issue, which eventually provides implementable update rules.

Keywords

Online Algorithm Implementation Issue Separation System Blind Source Separation Natural Gradient 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media, LLC 2009

Personalised recommendations