AN OLD WORKFRAME FOR A NEW PROBLEM: A CLASSICAL MODEL FOR UNSUPERVISED ADAPTIVE FILTERING | ||
| International Conference on Aerospace Sciences and Aviation Technology | ||
| Article 111, Volume 12, ASAT Conference, 29-31 May 2007, May 2007, Pages 1-10 PDF (132.8 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/asat.2007.24130 | ||
| Author | ||
| M. Elsabrouty | ||
| Faculty of Information and Engineering Technology, The German University in Cairo. | ||
| Abstract | ||
| A classical adaptive filtering model of the problem of instantaneous blind signal separation, or what is formally known as unsupervised adaptive filtering is presented. This classical form helps understanding the well-known superior behaviour of the natural gradient solution to the blind separation problem. A new RLS-based algorithm is developed using this classical model. The algorithm provides improved on-line separation speed under the same steady state error compared to the natural gradient algorithm without requiring pre-whitening. | ||
| Keywords | ||
| Blind Signal Separation; Natural Gradient; Recursive Least Square; Unsupervised Adaptive Filtering | ||
|
Statistics Article View: 158 PDF Download: 215 |
||
