A simplified FTF-type algorithm for adaptive filtering

Authors:
Ahmed Benallal;Abdelhak Benkrid
Affiliations:
Department of Electronics, Dammam College of Technology, Dammam 7650, Saudi Arabia;Department of Electronics, Dammam College of Technology, Dammam 7650, Saudi Arabia
Venue:
Signal Processing
Year:
2007

Citing 6
Cited 2

Adaptive filter theory

Adaptive filter theory
A stabilized fast transversal filters algorithm for recursive least squares adaptive filtering

Signal Processing
The fast Newton transversal filter: an efficient scheme foracoustic echo cancellation in mobile radio

IEEE Transactions on Signal Processing
On the convergence behavior of the LMS and the normalized LMSalgorithms

IEEE Transactions on Signal Processing
Fast Newton transversal filters-a new class of adaptive estimationalgorithms

IEEE Transactions on Signal Processing
Simplified Newton-type adaptive estimation algorithms

IEEE Transactions on Signal Processing

Fast algorithms with low complexity for adaptive filtering

WSEAS Transactions on Signal Processing
Advanced algorithms for adaptive filtering

ISPRA'09 Proceedings of the 8th WSEAS international conference on Signal processing, robotics and automation

Quantified Score

Hi-index	0.08

Visualization

Abstract

Fast RLS algorithms are known to present numerical instability and this instability is originated in the backward prediction parameters. In this paper, a simplified FTF-type algorithm for adaptive filtering is presented. The basic idea behind the proposed algorithm is to avoid using the backward variables. By using only forward prediction variables and adding a small regularization constant and a leakage factor, we obtain a robust numerically stable FTF-type algorithm that shows the same performances as the numerically stable FTF algorithms. The computational complexity of the proposed algorithm is 7N when used with a full size predictor, which is less complex than the 8N numerically stable FTF algorithms and this computational complexity can be significantly reduced to 2N+5P when used with a reduced P-size forward predictor.