Journal ArticleDOI
A numerically stable fast transversal filter with leakage correction
TLDR
A new method to stabilize the algorithm is introduced that does not depend on the characteristics of the excitation signal, and by inserting leakage factors in the filter equations, a steady contraction of error components is reached.Abstract:
A derivation of fundamental fast transversal filter equations comes to a 7M fast RLS algorithm for system identification. Yet, this algorithm is not stable due to numerical errors resulting from implementation on a hardware with finite precision arithmetic. The known stabilization methods with feedback of numerical errors require a judicious choice of the feedback gains and depend on the properties of the exciting sequence, as simulations have shown. A new method to stabilize the algorithm is introduced that does not depend on the characteristics of the excitation signal. By inserting leakage factors in the filter equations, a steady contraction of error components is reached. >read more
Citations
More filters
Journal ArticleDOI
New efficient adaptive fast transversal filtering (FTF)‐type algorithms for mono and stereophonic acoustic echo cancelation
TL;DR: This paper proposes two new FTF‐type algorithms with low complexity and good convergence speed characteristics, mainly on the basis of a forward prediction scheme to estimate the so called dual Kalman gain, which is inherent in the filtering part update of the fast transversal filter algorithm.
Proceedings Article
Error propagation analysis of fast recursive least squares algorithms
TL;DR: New versions of numerically stable fast recursive least squares (NS-FRLS) algorithms are presented and a theoretical justification for these versions is presented by formulating new conditions on the forgetting factor.
Proceedings ArticleDOI
Near real-time system identification in a wireless sensor network for adaptive feedback control
TL;DR: Recursion identification of system poles is proposed for use in a wireless sensing network engaged in feedback control and is ideally suited for adaptive control methods that update control and estimation gains as system properties change.
Analysis of Fast Recursive Least Squares Algorithms for Adaptive Filtering
Madjid Arezki,Ahmed Benallal,P. Meyrueis,Abderrezak Guessoum,Daoud Berkani,Boulevard Sébastien Brant +5 more
TL;DR: A theoretical justification for this new version of numerically stable fast recursive least squares (NS-FRLS) algorithm is presented by formulating new conditions on the forgetting factor and their robustness is shown.
Proceedings ArticleDOI
Analysis of the stabilized FTF algorithm with leakage correction
J.K. Soh,Scott C. Douglas +1 more
TL;DR: This paper analyzes the stability characteristics of the numerically-stable FTF algorithm employing leakage correction for recursive least-squares adaptive filtering and proves that for positive leakage factors v/ sub 1/ in the range 0/spl Lt/v/sub 1/, the algorithm is numerically stable.
References
More filters
Journal ArticleDOI
Numerically stable fast transversal filters for recursive least squares adaptive filtering
Dirk Slock,Thomas Kailath +1 more
TL;DR: A solution is proposed to the long-standing problem of the numerical instability of fast recursive least squares transversal filter (FTF) algorithms with exponential weighting, an important class of algorithms for adaptive filtering.
Proceedings ArticleDOI
A new method to stabilize fast RLS algorithms based on a first-order of the propagation of numerical errors
Ahmed Benallal,A. Gilloire +1 more
TL;DR: An effective method to stabilize fast RLS algorithms is proposed, based on the analysis of the propagation of the numerical errors according to a first-order linear model, which modifies the numerical properties of these variables while preserving the theoretical form of the algorithms.
Journal ArticleDOI
Easy and effective stabilisation measure for fast recursive least squares algorithms for adaptive transversal filters
H. Schutze,Z. Ren +1 more
TL;DR: In this article, a new and effective stabilisation measure is presented for a 0(7N) FRLS algorithm which needs only one additional multiplication per iteration step, which is the same as in this paper.
Proceedings ArticleDOI
Stabilized fast adaptation algorithms for acoustic echo control
TL;DR: A new stabilization measure is developed for three well-known fast recursive least squares algorithms that needs only a maximum of one multiplication per iteration step to remain stable in the simulation.