Home // International Journal On Advances in Telecommunications, volume 2, number 2 and 3, 2009 // View article

A Family of Recursive Least-Squares Adaptive Algorithms Suitable for Fixed-Point Implementation

Authors:
Constantin Paleologu
Silviu Ciochină
Andrei Alexandru Enescu

Keywords: Adaptive filters, fixed-point implementation, noise reduction, QR-decomposition-based least-squares lattice (QRD-LSL) algorithm, recursive leastsquare (RLS) algorithm

Abstract:
The main feature of the least-squares adaptive algorithms is their high convergence rate. Unfortunately, they encounter numerical problems in finite precision implementation and especially in fixed-point arithmetic. The objective of this paper is twofold. First, an analysis of the finite precision effects of the recursive least-squares (RLS) algorithm is performed, outlining some specific problems that could appear in fixed-point implementation; consequently, we present a modified version of the RLS algorithm suitable for fixed-point implementation, using an asymptotically unbiased estimator for the algorithm’s cost. Second, we extend the procedure for the case of QR-decompositionbased least-squares lattice (QRD-LSL) adaptive algorithm, a “fast” member of RLS family, with good numerical properties. The reduced dynamics of the algorithm’s parameters leads to facility for fixed-point implementation. The simulations performed on a fixed-point digital signal processor (DSP) sustain the theoretical findings. Also, as a practical aspect of this work, we illustrate the performance of the proposed QRD-LSL algorithm for noise reduction.

Pages: 88 to 97

Copyright: Copyright (c) to authors, 2009. Used with permission.

Publication date: December 1, 2009

Published in: journal

ISSN: 1942-2601