Consistent normalized least mean square filtering with noisy data matrix
Authors:
- 23 May 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 53 (6) , 2112-2123
Abstract
When the ordinary least squares method is applied to the parameter estimation problem with noisy data matrix, it is well-known that the estimates turn out to be biased. While this bias term can be somewhat reduced by the use of models of higher order, or by requiring a high signal-to-noise ratio (SNR), it can never be completely removed. Consistent estimates can be obtained by means of the instrumental variable method (IVM),or the total/data least squares method (TLS/DLS). In the adaptive setting for the such problem, a variety of least-mean-squares (LMS)-type algorithms have been researched rather than their recursive versions of IVM or TLS/DLS that cost considerable computations. Motivated by these observations, we propose a consistent LMS-type algorithm for the data least square estimation problem. This novel approach is based on the geometry of the mean squared error (MSE) function, rendering the step-size normalization and the heuristic filtered estimation of the noise variance, respectively, for fast convergence and robustness to stochastic noise. Monte Carlo simulations of a zero-forcing adaptive finite-impulse-response (FIR) channel equalizer demonstrate the efficacy of our algorithm.Keywords
This publication has 28 references indexed in Scilit:
- QR-based TLS and mixed LS-TLS algorithms with applications to adaptive IIR filteringIEEE Transactions on Signal Processing, 2003
- Noise-constrained least mean squares algorithmIEEE Transactions on Signal Processing, 2001
- Analysis of the convergence and divergence of a constrained anti-Hebbian learning algorithmIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1998
- Total least mean squares algorithmIEEE Transactions on Signal Processing, 1998
- Projection approximation subspace trackingIEEE Transactions on Signal Processing, 1995
- Bias removal in equation-error adaptive IIR filtersIEEE Transactions on Signal Processing, 1995
- An unbiased equation error identifier and reduced-order approximationsIEEE Transactions on Signal Processing, 1994
- An efficient recursive total least squares algorithm for FIR adaptive filteringIEEE Transactions on Signal Processing, 1994
- Adaptive nonlinear recursive state-space filtersIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1994
- The Data Least Squares Problem and Channel EqualizationIEEE Transactions on Signal Processing, 1993