Tracking properties of vector space adaptive filters
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10586393,p. 30-34
- https://doi.org/10.1109/acssc.1992.269263
Abstract
Tracking properties are considered for adaptive filters which are adjusted within a vector space of filtering operations. For a given vector space of systems, the adaptive filter structure is determined by a choice of basis for the vector space. Basis dependent expressions are developed for the asymptotic mean square error (MSE) under least-mean-square (LMS) and recursive-least-square (RLS) adaptation, when the optimal filter specification is subject to constant drift. For the idealized setting considered, it is shown that the minimum achievable MSE using LMS adaptation is less than or equal to that achievable under RLS adaptation.Keywords
This publication has 9 references indexed in Scilit:
- System identification using Laguerre modelsIEEE Transactions on Automatic Control, 1991
- A system identification algorithm using orthogonal functionsIEEE Transactions on Signal Processing, 1991
- Adaptation and tracking in system identification—A surveyAutomatica, 1990
- Frequency domain tracking characteristics of adaptive algorithmsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- On tracking characteristics of weighted least squares estimators applied to nonstationary system identificationIEEE Transactions on Automatic Control, 1988
- Design of adaptive algorithms for the tracking of time‐varying systemsInternational Journal of Adaptive Control and Signal Processing, 1987
- Tracking properties and steady-state performance of RLS adaptive filter algorithmsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986
- Learning characteristics of stochastic-gradient-descent algorithms: A general study, analysis, and critiqueSignal Processing, 1984
- Stationary and nonstationary learning characteristics of the LMS adaptive filterProceedings of the IEEE, 1976