Title :
Mean weight behavior of the filtered-X LMS algorithm
Author :
Tobias, Orlando J. ; Bermudez, José Carlos M ; Bershad, Neil J.
Author_Institution :
Dept. of Electr. Eng., Fed. Univ. of Santa Catarina, Florianopolis, Brazil
fDate :
4/1/2000 12:00:00 AM
Abstract :
A new stochastic analysis is presented for the filtered-X LMS (FXLMS) algorithm. The analysis does not use independence theory. An analytical model is derived for the mean behavior of the adaptive weights. The model is valid for white or colored reference inputs and accurately predicts the mean weight behavior even for large step sizes. The constrained Wiener solution is determined as a function of the input statistics and the impulse responses of the adaptation loop filters. Effects of secondary path estimation error are studied. Monte Carlo simulations demonstrate the accuracy of the theoretical model
Keywords :
Monte Carlo methods; active noise control; adaptive filters; least mean squares methods; stochastic processes; transient response; FXLMS; Monte Carlo simulations; adaptation loop filters; adaptive weights; colored reference inputs; constrained Wiener solution; filtered-X LMS algorithm; impulse responses; input statistics; mean weight behavior; secondary path estimation error; stochastic analysis; white reference inputs; Acoustic noise; Adaptive algorithm; Adaptive filters; Algorithm design and analysis; Analytical models; Least squares approximation; Signal processing algorithms; Statistics; Stochastic processes; Vibration control;
Journal_Title :
Signal Processing, IEEE Transactions on
