Variable LMS Algorithms Using the Time Constant Concept

Two variable least mean square (LMS) algorithms using the simple time constant concept, variable step size LMS (VS-LMS) and variable length LMS (VL-LMS) algorithms, are proposed. In proposed variable LMS algorithms, the time constant, by which the step size is changed in the VS-LMS algorithm and the filter length is varied in the VL-LMS algorithm, is used as a measure of the error signal convergence. Computer simulation results show that proposed algorithms are simpler but show better performance than conventional variable LMS algorithms. >

[1]  Richard W. Harris,et al.  A variable step (VS) adaptive filter algorithm , 1986, IEEE Trans. Acoust. Speech Signal Process..

[2]  Héctor M. Pérez Meana,et al.  A fast adaptive filter algorithm using eigenvalue reciprocals as stepsizes , 1990, IEEE Trans. Acoust. Speech Signal Process..

[3]  Arie Feuer,et al.  Variable length stochastic gradient algorithm , 1991, IEEE Trans. Signal Process..

[4]  Wasfy B. Mikhael,et al.  A Fast Block FIR Adaptive Digital Filtering Algorithm with Individual Adaption of Parameters , 1989 .

[5]  Raymond H. Kwong,et al.  A variable step size LMS algorithm , 1992, IEEE Trans. Signal Process..

[6]  Thomas Kailath,et al.  Adaptive algorithms with an automatic gain control feature , 1988 .

[7]  Ping Xue,et al.  Analysis and implementation of variable step size adaptive algorithms , 1993, IEEE Trans. Signal Process..

[8]  B. Widrow,et al.  The time-sequenced adaptive filter , 1981 .

[9]  J. Nagumo,et al.  A learning method for system identification , 1967, IEEE Transactions on Automatic Control.