Title :
Adaptive pilot filtering for LMS algorithm
Author_Institution :
Bell Commun. Res., Morristown, NJ, USA
Abstract :
An adaptive pilot filtering procedure is proposed to increase the convergence speed of the LMS (least mean square) algorithm. The procedure uses an adaptive filter with only a few filter coefficients to filter both the received signal and the original signal for the purpose of whitening the received signal. The convergence speed of the adaptive pilot filtering procedure combined with the LMS algorithm is comparable to that of the Kalman algorithm for some applications. The procedure combined with the main LMS algorithm requires less than twice the computation power of a conventional LMS algorithm
Keywords :
adaptive filters; convergence of numerical methods; filtering and prediction theory; least squares approximations; signal processing; Kalman algorithm; LMS algorithm; adaptive filter; adaptive pilot filtering; computation power; convergence speed; least mean square algorithm; original signal; received signal; signal processing; signal whitening; Adaptive filters; Autocorrelation; Convergence; Equalizers; Filtering algorithms; Kalman filters; Least squares approximation; Robustness; Signal processing; Transversal filters;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7803-0003-3
DOI :
10.1109/ICASSP.1991.150521
