Title :
New adaptive algorithms based on multi-band decomposition of the error signal
Author :
Resende, Fernando Gil V, Jr. ; Diniz, Paulo S R ; Tokuda, Keiichi ; Kaneko, Mineo ; Nishihara, Akinori
Author_Institution :
Univ. Fed. do Rio de Janeiro, Brazil
fDate :
5/1/1998 12:00:00 AM
Abstract :
New adaptive algorithms based on multi-band decomposition of the error signal and application of a different convergence factor for each band are derived. With this approach, tracking ability and performance in steady state can be traded off along the frequency domain giving rise to estimates of the adaptive filter coefficients closer to the ideal response as compared to those obtained with conventional least-mean-square (LMS) and recursive least-squares (RLS) algorithms, particularly when the statistical properties of the analyzed signal vary along the frequency spectrum. A new adaptation technique for the forgetting factor depending exclusively on the autocorrelation values of the input signal is also introduced and a multi-band RLS algorithm, with an independent variable forgetting factor for each band, suitable for the analysis of nonstationary signals is described. Computer experiments comparing the performance of multi-band and conventional LMS and RLS algorithms are shown
Keywords :
adaptive filters; convergence; correlation theory; filtering theory; least squares approximations; tracking; RLS algorithm; adaptive algorithms; autocorrelation values; convergence factor; error signal; filter coefficients; forgetting factor; multi-band decomposition; nonstationary signals; statistical properties; tracking ability; Adaptive algorithm; Algorithm design and analysis; Convergence; Frequency domain analysis; Frequency estimation; Least squares approximation; Recursive estimation; Resonance light scattering; Signal analysis; Steady-state;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on
