Title :
On affine projection direction vector (non)whiteness
Author :
Beex, A.A. ; Sankaran, Sundar G.
Author_Institution :
DSP Res. Lab., Virginia Tech., Blacksburg, VA, USA
Abstract :
Hypotheses made about the behavior of the affine projection algorithm (APA) are investigated by means of carefully designed comparative experiments. These experiments lead us to the properties of the direction vector used in APA. Experiments also show that APA converges faster than NLMS in the case of white noise input, leading us to question that whitening of the direction vector is the explaining factor for the convergence acceleration observed with APA. An alternative hypothesis is offered for why APA may yield faster convergence than NLMS.
Keywords :
adaptive filters; convergence; correlation theory; least mean squares methods; APA; NLMS; affine projection algorithm; alternative hypothesis; convergence acceleration; direction vector; normalized least mean square algorithm; whitening; Adaptive filters; Convergence; Equations; Least squares approximation; Polynomials; System identification; System testing; Wiener filter;
Conference_Titel :
Signals, Systems and Computers, 2004. Conference Record of the Thirty-Eighth Asilomar Conference on
Print_ISBN :
0-7803-8622-1
DOI :
10.1109/ACSSC.2004.1399130
