DocumentCode :
3003241
Title :
On the performance surfaces of a frequency domain adaptive IIR filter
Author :
Fan, Hong ; Yang, Yang ; Nayeri, Majid
Author_Institution :
Dept. of Electr. & Comput. Eng., Cincinnati Univ., OH, USA
fYear :
1988
fDate :
11-14 Apr 1988
Firstpage :
1564
Abstract :
The performance surface of a recently proposed frequency-domain adaptive IIR (infinite-impulse response) filter are analyzed. It is shown that for the sufficient-order case the surfaces are unimodal up to an equivalence class of N-factorial members where N is the number of adaptive poles. It is also shown that there exist manifolds separating the N-factorial members in the equivalence class from each other. On these manifolds lie saddle points. These saddle points cause slow convergence which appears to be shoulders on the MSE (mean-squared error) convergence curves. This can be avoided by initializing adaption away from the manifolds. Methods of finding saddle points are given. A second-order example confirms the above results
Keywords :
digital filters; filtering and prediction theory; frequency-domain analysis; IIR filter; MSE convergence curves; N-factorial members; adaptive poles; digital filters; equivalence class; frequency domain adaptive filter; infinite-impulse response; manifolds; mean-squared error; performance surfaces; saddle points; slow convergence; unimodal surfaces; Adaptive filters; Convergence; Filtering; Frequency domain analysis; IIR filters; Least squares methods; Newton method; Recursive estimation; Signal processing algorithms; Surface treatment;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on
Conference_Location :
New York, NY
ISSN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.1988.196907
Filename :
196907
Link To Document :
بازگشت