Title :
An IIR parallel-type adaptive algorithm using the fast least squares method
Author :
Kurosawa, Kaoru ; Tsujii, Shigeo
Author_Institution :
Graduate Sch., Tokyo Inst. of Tech., Yokohama, Japan
fDate :
8/1/1989 12:00:00 AM
Abstract :
A parallel-type adaptive algorithm is proposed which utilizes the fast least-squares method. Its computational complexity is much less than that of L. Landau´s (1978) method, which is based on hyperstability theory Hyperstability requires much computation because it involves matrix operations. The proposed method has nothing to do with hyperstability. It is also shown theoretically and using computer simulation, that the convergence performance of the proposed method is better than that of the series-parallel-type fast least-squares method
Keywords :
adaptive filters; filtering and prediction theory; least squares approximations; IIR parallel-type adaptive algorithm; computer simulation; fast least squares method; filtering; hyperstability theory; matrix operations; Adaptive algorithm; Adaptive systems; Computational complexity; Computer simulation; Convergence; Equations; Least squares methods; Performance analysis; Signal processing algorithms; Stability;
Journal_Title :
Acoustics, Speech and Signal Processing, IEEE Transactions on
