Title :
Fast adaptive IIR filtering with noisy input and output data
Author_Institution :
Sch. of Quantitative Methods & Math. Sci., Univ. of Western Sydney, Kingswood, NSW, Australia
Abstract :
A new adaptive infinite impulse response (IIR) filtering algorithm for noisy input-output systems is proposed. The variances of the input and output measurement noise, which specifies the source of the noise-induced bias in the standard least-squares estimate, are computed using extra delayed noisy input measurements. Since good estimates of the noise variances are obtained in a quicker manner, the proposed adaptive algorithm achieves a faster rate of convergence
Keywords :
IIR filters; adaptive filters; convergence of numerical methods; filtering theory; least squares approximations; IIR filtering; adaptive filtering; convergence; infinite impulse response filtering; least-squares estimate; noise variance estimation; noisy input-output systems; Adaptive filters; Australia; Convergence; Filtering algorithms; Finite impulse response filter; IIR filters; Noise cancellation; Noise measurement; Parameter estimation; Signal processing algorithms;
Conference_Titel :
Signal Processing and its Applications, Sixth International, Symposium on. 2001
Conference_Location :
Kuala Lumpur
Print_ISBN :
0-7803-6703-0
DOI :
10.1109/ISSPA.2001.949839
