Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers (1994)
Pacific Grove, CA, USA
Oct. 31, 1994 to Nov. 2, 1994
S.L. Netto , Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada
P. Agathoklis , Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada
Adaptive infinite-duration impulse response (IIR) filters have been studied as a possible alternative to adaptive finite-duration impulse response (FIR) filters. Two of the best known approaches for adaptive IIR filtering include the output error (OE) and the equation error (EE) algorithms. A new algorithm, the so-called composite square error (CSE) algorithm, for adaptive IIR filtering is introduced based on the explicit combination of the OE and and EE schemes. An innovative strategy for updating the composite factor and force the proposed algorithm to converge to the OE solution is also presented. Examples are included to demonstrate some of the interesting features of the new technique.<
IIR filters, adaptive filters, filtering theory, adaptive signal processing, convergence of numerical methods, error analysis
S. Netto and P. Agathoklis, "A new composite adaptive IIR algorithm," Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers(ACSSC), Pacific Grove, CA, USA, 1995, pp. 1506-1510.