ONLINE OPTIMIZATION OF THE POLES LOCATIONS OF GENERALIZED ORTHONORMAL IIR ADAPTIVE FILTERS USING PARTICLE SWARM OPTIMIZATION

In this paper, an evolutionary method has been proposed for online obtaining the free parameters of generalized orthonormal IIR (GO-IIR) filters and its special case, Laguerre filters. This method is based on particle swarm optimization and is capable to extract both pole locations and filter weights simultaneously. Empirically, the stability of the designed filter is shown to be guaranteed in the proposed algorithm. Simulation results show that the proposed algorithm gives 30db reduction in mean squared error compared to other parameter estimation methods for Laguerre filters and in this method, there is not sensitive to initial conditions of the free parameter and learning rate.