Optimal digital IIR filter design using ant colony optimization

Abstract

Digital filters are mainly classified into two types: Finite Impulse Response (FIR) filters and Infinite Impulse Response (IIR) filters. The IIR filters are fundamental elements of digital signal processing, they can present a better performance compared to that of the FIR filters. However, the error surface of IIR filters is generally nonlinear and multimodal. Hence, global optimization techniques must be used. The Ant Colony algorithms form a class of proposed metaheuristics for solving difficult optimization problems. In this paper, tow variants of Ant Colony Optimization, namely, the Ant System and the Ant Colony System are proposed to deal with the optimal design of IIR filters. Also, the performance of the proposed algorithms is compared.