IEICE Trans - IIR Filter Design Using Multi-Swarm PSO Based on Particle Reallocation Strategy

IIR Filter Design Using Multi-Swarm PSO Based on Particle Reallocation Strategy

Haruna AIMI  Kenji SUYAMA

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E99-A    No.11    pp.1947-1954
Publication Date: 2016/11/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E99.A.1947
Type of Manuscript: Special Section PAPER (Special Section on Smart Multimedia & Communication Systems)
Category: Digital Signal Processing
Keyword:
digital filter,  particle swarm optimization,

Full Text: PDF>>

Summary:
In this paper, we study a novel method to avoid a local minimum stagnation in the design problem of IIR (Infinite Impulse Response) filters using PSO (Particle Swarm Optimization). Although PSO is appropriate to solve nonlinear optimization problems, it is reported that a local minimum stagnation occurs due to a strong intensification of particles during the search. Then, multi-swarm PSO based on the particle reallocation strategy is proposed to avoid the local minimum stagnation. In this method, a reallocation space is determined by using some global bests. In this paper, the relationship between the number of swarms and the best value of design error is shown and the effectiveness of the proposed method is shown through several design examples.