Title :
A heuristic approach for designing microphone array directivity based on PSO
Author :
Haruna Aimi;Kenji Suyama
Author_Institution :
School of Engineering, Tokyo Denki University, 5 Senju-Asahi-cho, Adachi-ku, 120-8551, Japan
Abstract :
In this paper, a novel approach for designing two dimensional directivity of microphone array using IIR (Infinite Impulse Response) filters is presented. A design problem based on the minimax criterion is formulated as a non-linear programming problem and cannot be solved easily. In our method, PSO (Particle Swarm Optimization) is applied to solve such a problem. Although PSO is applicable easily to solve non-linear optimization problems, it is reported that a local minimum stagnation occurs due to its strong intensification. The design problem of IIR filters is assumed to occur the stagnation because it has a lot of local minimums. Therefore, a method for avoiding the local minimum stagnation plays an important role. In this paper, multiple swarm PSO is used to avoid the local minimum stagnation by reallocating particles. Several design examples are shown to present a design performance.
Keywords :
"Microphone arrays","Linear programming","Array signal processing","Communication systems","Artificial intelligence"
Conference_Titel :
Intelligent Signal Processing and Communication Systems (ISPACS), 2015 International Symposium on
DOI :
10.1109/ISPACS.2015.7432747