An approach to optimize FIR filter coefficients using GA, PSO and BAT algorithm and their comparative analysis

In this paper, we propose the nonlinear multimodal optimization problem of low pass FIR filter design using three conventional optimization algorithms. The efficacy of the proposed method was compared with the traditional approach of filter design Parks McClellan algorithm as reference. In optimization algorithms mean square error based cost function was used as the fitness function. It is seen was observed that the BAT algorithm statistically outperforms Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) in terms of stopband attenuation characteristics and ripple performance of the designed filter.