Efficient design of Quadrature Mirror filter bank for Audio Signal Processing using Craziness based Particle Swarm Optimization Technique

In this paper, a superior version of Particle Swarm Optimization called Craziness based Particle Swarm Optimization (CRPSO) Technique is demonstrated for designing two-channel Quadrature Mirror Filter (QMF) Bank so as to process an audio signal with nearly perfect reconstructed output. Apart from achieving a better control on cognitive and social components of standard PSO, the proposed CRPSO dictates better implementation due to incorporation of a fresh craziness parameter, in the velocity equation of PSO, to ensure that the particle would have a predefined craziness probability to maintain the diversity of the particles. This mutation in the velocity equation not only ensures the faster searching in the multidimensional search space but also the solution produced is nearly accurate to the global optimal solution. The algorithm's performance is studied with the comparison of traditional PSO. Simulation results articulate that the proposed CRPSO algorithm outperforms its counterparts(PSO) not only in terms of quality output, i.e. sharpness at cut-off, pass band ripple and stop band attenuation but also in convergence speed with assured fidelity.