An improved PSO algorithm and its application in fast feature extraction of radar emitter signals

An improved PSO (particle swarm optimization) algorithm with stochastic inertia weight and natural selection is proposed. This algorithm effectively avoids the particle swarm easily falling into the local optimal and improves the convergence speed by the strategies of uniform initialization, stochastic inertia weight and natural selection. In order to verify the performance of the proposed algorithm, we apply it to the fast feature extraction of AFMR (ambiguity function main ridge) slice of radar emitter signals. The simulation experiments show that the modified PSO algorithm not only can obtain more accurate AFMR slice, but also can improve the search speed significantly at the same time. Our results confirm the feasibility and effectiveness of the suggested algorithm.