A Novel Sigmoid-Function-Based Adaptive Weighted Particle Swarm Optimizer

In this paper, a novel particle swarm optimization (PSO) algorithm is put forward where sigmoid-function-based weighting strategy developed to adaptively adjust the acceleration coefficients. The newly proposed adaptive takes into account both distances from global best position and its personal position, thereby having distinguishing feature of enhancing convergence rate. Inspired by activation function neural networks, new employed update coefficients using sigmoid function. search capability PSO (AWPSO) comprehensively evaluated via eight well-known benchmark functions including unimodal multimodal cases. experimental results demonstrate that designed AWPSO substantially improves rate optimizer also outperforms some currently popular algorithms.