Improving Particle Swarm Optimization by using incremental attribute learning and centroid of particle's best positions
Sornnarong Srimakham, Kietikul Jearanaitanakij · 2017
Particle Swarm Optimization (PSO) is a powerful algorithm that can search a solution for a function which contains a large number of peaks and valleys. However, PSO might encounter a difficulty when the function gets more complex or the number of attributes (dimensions) grows larger. This paper proposes a modification of PSO by using the incremental attribute strategy along with the centroid of particle's best positions to avoid the local minima which can easily occur in a multimodal problem. The experimental results from four standard benchmarks show that the proposed method can improve PSO in terms of optimality and stability when compared with the conventional PSO and another incremental attribute-based PSO.