Search

This article presents a comparative analysis of particle swarm optimisation (PSO), self-organising hierarchical particle swarm optimiser (HPSO) and self-organising hierarchical particle swarm optimiser with time-varying acceleration coefficients (HPSO-TVAC) for data clustering. Through experiments on six well-known benchmarks, we find that the HPSO and the HPSO-TVAC algorithms have better performance than the PSO algorithm in most cases, and all the clustering algorithms using PSO have good performance for large-scale data and high-dimensional data, especially the two algorithms proposed in this article. Furthermore, we have also observed that the convergence of the HPSO and the HPSO-TVAC algorithms are better when using a suitable fitness function.