An Empirical Study of Particle Swarm Optimization for Cluster Analysis.

This paper investigates the use of Particle Swarm Optimization (PSO) for cluster analysis. In clustering, primitive exploration with minimum prior knowledge consists of research across a wide variety of communities. The diversity in the field of PSO-based clustering equips us with many tools. This paper provides an integrated framework of the diversified PSO-based clustering. In addition, a novel Particle Swarm Optimization (PSO) algorithm using the concept of aging of particles like bird within a flock is provided. The effectiveness of this concept is demonstrated by cluster analysis. Results show that the model provides enhanced performance and maintains more diversity in the swarm and thereby allows the particles to be robust to trace the changing environment. [ABSTRACT FROM AUTHOR]