Center of Gravity PSO for Partitioning Clustering

TL;DR

This paper introduces a novel local best PSO model for partition-based clustering that improves upon gbest PSO, using neighborhoods to optimize cluster centroids and outperform k-means and global PSO in accuracy.

Contribution

It proposes the LPOSC model, a local best PSO approach with neighborhood-based optimization for clustering, addressing limitations of previous PSO methods.

Findings

LPOSC outperforms k-means in clustering accuracy.

LPOSC achieves higher adjusted rand index than gbest PSO.

The model effectively optimizes cluster centroids using neighborhood structures.

Abstract

This paper presents the local best model of PSO for partition-based clustering. The proposed model gets rid off the drawbacks of gbest PSO for clustering. The model uses a pre-specified number of clusters K. The LPOSC has K neighborhoods. Each neighborhood represents one of the clusters. The goal of the particles in each neighborhood is optimizing the position of the centroid of the cluster. The performance of the proposed algorithms is measured using adjusted rand index. The results is compared with k-means and global best model of PSO.