Clustering is an unsupervised kind of grouping of data points based on the similarity that exists between them. This paper applied a combination of particle swarm optimization and K-means for data clustering. The proposed approach tries to improve the performance of traditional partition clustering techniques such as K-means by avoiding the initial requirement of number of clusters or centroids for clustering. The proposed approach is evaluated using various primary and real-world datasets. Moreover, this paper also presents a comparison of results produced by the proposed approach and by the K-means based on clustering validity measures such as inter- and intra-cluster distances, quantization error, silhouette index, and Dunn index. The comparison of results shows that as the size of the dataset increases, the proposed approach produces significant improvement over the K-means partition clustering technique.

Clustering is a widely used technique for finding the similar hidden patterns from a dataset. Many techniques are available for data clustering such as partition clustering, hierarchical clustering, density based clustering, and grid based clustering. This paper discusses various clustering techniques along with their benefits, drawbacks, characteristics, and applications. The paper also discusses various validity measures, which are useful in evaluating cluster quality. The paper discusses issues involved in Particle Swarm Optimization (PSO) and compares various variants of PSO that address the discussed issues. PSO can be applied to partition based clustering for improving performance and quality of resulting clusters. In that connection, the paper discusses about how PSO is useful to solve issues present in partition clustering. Moreover, the paper presents a survey of partition clustering using PSO. This paper would become useful to beginners and researchers in advancing the field of applying data clustering using PSO.