An Automatic Clustering Technique for Optimal Clusters

TL;DR

This paper introduces AMOC, an automatic clustering algorithm extending k-means that efficiently finds nearly optimal clusters by merging, validated through experiments on synthetic and real datasets.

Contribution

The paper presents a novel automatic merging approach for k-means that determines optimal clusters without manual intervention.

Findings

AMOC effectively identifies nearly optimal clusters.

The algorithm improves clustering quality in terms of compactness and separation.

Experimental results validate the method's efficiency on diverse datasets.

Abstract

This paper proposes a simple, automatic and efficient clustering algorithm, namely, Automatic Merging for Optimal Clusters (AMOC) which aims to generate nearly optimal clusters for the given datasets automatically. The AMOC is an extension to standard k-means with a two phase iterative procedure combining certain validation techniques in order to find optimal clusters with automation of merging of clusters. Experiments on both synthetic and real data have proved that the proposed algorithm finds nearly optimal clustering structures in terms of number of clusters, compactness and separation.