Automatic Clustering with Single Optimal Solution

TL;DR

This paper introduces AMSOS, an algorithm that automatically merges clusters to produce a unique, nearly optimal clustering solution validated by cluster validity measures, applicable to synthetic and real datasets.

Contribution

The paper presents AMSOS, a novel method that automatically generates a single, nearly optimal clustering solution, addressing the lack of algorithms producing unique clusterings.

Findings

AMSOS effectively finds a single, nearly optimal number of clusters.

The algorithm produces clusters with high compactness and separation.

Experimental results validate AMSOS on synthetic and real datasets.

Abstract

Determining optimal number of clusters in a dataset is a challenging task. Though some methods are available, there is no algorithm that produces unique clustering solution. The paper proposes an Automatic Merging for Single Optimal Solution (AMSOS) which aims to generate unique and nearly optimal clusters for the given datasets automatically. The AMSOS is iteratively merges the closest clusters automatically by validating with cluster validity measure to find single and nearly optimal clusters for the given data set. Experiments on both synthetic and real data have proved that the proposed algorithm finds single and nearly optimal clustering structure in terms of number of clusters, compactness and separation.