Automatic Clustering with Single Optimal Solution
This addresses the challenge of non-unique clustering solutions for data analysts, though it appears incremental as it builds on existing methods by adding automatic merging for uniqueness.
The paper tackles the problem of determining the optimal number of clusters in datasets, which lacks unique solutions, by proposing AMSOS, an algorithm that automatically merges clusters to generate a single, nearly optimal clustering structure, with experiments on synthetic and real data confirming its effectiveness in terms of cluster number, compactness, and separation.
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.