Robust seed selection algorithm for k-means type algorithms

TL;DR

This paper introduces a new seed selection algorithm for k-means clustering that is robust, outlier-insensitive, and produces consistent, high-quality clustering results across multiple runs.

Contribution

It extends k-means++ with a novel seed selection method that improves robustness and consistency in clustering outcomes.

Findings

The new algorithm outperforms existing seed selection methods on synthetic data.

It produces more stable clustering results across multiple runs.

Effective on real-world and microarray datasets.

Abstract

Selection of initial seeds greatly affects the quality of the clusters and in k-means type algorithms. Most of the seed selection methods result different results in different independent runs. We propose a single, optimal, outlier insensitive seed selection algorithm for k-means type algorithms as extension to k-means++. The experimental results on synthetic, real and on microarray data sets demonstrated that effectiveness of the new algorithm in producing the clustering results