Fast and Robust General Purpose Clustering Algorithms

Abstract

General purpose and highly applicable clustering methods are usually required during the early stages of knowledge discovery exercises. k-MEANS has been adopted as the prototype of iterative model-based clustering because of its speed, simplicity and capability to work within the format of very large databases. However, k-MEANS has several disadvantages derived from its statistical simplicity. We propose an algorithm that remains very efficient, generally applicable, multidimensional but is more robust to noise and outliers. We achieve this by using medians rather than means as estimators for the centers of clusters. Comparison with k-MEANS, EXPECTATION and MAXIMIZATION sampling demonstrates the advantages of our algorithm.