The Uniform Effect of K-means Clustering

Abstract

This chapter studies the uniform effect of K-means clustering. As a well-known and widely used partitional clustering method, K-means has attracted great research interests for a very long time. Researchers have identified some data characteristics that may strongly impact the performance of K-means clustering, including the size of the data, the sparseness of the data, noise and outliers in the data, types of attributes and data sets, and scales of attributes.