Analysis of K- Means Clustering on Uniform and Non-Uniform Data Set
Cluster Analysis is a process of aggregating theobjects into various groups on the basis of their inter-cluster and
intra-cluster similarities. But since we have large data objects with wide variety which are collected from wide variety of
sources and perhaps include outliers as well, cluster formation still faces challenges over it. It faces many disputes such as a
high dimension of the dataset, arbitrarystructure of clusters, scalability, domain knowledge and noisy data. Currently there
are tremendous clustering algorithms to cleave data effectively had been proposed to address various existing challenges.
The purpose of our paper is to analyze K-Means clustering algorithm on various data sets. In this paper, we have focused on
analyzing the behavior of k-means clustering with uniform and non-uniform data sets.
Keywords— Euclidean,Cluster analysis,Clustering, K-means.