Fully unsupervised clustering in nonlinearly separable data using intelligent Kernel K-Means

Abstract

Intelligent Kernel K-Means is a fully unsupervised clustering technique. This technique is developed by combining Intelligent K-Means and Kernel K-Means. Intelligent Kernel K-Means used to cluster kernel matrix without any information about the number of clusters. The goal of this research is to evaluate the performance of Intelligent Kernel K-Means for clustering nonlinearly separable data. Various artificial nonlinearly separable data are used in this experiment. The best result is the clustering often ring datasets. It produces Adjusted Rand Index (ARI) = 1.