Improving Performance of K-Means Clustering by Initializing Cluster Centers Using Genetic Algorithm and Entropy Based Fuzzy Clustering for Categorization of Diabetic Patients

Medical Data mining is the process of extracting hidden patterns from medical data. Among the various clustering algorithms, k-means is the one of most widely used clustering technique. The performance of k-means clustering depends on the initial cluster centers and might converge to local optimum. K-Means does not guarantee unique clustering because it generates different results with randomly chosen initial clusters for different runs of k-means. This paper investigates the use of two methods namely Genetic Algorithm (GA) and Entropy based fuzzy clustering (EFC) to assign k-means initial cluster centers for clustering PIMA Indian diabetic dataset. Experimental results show markable improvement of 3.06% reduction in the classification error and execution time of k-means clustering initialized by GA and EFC when compared to k-means clustering with random cluster centers.