Enhanced Partition-Based Method using Correlation Coefficient

Clustering is one of the important data analysis tools in data mining techniques and k-means [1] is one of the top ten methods for Clustering. Due to the random selection of the first k number of centroids, the standard k-means method highly depends on the selection of preliminary centroids for producing good quality of clusters. This paper introduces an enhanced centroid-based clustering method using a correlation coefficient of clusters. The proposed method was compared with the k-means method, and the experimental results show that our method consistently produces good quality of clusters effectively.