Effective Methods to Improve the Performance of K Means Clustering Algorithm

Abstract

Clustering is the data mining technique that has attracted a great deal of attention in the information industry and in society as a whole, due to the wide availability of huge amount of data and imminent need for turning such data into useful information and knowledge. By automated clustering, dense and sparse region in object space are identified and therefore discovers the overall distribution patterns and interesting correlations among data attributes. Various clustering techniques are available in the literature. When large data are involved the clustering may degrade. This drags the researchers to provide a better clustering technique to handle with large data. K-means clustering algorithm is one of the most widely used algorithms in clustering techniques because of its simplicity and performance. The initial centroid for K-means clustering is generated randomly. Efficiency of the K-means algorithm heavily rely on the initial centroid. The performance of K-means clustering is highly affected when the dataset used is of high dimension. The accuracy and time complexity is highly dropped because of the high dimension data. newline