Performance Validation of the Modified K-Means Clustering Algorithm Clusters Data

In this paper, we present the Modified K-Means Clustering algorithm Analysis and performance, the clustering analysis can be used to partition the cluster data with number of choice clusters and perform each cluster if it can form properly or not and it can pertain by using the silhouette coefficient method. In this one the silhouette coefficient can apply on the group of author’s Hand G-indices with same or different features [1]. The silhouette coefficient analysis can be used to separate the distance from each resulting clusters, the silhouette value measures and shows how each point in one cluster with other points in another cluster and also visually it provides how those cluster are formed with effectively the main functionality of the clustering analysis is to identify the quality assessment of the clustering results. The silhouette index investigated and suggests that the use of the preprocessor improves the quality of clusters significantly for the h and g indices data sets. Furthermore, it is then shown that the modified K-means algorithm good quality, compact and well-separated clusters of the h and g indices data