A Novel Silhouettes Cluster Internal Evaluation Index Based on Granular-Ball

Cluster internal evaluation index is used to evaluate and guide the results of clustering, which has been considered as one of the vital issues in the application of clustering. Granular-ball is the multi-granularity characterization of the data set, In this paper, the classic Silhouettes indexes were improved by using granular-ball to represent the grain, we proposed a Silhouettes cluster internal evaluation index based on granular-ball(GSCVI), GSCVI can effectively obtain the optimal number of clusters for arbitrary-shaped and noisy data sets, and it is superior to most of the existing indexes for both artificial and real data sets.