Data mining consists of a very vital task that is clustering, where not only the predictable data but also the clustering of uncertain data can be seen. In the previous papers, to cluster set of uncertain data some basic techniques that were used like DBSCAN, k-means and other methods which bank on distances between the object in a geometrical way. The methods that were used in previous papers cannot tackle with such uncertain data that has high computational complexity, it’s like when a product has alike mean but varies in customer’s grading. Thankfully, the probability distribution method, which is one of the most significant part in uncertain data, and will help in finding efficient ways to overcome the previous methodology used.

Keywords : Uncertainty of Data, Clustering, Fuzzy CMeans, Skew Divergence, Fast Gauss Transformation.