Cluster analysis is one in all the necessary knowledge analysis strategies and could be a terribly advanced task. it's the art of a sleuthing cluster of comparable objects in massive data sets while not requiring such teams by suggests that options or knowledge information bunch on unsure knowledge could be the toughest task in each modeling similarity between uncertain data objects. The foremost of the previous technique for a bunch unsure knowledge extends partitioning clustering algorithms and Density-based mostly clustering algorithms. These strategies are supported by the geometric distance between two unsure knowledge objects. Such technique unable to handle unsure objects, that are cannot distinguishable by victimization geometric characteristics and Distribution associated with object itself isn't thought-about. likelihood distribution could be the most vital characteristic of the unsure object isn't taking under consideration throughout measurement the similarity between 2 uncertain objects. The very fashionable technique Kullback-Leibler divergence won't to measures the distribution similarity between two unsure knowledge objects. Integrates the effectiveness of KL divergence into each partition and density based mostly bunch algorithms to properly cluster unsure knowledge. Calculation of KL-Divergence is extremely expensive to resolve this drawback by victimization well-liked technique kernel density estimation and use the quick Gauss remodel technique to any speed up the computation to decrease execution time