An efficient multi-resolution Z-tree approach of Skyline probability calculation for uncertain datasets

By definition the skyline points are the points in a given dataset which cannot be dominated by any other points in the same dataset and the skyline probabilities are the possibility of the any point that it will not be dominated by other points. It is found useful in many applications where estimation of possibility of being the best under some constrains are required such as probability of some player for performance etc. till now many approaches has been proposed and published but because of the characteristics of the problem they all required large memory and processing power. In this paper, we proposed and computationally efficient approach for estimating the skyline probabilities for uncertain data. The proposed algorithm utilizes the fundamental relations among the group of points to calculate the skyline probability. Since the properties of dominating points of a group can be taken as the abstract of the group properties the computational complexity can greatly reduce. The simulation of the proposed work shows that the proposed algorithm outperforms the existing algorithms by acceptable margin.