Privacy preserving for spatio-temporal data publishing ensuring location diversity using K-anonymity technique

The rise of mobile technologies are in lead to leverage large amount of personal location information. From knowledge discovery in different point of view, these data are usable, but that personal information is the privacy concerns. There exist many algorithms in the literature namely, perturbing, suppression, generalizing their data to satisfy privacy, required by individuals. Current techniques try to ensure distinguishability between trajectories in real dataset. K-anonymity used for real dataset works on lack of diversity in sensitive regions. We propose a privacy of confidentiality that ensures location diversity by limiting probability of user visiting a sensitive location or probabilistic analysis based on adversary knowledge. Anonymizing trajectory with underlying map, that is interest of point create confusion areas around sensitive locations. Then use map anonymization as a anonymize trajectories and probabilistic methods to improve diversified trajectory and location show to be satisfied diversification effectively.