Data Anonymization Using Augmented Rotation of Sub-Clusters for privacy preservation in data mining

The increase in size of data in current scenario raises the problem of providing privacy by not deteriorating its accuracy and usability. Among the various existing methodologies data Anonymization takes its place as the procedure is simple and provides better privacy. In this paper, an augmented Anonymization technique is explained which has a better performance compared to the existing methods. The data are altered by forming sub-clusters followed by an Isometric transformation. The method is explained by the algorithm, its performance is compared with base-line techniques for various numbers of sub-clusters and the results are provided with related graphs.