A Hybrid Clustering Approach and Random Rotation Perturbation (RRP) for Privacy Preserving Data Mining
Sivakumar Kaliappan · International journal of intelligent engineering and systems · 2018
The Privacy Preserving Data Mining (PPDM) is known to be the most critical perspective among analysts.As privacy preserving data mining grants, sharing and exchanging of privacy susceptible data for analysis, it has exploited increasingly popular.Since one of the critical aspects of data mining is safeguarding privacy.The diverse technique is embraced for preserving privacy while maintaining the real characteristic of data under consideration.In the proposed work, the high-dimensional data are isolated into various parts by utilizing the k-mean clustering technique and each partition is considered as a cluster.By then the mean estimate of each cluster is processed, after that, the contrast between each cluster member and the mean of the cluster esteem is processed.In the succeeding stage, the clustered information is enhanced by utilizing the Ant Colony Optimization (ACO) algorithm.After that, the optimized clustered particles are perturbed by utilizing the Random Rotation Perturbation (RRP) algorithm which makes the values hard to be recognized.These perturbed values are then stored in the public cloud and the key parameters for randomizing and the clustering is stored in the private cloud.Our approach would contribute in the diminishment of a lot of storage in a private cloud, in case we essentially store the entire sensitive information on private clouds.The experimental results demonstrate that the RRP algorithm has better privacy preserving contrasted with the other existing technique.