Hybrid Approach with Zero Mean Distribution and Randomization for Privacy Preservation Technique
Mausumi Dey, Anamika Ahirwar · 2017
Currently increasing in data exhaustive processing systems of information is now becomes very important for making decisions in the business or companies. Important and responsive knowledgeable designs may consist in process of the business analysis. Now a day privacy-preserving data-mining may obtain a huge enhancement with the help of data-mining and the researchers of the Information security community in the development of the technologies that are merges with the concerns of privacy. In the original data, the random-noise is added in the privacy preserving data Mining (PPDM) method, that is used for publishing the exact information regarding the actual data. The basic perspective of the privacy preserving data mining is to design various algorithms for updating the actual data and for providing the security to the information which is to be get misused, as a result of this the private data and private information still remain same even after the mining process. This paper calculates the results on comparative dependent analytical of the privacy preserving data mining algorithms and implemented those in MATLAB.