A Comparative Analysis on the Applicability of Various Mutation Types for Achieving Privacy in medical Data Mining

Achieving privacy in data mining is at present an energetic area of research. During the entire course of data mining a variety of sensitive data gets exposed to several parties. This disclosure of insightful data violates individual privacy. In order to achieve privacy many privacy preserving techniques have been proposed recently and one such technique to preserve privacy is to use various operators in genetic algorithm (GA). In this paper we compare the various mutation techniques in genetic algorithm and their appropriateness to achieve data privacy. From our experimental results it is evident that the outcome of the mutation process depends on various parameters such as type of data and the binary pattern used for replacement.