Privacy Preservation using T-Closeness with Numerical Attributes

Abstract

Data mining is a process that is used to retrieve the knowledgeable data from the large dataset. Information imparting around two associations will be basic done a large number requisition zones. As people are uploading their personal data over the internet, however the data collection and data distribution may lead to disclosure of their privacy. So, preserving the privacy of the sensitive data is the challenging task in data mining. Many organizations or hospitals are analyzing the medical data to predict the disease or symptoms of disease. So, before sharing data to other organization need to protect the patient personal data and for that need privacy preservation. In the recent year�s privacy preserving data mining has being received a large amount of attention in the research area. To achieve the expected goal various methods have been proposed. In this paper, to achieve this goal a pre-processing technique i.e. k-means clustering along with anonymization technique i.e. k-anonymization and t-closeness and done analysis which techniques achieves more information gain.