Privacy Preserving in Data stream classification using different proposed Perturbation Methods

Data mining is extracts valuable knowledge from large amounts of data. Recently, data streams are emerging as a new type of data, which are different from traditional static data. The characteristics of data streams are: Data has timing preference; data distribution changes constantly with time; the amount of data is enormous; Data flows in and out with fast speed; and immediate response is required. Traditional algorithm is designed for the static database. If the data changes, it would be necessary to rescan the database, which leads to more computation time and inability to promptly respond to the user. The issue of privacypreserving data mining has widely been studied and many techniques have been proposed. However, existing techniques for privacy-preserving data mining are designed for traditional static databases and are not suitable for data streams. So the privacy preservation issue of data streams mining is very important issue. We proposed methods and algorithms which extends the existing process of data streams classification to achieve privacy preservation.