Performance Analysis on Modified Hybrid DB Scan Clustering Technique To Enhance Average Total Execution Time

Abstract

This paper shows security and privacy of user data stored in cloud services is of utmost concern especially for commercial public cloud platforms and service providers. The user data stored on cloud is encrypted, and it is desired that data mining operations on encrypted data must be executed efficiently. The proposed system implements a data mining operation namely clustering on encrypted data on cloud platforms using TCP / IP protocol. The clustering operation is performed using standard K-Means, Spectral, Hierarchical, Hybrid DBSCAN and simple DBSCAN clustering technique optimized for encrypted data.