Information Technology (IT) has prompted an exceptionally fundamental development in the healthcare area called electronic health (e-Health). In any case, with detectable and various advantages inalienable from e- Health in distributed computing, its full usage is as yet being hampered by difficulties of security as well as privacy. In the proposed work, multi-datasets are considered for the privacy analysis and it has been downloaded from the University of California at Irvine (UCI) machine learning repository. The dataset consists of a large amount of data as lakhs as or more than lakhs; from the medical datasets, the respective diseases are grouped or clustered by their degree of illness. For clustering, an innovative model has introduced i.e. Multi-Objective Weighted Clustering (MOWC). Moreover, to improve the privacy-preserving for clustered data (patient’s record), it is secured in the cloud with the help of item set mining which works based on the threshold value. The optimal threshold value is chosen by using hybrid optimization; this algorithm mimics the behavior of two different swarms i.e. Salp Swarm and Particle Swarm Optimization (SS-PSO). The results showed that the combination of MOWC and itemset mining algorithm improves the accuracy of e-health care data privacy in all the datasets.
Volume 12 | Issue 4
Pages: 338-350
DOI: 10.5373/JARDCS/V12I4/20201448