A Data Clustering Strategy for Enhancing Mutual Privacy in Healthcare System of IoT

Abstract

Recent advances in the healthcare system of Internet of Things (IoT) has led to a generation of a large amount of physic sensor data. Data analyst collects and analyzes these sensor data through wireless sensor network, so as to provide some treatment advices to physicians and patients. As a common data mining method, the k-means clustering algorithm is being applied to process large-scale sensor data. However, it also poses a threat of privacy leakage in the specific application process. To enhance the privacy in healthcare system of IoT, mutual privacypreserving k-means strategy (M-PPKS) based on homomorphic encryption is proposed in this paper, which neither discloses an individual's private information nor leaks the cluster center's characteristic data. An extension performance evaluation shows that, in the case of ensuring accurate clustering results, even if the analyst and individuals collude, the M-PPKS can prevent the disclosure of private information.