Enhancing Security in Edge Computing Healthcare Analysis by Integration of Deep Learning

Abstract

Healthcare monitoring (HM) enables individuals to track their personal health with the help of different smart devices. The HM employs IoT technologies and cloud architecture for data collection, transmission via smart devices, storage, analysis, and healthcare recommendations. It is quite difficult to process so much data from so many IoT devices in such a short period. Thus, technology frameworks like edge computing might serve as a layer of intermediary communication between users and the cloud. These systems still have drawbacks, though, including poor security, excessive latency, wasteful energy use, inefficient bandwidth use, and a lack of automation. In this research, a Secure Health care monitoring system (Secure-HMS) in edge computing environment using Deep learning networks has been proposed. The suggested system employs a combination of fully homomorphic Quantum Diffie Helman encryption to protect patient health data during transmission and to manage it securely. The suggested method shares the key to convert the plain data into cipher data using the innovative secure Quantum Diffie Hellman key exchange (QDHKE) technique, then uses FH operations on the encrypted data before sending it to the edge server. Furthermore, Multihead Attention Bi-GRU (MA-BGRU) is utilized for prediction and enhancing overall system efficiency. This system mainly serves for real-time health monitoring, controlling the security, predictability, and confidentiality of medical data. The experimental outcomes demonstrate that the Secure-HMS framework's overall security rate by 4.08%, 3.06%, and 2.04% better than Medge-chain, EBPPA, and SDN-based Edge networks respectively.