Trustworthy Health Monitoring Based on Distributed Wearable Electronics With Edge Intelligence
Chaowei Wang, Ziye Wang, Weiwei Guan, Wenjie Wang, Lexi Xu, Lihua Li, Sai Huang, Weidong Wang
Abstract
The rapid development of smart healthcare and the increasing number of wearable devices in consumer electronics can facilitate health monitoring services with lower latency and less energy consumption, and provide more reliable computation and communication for medical cares. In this paper, we consider the next generation (next-gen) wearable consumer electronics architecture and introduce D2D communication in a trustworthy health monitoring system that utilizes collaborative computing among different wearables to reduce the execution cost of health monitoring tasks and improve the efficiency of medical services, which can monitor several health indicators of the human body in real-time. We further construct a device-collaborative offloading framework for health monitoring (DCO-HM) to reduce energy consumption and computational latency. A directed acyclic graph (DAG)-based offloading algorithm, in which wearables can execute medical tasks locally or perform device-collaborative computation, is proposed. We also consider the priority of task execution and the CPU frequency of wearables to achieve distributed smart monitoring. The simulation results show that the proposed device-collaborative computing scheme significantly improves the computational efficiency of smart health monitoring system with a trustworthy manner.