Federated Learning Driven Secure Internet of Medical Things
Junqiao Fan, Xuehe Wang, Yanxiang Guo, Xiping Hu, Bin Hu
Abstract
With the outbreak of COVID-19, people are experiencing increasing physical and mental health issues. Therefore, personal daily healthcare and monitoring become vital for our physical and mental well being. As a combination of the Internet of Things (IoT) and healthcare services, the Internet of Medical Things (IoMT) has emerged to provide intelligent medical services. However, privacy and security concerns have deterred its wide adoption. In this article, we propose a Federated Learning Driven IoMT (FLDIoMT) framework, which aims to support flexible deployment of IoMT services and address the privacy and security issues at the same time. Also, a systematic workflow of IoMT services is proposed to show an efficient data processing and analysis scheme for specific medical applications. Moreover, we demonstrate the feasibility of the proposed FLDIoMT framework by implementing a novel sleep monitoring system called iSmile.