Design and Deployment of a Wireless BAN at the Edge for Reliable Healthcare Monitoring

Body Area Networks (BANs) have attracted a lot of research interest in the last decades as also witnessed by standardization activities and European Commission fundings. Today, commercial devices, which implement simplified BAN monitoring have appeared, although they usually imply expensive subscription costs or need for a supporting device carried by the user (e.g. a smart phone) which, in case of elderly people, cannot be easily held. However, the integration between commercial devices and external sensors located on/in the body is still an open issue due to the limited processing capabilities of low cost commercial devices. Also, no tools for anomaly detection aimed at reliable healthcare monitoring are currently commercially available. In this paper, we focus on Cloud-Assisted BANs and evolve this vision according to the emerging paradigm of edge computing. We present design, implementation and experimentation of a wireless BAN system which performs data transmission using a commercial, cheap, off-The-shelf gateway smart watch. A mechanism for prompt anomaly detection at the edge node is also supported for the purpose of reliable healthcare monitoring as well as pre-filtering of the data at the smart device itself. Also, in order to reduce the overhead caused by propagation of useless and time-correlated data, and to guarantee a prompt action in case of emergency, edge network nodes located closer to the patient BAN are exploited since they can execute machine learning algorithms to process large amounts of data and activate potential alerts in a shorter time and without overloading the cloud. In this work we describe a real system and evaluate the effectiveness of the approach in terms of false alarm probability.