Edge IoT System for Wearable Devices: Real-Time Data Processing, Inference, and Training for Activity Monitoring and Health Evaluation

Abstract

Developing a medical device or solution involves gathering biomedical data from different devices, which can have different communication protocols, characteristics and limitations. Thus, deploying a test lab to record experiments can be challenging, requiring the synchronisation of the source signals, processing of the information, storing it and extracting conclusions. In this work, we face this problem by developing an edge Internet of Things (IoT) system composed of a Raspberry Pi and an NVIDIA Jetson TX2 device (integrating an NVIDIA Pascal GPU). The information from two biomedical devices (Biosignals Plux and Polar Verity Sense) is synchronised and fused, interpolating the information and extracting features such as mean and standard deviation in real-time. In parallel, the Jetson TX2 device is able to execute a Deep Learning (DL) model in real-time as new data is received using the Message Queuing Telemetry Transport (MQTT) protocol. Also, an online learning approach involving a loss function that takes into account past predictions is proposed, as well as a density-based clustering algorithm that selects the most representative samples of the most repeated class. The system has been deployed in the Smart Home of the University of Almería. Results show that the proposed fusion scheme accuracy represents the intrinsic information of the received data and enables the DL model to run in real time. The next steps involve the deployment of the system in a hospital, in order to monitor epilepsy patients, create a robust dataset and detect epileptic seizures in real-time.