H-Watch: An Open, Connected Platform for AI-Enhanced COVID19 Infection Symptoms Monitoring and Contact Tracing

Abstract

The novel COVID-19 disease has been declared a pandemic event. Early detection of infection symptoms and contact tracing are playing a vital role in containing COVID-19 spread. As demonstrated by recent literature, multi-sensor and connected wearable devices might enable symptom detection and help tracing contacts, while also acquiring useful epidemiological information. This paper presents the design and implementation of a fully open-source wearable platform called H-Watch. It has been designed to include several sensors for COVID-19 early detection, multi-radio for wireless transmission and tracking, a microcontroller for processing data on-board, and finally, an energy harvester to extend the battery lifetime. Experimental results demonstrated only 5.9 mW of average power consumption, leading to a lifetime of 9 days on a small watch battery. Finally, all the hardware and the software, including a machine learning on MCU toolkit, are provided open-source, allowing the research community to build and use the H-Watch.

Q-PPG: Energy-Efficient PPG-Based Heart Rate Monitoring on Wearable Devices

“…We deployed TCNs on the embedded system described in [21], whose main board is designed with a wrist-worn form factor. Its picture together with a simplified block diagram of the system is shown in Fig.…”

“…The other two relevant components of the system of [21] for our target applications are two sensors: the MAX30101 [33] and the LSM6DSM [34]. The former is a low-power pulse oximeter and PPG module, while the latter is a 6-axes Inertial Measurement Unit (IMU).…”

“…This hardware-friendly quantization enables further model size reductions, thus enriching and improving the Pareto frontier. • We deploy the models resulting from our search on a real embedded platform with a smartwatch form-factor [21].…”

“…Fig.1. Wrist-worn form factor board presented in[21] used in our experiments and its simplified block diagram.…”

Investigating the RSSI-based Distance Classification using Median Confidence Interval in a Multi-Device BLE Environment

“…Emerging low power wireless technologies, such as BLE, have enabled dynamic wireless communication between devices and paved the way for IoT applications in automation, health, tracking, etc (Lubis & Basari, 2020;Polonelli et al, 2021). BLE is particularly suited to power-constrained applications, and its beacon technology offers efficient location-based services, which can be used in unmanned proximity-based applications (Jeon et al, 2018;Lubis & Basari, 2020;Polonelli et al, 2021). The neighbor discovery process (NDP) of BLE is used in proximity-based applications, where devices send information in the form of advertising packets over advertising channels to be discovered by scanners (Song et al, 2019).…”