Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Tommaso Polonelli, Lukas Schulthess, Philipp Mayer, Michele Magno, Luca Benini

TL;DR

The paper addresses the need for early detection of COVID-19 infection symptoms and scalable contact tracing with privacy considerations. It presents H-Watch, a fully open-source wearable platform that fuses multi-sensor health monitoring, on-device neural inference, dual-radio wireless connectivity (BLE 5.0 and NB-IoT), and energy harvesting to achieve long operation on a compact form factor. Key contributions include a complete open hardware and software stack, an energy-harvesting power architecture, on-MCU AI tools (X-CUBE-AI and FANN-ON-MCU), and detailed power and lifetime characterizations demonstrating practical operation in indoor and outdoor lighting conditions. The platform promises a research-ready testbed for remote health monitoring and epidemiological data collection, enabling researchers to study early detection and tracing strategies in real-world settings.

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.

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

TL;DR

The paper addresses the need for early detection of COVID-19 infection symptoms and scalable contact tracing with privacy considerations. It presents H-Watch, a fully open-source wearable platform that fuses multi-sensor health monitoring, on-device neural inference, dual-radio wireless connectivity (BLE 5.0 and NB-IoT), and energy harvesting to achieve long operation on a compact form factor. Key contributions include a complete open hardware and software stack, an energy-harvesting power architecture, on-MCU AI tools (X-CUBE-AI and FANN-ON-MCU), and detailed power and lifetime characterizations demonstrating practical operation in indoor and outdoor lighting conditions. The platform promises a research-ready testbed for remote health monitoring and epidemiological data collection, enabling researchers to study early detection and tracing strategies in real-world settings.

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.
Paper Structure (7 sections, 3 figures, 1 table)

This paper contains 7 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. System Architecture
  3. Power supply and Energy Harvesting
  4. Smart Module and on-board Processing
  5. Wireless Connectivity
  6. Experimental Results
  7. Conclusions

Figures (3)

  • Figure 1: H-Watch logic schematic
  • Figure 2: Solar cell output power in matched condition. The inlet shows the influence of the transducer load on the output power in a single harvesting point at 1900lx.
  • Figure 3: H-Watch mechanical cross-section. (a) LS012B7DH02 LCD display; (b) H-Watch's PCB, (c) Watch case, (d) SP3-12 flexible solar panel.