Identifying the fall risk and detecting it is of utmost importance in presenting adverse short-and long-term health consequences of falls. The occurrence of falls is not only caused by biological ageing but also by the fatigue of the lower leg muscles. Hence the ability to quantify muscle fatigue is critical to identifying falls among older people during their daily activities. Most studies on this topic in the literature use offline data analysis methods. This study proposes a mechanism for fatigue detection in real time. We investigate the assessment of muscle fatigue by using a bespoke multi-channel Body Area Sensor Network (BASN) based on surface electromyogram (EMG). Our proposed network of digital EMG electrodes utilises Inter-Integrated Communication (I2C) protocol to provide a multi-channel measurement system. We describe the hardware and firmware development of the proposed platform. We validate the digital electrode in detecting fatigue in the EMG signal methods appropriate for low-power embedded systems, comparing it with the results of a clinical EMG recording system.

Authors:
Eisa Aghchehli, Newcastle University, United Kingdom
Matthew Dyson, Newcastle University, United Kingdom
Kia Nazarpour, The University of Edinburgh, United Kingdom

About the Presenter(s)
I'm Eisa Aghchehli, a Marie-Curie ITN Early Stage Researcher at Newcastle University. My project develops an EMG recording system that leverages on-sensor AI to enhance elderly people's quality of life, funded by the European H2020 project.

Connect on Linkedin
https://uk.linkedin.com/in/eisa-aghchehli-bb3b2b137

Connect on ResearchGate
https://www.researchgate.net/profile/Eisa-Aghchehli-2

See this presentation on the full schedule – Friday Schedule

Bookmark