A Fall Risk Assessment Mechanism for Elderly People Through Muscle Fatigue Analysis on Data From Body Area Sensor Network

With the rapid growth and commercialization of wearable sensor technology, the research community foresees great potential of Body Area Sensor Network (BASN) applications in the healthcare industry, including elderly healthcare. We consider the issue of fall in elderly, which has severe consequences including death. Most of the related proposals in the literature are reactive. In this paper, we propose a proactive Fall Risk Assessment mechanism for elderly by performing Muscle Fatigue Analysis on data collected using BASN consisting of wearable sensors. We first discuss the in-house developed android application that connects with the wearable EMG sensors placed on the human body to collect data of four activities including walking, sitting and getting up from a chair, and ankle stretch (Dorsiflexion and planter flexion) in a controlled environment. Then we present our Fall Risk Assessment algorithm that computes the Fall Risk Assessment score based on various levels of muscle fatigue. We tested our algorithm using four features to determine muscle fatigue in two lower limb muscles i.e. Tibilias (TM) and Gastrocnemius (GM) muscles. The implementation results of various scenarios on Matlab are presented as the proof-of-concept. Our evaluation results of two lower limb muscles behavior in selected activities justify our claim that muscle fatigue in these two muscles could lead to falling in an elderly person.

Automated summary

This paper proposes a proactive Fall Risk Assessment mechanism for elderly by performing Muscle Fatigue Analysis on data collected using wearable sensors. It shows that muscle fatigue in two lower limb muscles could lead to falling in an elderly person, based on evaluation results and simulations on Matlab.