Validation of a Gait Analysis Algorithm for Wearable Sensors

Abstract

The world population ageing and the increase of health costs make necessary the development of new technologies and IoT solutions. Smart and wearable systems can improve people's lives, monitoring the elderly and transforming everyday living environments into more connected and sustainable systems. Due to ageing, people tend to suffer more and more from motor problems, so gait analysis is fundamental for many medical and health applications. In this paper, we propose a wearable sensors system for gait analysis constituted of a triaxial accelerometer, gyroscope, and magnetometer with efficient gait analysis algorithms. In this study we have developed an algorithm for the estimation of percentage duration of double support, stride length and stride speed. The results obtained from comparison with the gold standard show errors of 4.3 % for double support duration, 5.9 % for stride length, and 6.3 % for stride speed.