The purpose of this study was to develop a system to estimate ground reaction forces during running using inertial measurement units and artificial neural networks. Kinematics of the pelvis and feet and ground reaction forces were measured using an inertial measurement system developed by Casio and Kistler force plates from seventy-nine runners (57 males and 22 females). Two long short-term memory based neural networks were used to estimate the instants of foot-strike and toe-off, and anteroposterior and vertical ground reaction forces from the triaxial accelerations and angular velocities measured by inertial measurement units fixed to the pelvis and foot of support leg. Although there are some limitations due to the small sample size, the results of this study showed the potential of estimating the ground reaction forces during running using a small number of inertial measurement units and artificial neural networks.
© Copyright 2020 ISBS Proceedings Archive (Michigan). Northern Michigan University. Published by International Society of Biomechanics in Sports. All rights reserved.