A comparison of three methods for estimating vertical ground reaction forces in running

Komaris, Dimitrios-Sokratis; Perez-Valero, Eduardo; Jordan, Luke; Barton, John; Hennesy, Liam; O'Flynn, Brendan; Tedesco, Salvatore

A comparison of three methods for estimating vertical ground reaction forces in running

Files

A_COMPARISON_OF_THREE_METHODS_FOR_ESTIMATING_VERTICAL_GROUND_REAC.pdf(382.04 KB)

Published version

Date

2020-07

Authors

Komaris, Dimitrios-Sokratis

Perez-Valero, Eduardo

Jordan, Luke

Barton, John

Hennesy, Liam

O'Flynn, Brendan

Tedesco, Salvatore

Publisher

North Michigan University, NMU Commons

Abstract

The purpose of this study was to compare different approaches for the estimation of biomechanical loads in running. A neural network, a biomechanical model, and a two-mass model were tested on the same data set. The predictions of the neural network were highly accurate for all considered running speeds (average RMSE, 0.11 BW). The biomechanical model returned statistically similar results (p=0.113, 0.14 BW), but with increasing RMS errors at high running speeds. Finally, the two-mass model estimates were independent of running speed, but were the least accurate (RMSE, 0.18 BW).

Keywords

Artificial neural networks , Biomechanics , Motion analysis , Kinematics

Citation

Komaris, D. S., Perez-Valero, E., Jordan, L., Barton, J., Hennesy, L., O'Flynn, B. and Tedesco, S. (2020) ‘A comparison of three methods for estimating vertical ground reaction forces in running’, 38th International Society of Biomechanics in Sport Conference Physical conference, 20-24 July, ISBS Proceedings Archive, 38 (1) Article 14. Available at: https://commons.nmu.edu/isbs/vol38/iss1/14