Neural network based approximation of muscle and joint contact forces during jumping and landing

Daniel J. Cleather^{1 2}

¹ St Mary’s University, Waldegrave Road, Twickenham, TW1 4SX, United Kingdom
² Institute for Globally Distributed Open Research and Education (IGDORE)

Background: ‪Musculoskeletal models have been used to estimate the muscle and joint contact forces expressed during movement. One limitation of this approach, however, is that such models are computationally demanding, which limits the possibility of using them for real-time feedback. One solution to this problem is to train a neural network to approximate the performance of the model, and then to use the neural network to give real-time feedback.

Material and methods: In this study, neural networks were trained to approximate the FreeBody musculoskeletal model for jumping and landing tasks.

Results: The neural networks were better able to approximate jumping than landing, which was probably a result of the greater variability in the landing data set used in this study. In addition, a neural network that was based on a reduced set of inputs was also trained to approximate the outputs of FreeBody during a landing task.

Conclusions: ‪These results demonstrate the feasibility of using neural networks to approximate the results of musculoskeletal models in order to provide real-time feedback. In addition, these neural networks could be based upon a reduced set of kinematic variables taken from a 2-dimensional video record, making the implementation of mobile applications a possibility.

Key words: musculoskeletal modelling, FreeBody, machine learning, real-time feedback, biofeedback.