Convolutional LSTM: a deep learning approach to predict shoulder joint reaction forces

Abstract

We developed a Convolutional LSTM (ConvLSTM) network to predict shoulder joint reaction forces using 3D shoulder kinematics data containing 30 different shoulder activities from eight human subjects. We considered simulation outcomes from the AnyBody musculoskeletal model as the baseline force dataset to validate ConvLSTM model predictions. Results showed a good correlation (>80% accuracy, r ≥ 0.82) between ConvLSTM predicted and AnyBody estimated force values, the generalization of the developed model for novel task type (p-value = 0.07 ∼ 0.33), and a better prediction accuracy for the ConvLSTM model than conventional CNN and LSTM models.

Keywords:

• Deep learning network
• AnyBody musculoskeletal modelling
• convolutional LSTM
• shoulder movement
• shoulder joint reaction forces

Acknowledgments

The authors thank Dr. Ashish Nimbarte from the West Virginia University for facilitating the experimental kinematics data and Karan Shah from the Texas Tech University for assisting in data processing.

Disclosure statement

No potential conflict of interest was reported by the authors.

Funding

The author(s) reported there is no funding associated with the work featured in this article.