Physics-informed Deep Learning for Muscle Force Prediction with Unlabeled sEMG Signals
This addresses the challenge of high computational latency in physics-based models and the need for labeled data in data-driven methods for biomechanical analysis, offering a more practical solution for researchers and clinicians.
The paper tackles the problem of predicting muscle forces from unlabeled surface electromyography (sEMG) signals by proposing a physics-informed deep learning method that embeds the Hill muscle model into a neural network as an additional loss, achieving comparable or lower RMSE and higher coefficient of determination compared to baseline methods that require labeled data.
Computational biomechanical analysis plays a pivotal role in understanding and improving human movements and physical functions. Although physics-based modeling methods can interpret the dynamic interaction between the neural drive to muscle dynamics and joint kinematics, they suffer from high computational latency. In recent years, data-driven methods have emerged as a promising alternative due to their fast execution speed, but label information is still required during training, which is not easy to acquire in practice. To tackle these issues, this paper presents a novel physics-informed deep learning method to predict muscle forces without any label information during model training. In addition, the proposed method could also identify personalized muscle-tendon parameters. To achieve this, the Hill muscle model-based forward dynamics is embedded into the deep neural network as the additional loss to further regulate the behavior of the deep neural network. Experimental validations on the wrist joint from six healthy subjects are performed, and a fully connected neural network (FNN) is selected to implement the proposed method. The predicted results of muscle forces show comparable or even lower root mean square error (RMSE) and higher coefficient of determination compared with baseline methods, which have to use the labeled surface electromyography (sEMG) signals, and it can also identify muscle-tendon parameters accurately, demonstrating the effectiveness of the proposed physics-informed deep learning method.