STGNN-LMR: A Spatial-Temporal Graph Neural Network Approach Based on sEMG Lower Limb Motion Recognition

Lower limb motion recognition techniques commonly employ Surface Electromyographic Signal (sEMG) as input and apply a machine learning classifier or Back Propagation Neural Network (BPNN) for classification. However, this artificial feature engineering technique is not generalizable to similar tasks and is heavily reliant on the researcher's subject expertise. In contrast, neural networks such as Convolutional Neural Network (CNN) and Long Short-term Memory Neural Network (LSTM) can automatically extract features, providing a more generalized and adaptable approach to lower limb motion recognition. Although this approach overcomes the limitations of human feature engineering, it may ignore the potential correlation among the sEMG channels. This paper proposes a spatial-temporal graph neural network model, STGNN-LMR, designed to address the problem of recognizing lower limb motion from multi-channel sEMG. STGNN-LMR transforms multi-channel sEMG into a graph structure and uses graph learning to model spatial-temporal features. An 8-channel sEMG dataset is constructed for the experimental stage, and the results show that the STGNN-LMR model achieves a recognition accuracy of 99.71%. Moreover, this paper simulates two unexpected scenarios, including sEMG sensors affected by sweat noise and sudden failure, and evaluates the testing results using hypothesis testing. According to the experimental results, the STGNN-LMR model exhibits a significant advantage over the control models in noise scenarios and failure scenarios. These experimental results confirm the effectiveness of the STGNN-LMR model for addressing the challenges associated with sEMG-based lower limb motion recognition in practical scenarios.

Automated summary

This paper proposes a spatial-temporal graph neural network model, STGNN-LMR, for recognizing lower limb motion from multi-channel sEMG. The model automatically extracts features and shows a significant advantage over traditional feature engineering methods. Experimental results demonstrate the superior recognition accuracy of the STGNN-LMR model, as well as its better performance in noise and failure scenarios.