GTGR-Net: Graph Attentional-Temporal Network for Surface-Electromyography-Based Gesture Recognition

In this process of active rehabilitation assisted by hand rehabilitation robot, the patient’s hand motion intention, that is, the patient’s gesture recognition, plays an important role. Gesture recognition based on sEMG signal is a hot research topic. Due to the spatial correlation and time non-stationary of sEMG signal, this research topic has many difficulties. In order to solve this problem, we come up with a gesture recognition network GTGR-Net based on sEMG signal, which uses the combination of graph attention network and time convolution network to extract the spatiotemporal information of sEMG signal. We verify the effect of our algorithm on three public data sets and achieve good results, which is better than the other ways.