A Real-Time Gait Phase Recognition Method Based on Multi-Information Fusion

In this paper, a novel recognition method of multi-information fusion is proposed to improve the recognition accuracy of the gait phase. Firstly, a multi-information wireless multi-channel gait information acquisition system is built. Then, the system collects multiple gait information including plantar pressure information, joint angle information, and sEMG information, and uses a deep learning convolution neural network (CNN) for fusion to quickly and accurately identify the gait phase. Finally, three kinds of speed task experiments were carried out on three healthy subjects, and different models were compared to study the ability of multi-information used in gait phase recognition at different speeds. The experimental results verify the feasibility and superiority of the method.