Human motion intention recognition based on EMG signal and angle signal

Abstract

As the traditional single biological signal or physical signal is not good at predicting the angle value of the knee joint, the innovative fusion of biological signals and physical signals is used to analyze the movement posture of the lower limbs. In order to solve the problem of human movement intention recognition, a wearable is designed. The signal-acquisition experiment platform uses muscle electrical signals and joint angle signals as motion data. After the signals are processed, the KNN algorithm is used to identify the four gait motion modes of the human body to walk naturally, climb stairs, descend stairs, and cross obstacles. The test results show that it is feasible to use the KNN algorithm to analyze the strength of the active and passive muscles of the knee joint movement according to different thigh lift heights, and to predict the knee joint angle value when the human body goes up and down the stairs. The comprehensive prediction accuracy rate reaches 91.45%.