Prediction of Actively Exerted Torque From Ankle Joint Complex Based on Muscle Synergy

Prediction of actively exerted torque from the ankle joint complex is critical for human-robot interaction because this is the real torque that the patient exerts. In this work, we develop a prediction framework to predict the actively exerted torque from the surface electromyography signal. The modified nonnegative matrix factorization algorithm is used to extract muscle activation information (MAI) and muscle synergy information (MSI); the pseudosiamese network is used to fit the MAI and MSI to actively exerted torque. The prediction accuracy is compared under different ankle attitudes, synergistic feature extraction algorithms, and prediction algorithms, and the results show that the prediction accuracy of the proposed framework is 94.15%, and the variance of prediction accuracy is just 3.56% under different ankle attitudes. The proposed framework can provide the real actively exerted torque for the active rehabilitation training of ankle joint, so as to improve the enthusiasm and initiative of patients during rehabilitation training.