FES-induced muscular torque prediction with evoked EMG synthesized by NARX-type recurrent neural network

Functional electrical stimulation (FES) is able to restore motor function of spinal cord injured (SCI) patients. To make adaptive FES control taking into account the actual muscle state with muscular feedback information, torque estimation and prediction are important to be provided beforehand. Evoked EMG (eEMG) has been found to be highly correlated with FES-induced torque under various muscle conditions, indicating that it can be an useful tool for torque/force prediction. To better construct the relationship between eEMG and stimulated muscular torque, nonlinear-arx-type (NARX-type) model is preferred. This paper presents and exploits a NARX-type recurrent neural network (NARX-RNN) model for identification and prediction of FES-induced muscular dynamics with eEMG. Such NARX-RNN model is with a novel architecture for prediction, with robust prediction performance. To make fast convergence for identification of such NARX-RNN, directly-learning pattern is exploited during the learning phase. Due to difficulty of choosing a proper forgetting factor of Kalman filter for predicting time-variant torque with eEMG, such NARX-RNN may be considered to be a better alternative as torque predictor. Data gathered from two SCI patients is used to evaluate the proposed NARX-RNN model. The NARX-RNN model shows promising estimation and prediction performance only based on eEMG.