Functional Electrical Stimulation System for Drop Foot Correction Using a Dynamic NARX Neural Network

Neurological diseases may reduce Tibialis Anterior (TA) muscle recruitment capacity causing gait disorders, such as drop foot (DF). The majority of DF patients still retain excitable nerves and muscles which makes Functional Electrical Stimulation (FES) an adequate technique to restore lost mobility. Recent studies suggest the need for developing personalized assist-as-needed control strategies wearable FES in order promote natural functional movements while reducing early onset fatigue. This study contributes a real-time implementation trajectory tracking strategy correction. combines feedforward Non-Linear Autoregressive Neural Network with Exogenous inputs (NARXNN) feedback PD controller. advances user-specific TA model achieved by NARXNN’s ability dynamic systems relying on angle angular velocity inputs. A closed-loop, fully stimulation system was using ISTim stimulator inertial sensor electrical user’s kinematic sensing, respectively. Results showed that NARXNN architecture 2 hidden layers 10 neurons provided highest performance modelling behaviour muscle. proposed revealed low discrepancy between real reference trajectories (goodness fit = 77.87%) time-effectiveness correctly stimulating towards