Simulation study of FES-assisted standing up with neural network control.

A neural network (NN) control system is designed for the functional electrical stimulation (FES) assisted standing up. A musculoskeletal model of nine muscles and three segments is constructed for the simulation study. Each muscle is controlled by the sub-network of the functional neural network. The sub-network is the radial basis function (RBF) NN. Minimal resource allocation (M-RAN) learning algorithm is used in the RBF NN design. This system aims to reduce the upper body effort and keep the body balance when the patient stands up. Promising simulation results provide the potential for feasible clinical application in the future.