Neural network control of a neural prosthesis to assist with gait for people with muscle weakness

Studies show that about 1.7% of the US population live with some sort of paralysis which can reduce muscle function. Functional electrical stimulation (FES) has been widely used in the biomedical field to increase the functionality of atrophied muscles. The goal of this research was to design, build, and test a neural prosthesis that uses artificial electrical stimulation to improve gait in people with muscle weakness. The overall objectives of this project were to quantify the gait tracking performance of the 3 rd generation prosthesis, and to develop the next generation model by implementing an artificial neural network that automatically controlled the electrical muscle stimulator. The 4th generation prosthesis was programmed to use sensor feedback from three inertial measurement units (IMUs) and four force sensitive resistors (FSRs) to predict the correct stimulation time. The IMUs were used to keep track of the leg movement during gait and the FSRs were used to track the force exerted by the foot at different stages of the gait cycle. Results showed that it was possible to program a highly accurate neural network from the received data of the sensors. After implementing the neural network and the stimulator device to the prosthesis, it was observed that the network correctly predicted when muscle contraction was required and was able to automatically send the stimulation signal.