Recurrent Neural Network Models for Myoelectricbased Control of a Prosthetic Hand

Abstract

This paper proposes a set of recurrent neural networks (RNNs) capable of replicating the non-linear mechanism of a prosthetic hand based on surface myoelectric sensors. The experimental results of the RNN show a good result of the system for the training data and an acceptable result on the validation data. A comparison between the developed RNNs and a similar size non-recurrent neural network is included.