EMG-based Force Estimation using Artificial Neural Networks
In this paper, the surface electromyogram (sEMG) signals acquired from linear surface electrode arrays, placed on the long head and short head of biceps brachii, and brachioradialis during isometric contractions are used to estimate force induced at the wrist using an artificial neural network (ANN).We extracted some features, in time and frequency domain, from sEMG signals and used them as inputs to the ANN model. Different hidden layer sizes were considered to investigate its effect on the model accuracy and find the appropriate number of neurons for our problem. Also, we studied the model accuracy, where we used features individually as the model’s input. The best accuracy, during train, validation and test, was obtained for the maximum number of sEMG features.