The Deep Neural Network Based Classification of Fingers Pattern Using Electromyography

Abstract

In this paper, the Deep Neural Network (DNN) based classification of five fingers Electromyography (EMG) pattern is presented. The aim is to improve EMG signal acquisition and classification accuracy for the robustness of hand control prosthetics. Wavelet Transform (WT) is used to extract a total of 500 feature vectors from five fingers that are used to train an autoencoder based five-layered Deep Neural Network (DNN). The hidden layer holds Sparse Autoencoders followed by a SoftMax layer that are stacked together to form multi-layered feed forward network. Finally, the conjugate gradient backpropagation technique is performed on the whole DNN for mitigating the Mean Square Error (MSE) used to define the performance of DNN. The MSE is evaluated for 5 and 10 neurons being used in the hidden layer which get stabilized at about 500 epochs to a very low value of 0.010498. The overall results showed that designed system is able to capture optimum EMG signals having meaningful information and promises a fruitful accuracy rate of 99.3% with an average error rate of 0.7% for the given dataset. The superlative performance of DNN has shown edge over the existing techniques in literature due to its robustness. In future similar techniques can be extended for use in classification of simultaneous movement of fingers which in turn could provide genuine movements for amputees as compared to exclusive classification of distinct movements.