Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

By Manfredo Atzori, Matteo Cognolato, Henning Müller. Front. Neurorobot., 2016

582 citations recorded by the source corpus.

Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

Subfields: Biomedical Engineering, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/c159a5c8206e79992c0403853af59c9e4889f667

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Human-Computer Interaction

Citations in the corpus

Surface EMG-Based Inter-Session Gesture Recognition Enhanced by Deep Domain Adaptation (2017, methodology): “[49] also employed a ConvNet-based gesture classifier to recognize hand gestures from a 150 ms window of sEMG signals in the NinaPro database.”
Deep learning for healthcare applications based on physiological signals: A review (2018, background): “, 2016 [65] Hand movement classification CNN NinaPro DB [62] accuracy: 66.”
Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network (2017, methodology): “Atzori et al. (2016) applied a CNN classifier on the NinaPro dataset, which reached an average accuracy of 60.27% on DB2 taking a total training time of 1 h and 42min.”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “eing trained with data preprocessed by wavelet decomposition [138]. Also, a lapse of responsiveness warning system was proposed using RNN (LSTM) [32]. Using CNN Park & Lee [134] and Atzori et al. [8] decoded hand movements from EMG signals. ECG Arrhythmias were successfully detected using DBN [1”
Comparison of six electromyography acquisition setups on hand movement classification tasks (2017, background): “Offline data analysis on public benchmark datasets on the other hand can be performed by any researcher worldwide (including a wide community of scientists that are highly specialized in machine learning) and it allows the immediate comparison of different methods (including very recent ones [8]) an”
Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning (2018, methodology): “Recently, researchers have proposed deep learning approaches [4], [5], [6], shifting the paradigm from feature engineering to feature learning.”
Deep Learning on 1-D Biosignals: a Taxonomy-based Survey (2018, unknown): “, [81] proposed to classify the movements of a prosthetic hand using a CNN model.”
Deep Learning for EMG-based Human-Machine Interaction: A Review (2021, methodology): “[81] developed a TCN-based network named TEMPONet, which runs on an embedded system.”