Decoding Simultaneous Multi-DOF Wrist Movements From Raw EMG Signals Using a Convolutional Neural Network

Pattern recognition (PR) methods are commonly utilized in the extraction of motion intentions from myoelectric signals, which is realized by relating several electromyogram (EMG) patterns to specific types of motion. Researchers have reported that the hand-engineering features widely used in PR-based methods can be significantly affected by external confounding factors that diminish their accuracy and robustness in clinical settings. Moreover, since only simple mapping is carried out from the feature space to the task space (involving, for the most part, discrete motion intentions), there is no opportunity to exploit fully the underlying mechanism of synergic neuromuscular control. Inspired by deep learning, we have proposed a novel convolutional neural network (CNN) structure based on the characteristics of raw EMG signals that can effectively decode complex wrist movements with three degrees of freedom (DOF) directly from raw EMG signals rather than relying on hand-engineering features. Our method has the potential to incorporate more information than other models by enlarging the training dataset. We demonstrate here that our method performs significantly better (in terms of R2) than the current state-of-art regression method (i.e., support vector regression), especially when confounding factors are involved. We further found that this CNN-based decoding method can be generalized when multiple healthy subjects are taken into account. For a new subject, our method can provide an appropriate control over 3-DOF cursor movements on a screen even without a specific training.