Abstract
In contemporary muscle-computer interfaces for upper limb prosthetics there is often a trade-off between control robustness and range of executable movements. As a very low movement error rate is necessary in practical applications, this often results in a quite severe limitation of controllability; a problem growing ever more salient as the mechanical sophistication of multifunctional myoelectric prostheses continues to improve. A possible remedy for this could come from the use of multi-label machine learning methods, where complex movements can be expressed as the superposition of several simpler movements. Here, we investigate this claim by applying a multi-labeled classification scheme in the form of a deep convolutional neural network (CNN) to high density surface electromyography (HD-sEMG) recordings. We use 16 independent labels to model the movements of the hand and forearm state, representing its major degrees of freedom. By training the neural network on 16 × 8 sEMG image sequences 24 samples long with a sampling rate of 2048 Hz to detect these labels, we achieved a mean exact match rate of 78.7% and a mean Hamming loss of 2.9% across 14 healthy test subjects. With this, we demonstrate the feasibility of highly versatile and responsive sEMG control interfaces without loss of accuracy.
Highlights
Www.nature.com/scientificreports through muscle, fat- and skin tissue
In the relevant case of hand movement recognition, the class set would consist of the set of detectable movements, while the observation instances are represented either by raw sEMG or sEMG features
This is mainly due to the fact that the EMGs associated with similar movements are highly correlated[17,18] and even a sophisticated classifier used in conjunction with well-crafted features eventually lack sufficient discriminatory power
Summary
Www.nature.com/scientificreports through muscle-, fat- and skin tissue. the sEMG is notably affected by complicated types of noise, such as motion artefacts and other measurement problems[9]. Geng et al.[16] defined the concept of a sEMG image as a grayscale image with intensity values proportional to the raw HD-sEMG measured at a single time instant and achieved unprecedented performance by applying a deep learning image classification algorithm directly on such data From such results it can be postulated that spatial patterns correlated with movement information exists in the instantaneous raw HD-sEMG and allows for exploitation by a classifier. While certainly a useful framework, a problem inherent to multi-class classification approaches is that the performance of any multi-class classifier devised for movement recognition by necessity decreases as the number of classes increase This is mainly due to the fact that the EMGs associated with similar (in the sense of recruiting mutual motor units) movements are highly correlated[17,18] and even a sophisticated classifier used in conjunction with well-crafted features eventually lack sufficient discriminatory power. Those of the convolutional kind, have been successfully utilized for classification of sEMG in the past[16,25,26,27,28], to the best of our knowledge no work has been produced to date where EMG movement decoding is treated as a multi-label classification problem
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
