Abstract
High-density surface electromyography (HD-sEMG) and deep learning technology are becoming increasingly used in gesture recognition. Based on electrode grid data, information can be extracted in the form of images that are generated with instant values of multi-channel sEMG signals. In previous studies, image-based, two-dimensional convolutional neural networks (2D CNNs) have been applied in order to recognize patterns in the electrical activity of muscles from an instantaneous image. However, 2D CNNs with 2D kernels are unable to handle a sequence of images that carry information concerning how the instantaneous image evolves with time. This paper presents a 3D CNN with 3D kernels to capture both spatial and temporal structures from sequential sEMG images and investigates its performance on HD-sEMG-based gesture recognition in comparison to the 2D CNN. Extensive experiments were carried out on two benchmark datasets (i.e., CapgMyo DB-a and CSL-HDEMG). The results show that, where the same network architecture is used, 3D CNN can achieve a better performance than 2D CNN, especially for CSL-HDEMG, which contains the dynamic part of finger movement. For CapgMyo DB-a, the accuracy of 3D CNN was 1% higher than 2D CNN when the recognition window length was equal to 40 ms, and was 1.5% higher when equal to 150 ms. For CSL-HDEMG, the accuracies of 3D CNN were 15.3% and 18.6% higher than 2D CNN when the window length was equal to 40 ms and 150 ms, respectively. Furthermore, 3D CNN achieves a competitive performance in comparison to the baseline methods.
Highlights
Prosthetic hands that are capable of performing various movements have been, from a mechanical point of view, remarkably improved since the last decade
The results show that, where the same network architecture is used, 3D convolutional neural network (CNN) can achieve a better performance than 2D CNN, especially for CSL-HDEMG, which contains the dynamic part of finger movement
In the case of the same network architecture, 3D convolution can achieve a better performance than the combination of 2D convolution and majority voting, especially for the Surface electromyography (sEMG) data that contain the dynamic part of the finger movement
Summary
Prosthetic hands that are capable of performing various movements have been, from a mechanical point of view, remarkably improved since the last decade. The lack of an effective control interface still prevents its practical application in amputees. Surface electromyography (sEMG) is the non-invasive electrical recording of muscle activity and provides access to neural information associated with human movement. In comparison to touch screens and keyboards, the sEMG-based interface could offer a natural and intuitive way of controlling for disabilities. From its inception until now, the myoelectric prosthesis has been designed with trigger control, proportional control, and pattern recognition-based control [1]. In the pattern recognition-based control approach, a classifier trained with supervised learning was employed to map sEMG activity to one of the predefined classes that correspond to different control commands.
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.
