Sparse multi-channel EMG signal gesture recognition based on multi-view deep learning

Lu Wang; Mingjun Qi

doi:10.1117/12.3004170

11 October 2023 Sparse multi-channel EMG signal gesture recognition based on multi-view deep learning

Lu Wang, Mingjun Qi

Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 1280046 (2023) https://doi.org/10.1117/12.3004170
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China

Abstract

In order to improve the accuracy of gesture recognition based on sparse multichannel electromyography (sEMG), this paper proposes a multi-view fusion, multi-stream convolutional parallel neural network model framework using the SIA_delsys_16_movements dataset as a sample and combining classical surface EMG signal features with neural networks. The whole process consists of two parts. In the first part, features with discriminative properties are selected from multiple classical feature sets, and the feature sets are classified into three categories, time domain, frequency domain, and time-frequency domain, according to the different views of the signals. In the second part, the EMG images composed of EMG features from different viewpoints are input into the constructed multi-stream convolutional network, and the multi-stream convolutional network branches to extract and fuse the features from these different EMG images, and the fused features are input into the Softmax layer to classify the gesture actions. The final gesture recognition results demonstrate that the gesture recognition with fused multi-view deep learning has the best accuracy compared to single-view deep learning.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Lu Wang and Mingjun Qi "Sparse multi-channel EMG signal gesture recognition based on multi-view deep learning", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 1280046 (11 October 2023); https://doi.org/10.1117/12.3004170

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available