Generative sEMG Deep Learning for Early Prediction of Locomotion with Small Training Datasets

Page view(s)
151
Checked on Jul 13, 2024
Generative sEMG Deep Learning for Early Prediction of Locomotion with Small Training Datasets
Title:
Generative sEMG Deep Learning for Early Prediction of Locomotion with Small Training Datasets
Journal Title:
IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society
Keywords:
Publication Date:
16 November 2023
Citation:
Huang, Z., Lin, Z., Zhang, H., Wang, C., NG, S. H., Yin Tang, C. K., & Ang, K. K. (2023, October 16). Generative sEMG Deep Learning for Early Prediction of Locomotion with Small Training Datasets. IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society. https://doi.org/10.1109/iecon51785.2023.10312696
Abstract:
Early detection of locomotion intention is highly relevant to the development of intelligent rehabilitation/assistive robotics. While surface electromyography(sEMG) has been a promising tool, it is often challenged by the shear variability of sEMG patterns in contrast to only a handful of sEMG training samples per discrete motion intention class for each individual user to begin with. To address this issue, we introduce a deep convolutional generative adversarial networks (DCGANs), including dynamic time warping (DTW) and fast Fourier transform mean square error (FFT MSE) for artificial signal quality assessment. On a preliminary sEMG data set of 3-class directional lower-limb movement, the proposed method yielded an average accuracy rate of 89.31%±6.52. While this is a feasibility study using healthy human subjects only, the result warrants extended study to further establish the generative adversarial network learning for EMG intention detection in real-world rehabilitation/assistive system applications.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Robotics Programme - Assistive Robotics Programme
Grant Reference no. : M22NBK0074
Description:
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISBN:
979-8-3503-3182-0
Files uploaded:

File Size Format Action
generative-semg-deep-learning.pdf 1.18 MB PDF Request a copy