arrow
返回

Decomposing Task-Relevant Information From Surface Electromyogram for User-Generic Dexterous Finger Force Decoding

delete2024-07-01
delete0
PRE
AI
J
Jiahao Fan
X
Xiaogang Hu *
DOI:10.1109/JBHI.2024.3383598delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Existing electromyographic (EMG) based motor intent detection algorithms are typically user-specific, and a generic model that can quickly adapt to new users is highly desirable. However, establishing such a model remains a challenge due to high inter-person variability and external interference with EMG signals. In this study, we present a feature disentanglement approach, implemented by an autoencoder-like architecture, designed to decompose user-invariant, motor-task-sensitive high-level representations from user-sensitive, task-irrelevant representations in EMG amplitude features. Our method is user-generic and can be applied to unseen users for continuous multi-finger force predictions. We evaluated our approach on eight subjects, predicting the force of three fingers (index, middle, and ring-pinky) concurrently. We assessed the decoder's performance through a rigorous leave-one-subject-out validation. Our developed approach consistently outperformed both the conventional EMG amplitude method and a commonly used feature projection approach, principal component analysis (PCA), with a lower force prediction error (RMSE: 6.91 +/- 0.45 % MVC; R-2 : 0.835 +/- 0.026) and a higher finger classification accuracy (83.0 +/- 4.5%). The comparison with the state-of-the-art neural networks further demonstrated the superior performance of our method in user-generic force predictions. Overall, our methods provide novel insights into the development of user-generic and accurate neural decoding for myoelectric control of assistive robotic hands.
Keyword:
Surface electromyogram
feature decomposition
finger force prediction
neural interface

期刊

IEEE Journal of Biomedical and Health Informatics 封面图
IEEE Journal of Biomedical and Health Informatics
IF:
6.8
论文数:
4.6K
被引数:
2.0W

机构

P
pennsylvania commonwealth system of higher education (pcshe)
学者数:
12.9W
论文数: 11.7W
被引数: 177
引用论文

引用论文

A Vibrational Spectroscopic Study of the Sulfate Mineral Glauberite
err2014-05-09
err0
errOAAI
errAndrés López; Ray L. Frost; Yunfei Xi; Ricardo Scholz
err分享
err收藏
Changes in Cognitive Function Following Bariatric Surgery: a Systematic Review
err2016-07-28
err0
errOAAI
errJoel D. Handley; David M. Williams; Scott Caplin; Jeffrey W. Stephens; Jonathan Barry
err分享
err收藏
Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
err2021-05-24
err34
errOAAI
errCampbell, Evan; Phinyomark, Angkoon; Scheme, Erik
err分享
err收藏
err分享
err收藏
Plasma membrane diffusion of g protein-coupled receptor oligomers
err2008-12-01
err0
errOAAI
errStephen J. Briddon; Jorge Gandía; Olavo B. Amaral; Sergi Ferré; Carme Lluís; Rafael Franco; Stephen J. Hill; Francisco Ciruela
err分享
err收藏
err分享
err收藏
学者 查看更多内容