Joint Angle and Torque Estimation Using Multifrequency Electrical Impedance Myography and Surface Electromyography

Joint Angle and Torque Estimation Using Multifrequency Electrical Impedance Myography and Surface Electromyography

This article explores the feasibility of combining surface electromyography (sEMG) and multifrequency electrical impedance myography (mfEIM) for predicting joint angles and torques. We utilize a current-limited multifrequency electrical impedance spectrometer to simultaneously perform mfEIM on the b...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal Vol. 24; no. 20; pp. 32651 - 32659
Main Authors: Schouten, Martijn, Baars, Ewout C., Yavuz, Utku S., Krijnen, Gijs
Format: Journal Article
Language:English
Published: New York IEEE 15-10-2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Biomedical measurement
Control
Degrees of freedom
Elbow (anatomy)
Electrical impedance
electrical impedance myography (EIM)
electrical impedance tomography (EIT)
Electromyography
electromyography (EMG)
exoskeleton
Exoskeletons
Impedance
multifrequency electrical impedance tomography (MFEIT)
Muscles
Neural networks
Performance prediction
Sensors
time delay neural network (TDNN)
Torque
Torque measurement
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article explores the feasibility of combining surface electromyography (sEMG) and multifrequency electrical impedance myography (mfEIM) for predicting joint angles and torques. We utilize a current-limited multifrequency electrical impedance spectrometer to simultaneously perform mfEIM on the biceps brachii and triceps brachii at 14 frequencies. The same system also measures the sEMG signals using the same electrodes. Measurements are conducted while subjects perform tasks in a 1-degree-of-freedom (DOF) exoskeleton, which enables the measurement of elbow joint torque and angle. We train time-delay neural networks (TDNNs) to model the relationships between mfEIM, sEMG, joint torque, and joint angle. The results demonstrate that the sEMG signal can predict joint torque and that mfEIM can predict joint angle. Additionally, we find indications that a combination of sEMG and mfEIM enhances joint torque predictions compared to using sEMG alone. We also determine the delays between the sEMG, mfEIM signals, and the joint angle and torque, finding that the joint torque signal has a delay relative to the sEMG signal of 155 ms during an isometric exercise and 125 ms during dynamic tasks. These results suggest that combining sEMG and mfEIM measurements could provide additional insights during biomedical experiments.
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2024.3449286