Skip to main navigation Skip to main content
  • E-Submission

JKSPE : Journal of the Korean Society for Precision Engineering

OPEN ACCESS
ABOUT
BROWSE ARTICLES
EDITORIAL POLICIES
FOR CONTRIBUTORS
REGULAR

순환 신경망을 이용한 착용형 관성센서기반 하지 관절 역학 추정

Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network

Journal of the Korean Society for Precision Engineering 2023;40(8):655-663.
Published online: August 1, 2023

1 한경국립대학교 ICT로봇기계공학부

2 한경국립대학교 융합시스템공학과

1 School of ICT, Robotics & Mechanical Engineering, Hankyong National University

2 Department of Integrated Systems Engineering, Hankyong National University

#E-mail: jklee@hknu.ac.kr, TEL: +82-31-670-5112
• Received: April 14, 2023   • Revised: May 31, 2023   • Accepted: June 2, 2023

Copyright © The Korean Society for Precision Engineering

This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

  • 312 Views
  • 0 Download
  • 1 Crossref
  • 1 Scopus
prev next

Citations

Citations to this article as recorded by  Crossref logo
  • Long-duration Recovery of Missing Marker in Optical Motion Capture Using Rigid Body Constraints and IMU Signals
    Han Sol Woo, Ji Hoon Park, Chang June Lee, Jung Keun Lee
    Journal of the Korean Society for Precision Engineering.2026; 43(7): 745.     CrossRef

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

Include:

Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network
J. Korean Soc. Precis. Eng.. 2023;40(8):655-663.   Published online August 1, 2023
Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:
Include:
Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network
J. Korean Soc. Precis. Eng.. 2023;40(8):655-663.   Published online August 1, 2023
Close

Figure

  • 0
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network
Image Image Image Image Image Image Image
Fig. 1 Free-body diagrams of (a) foot segment and (b) arbitrary segment i
Fig. 2 Architecture of the recurrent neural network for joint kinetics estimation
Fig. 3 Experimental setup
Fig. 4 Experiment motions
Fig. 5 Scheme of splitting into training data and test data
Fig. 6 Estimation results of (a) joint force and (b) moment of Test 2 from Subject 3
Fig. 7 Estimation results of (a) joint force and (b) moment of Test 3 from Subject 6
Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network
(a) Joint force [N]
Ankle Knee Hip
M1 M2 M3 M1 M2 M3 M1 M2 M3
Test1 Subject1 0.13 0.19 2.21 1.14 1.23 2.18 4.00 5.20 2.50
Subject2 0.11 0.12 2.12 1.19 1.41 2.29 4.35 4.62 3.11
Test2 Subject3 0.17 0.23 2.30 1.23 1.51 2.22 3.90 4.92 3.00
Subject4 0.17 0.18 1.97 1.26 1.53 2.02 4.51 4.58 2.51
Test3 Subject5 0.23 0.40 2.45 1.23 1.96 2.58 3.06 6.30 3.07
Subject6 0.20 0.27 4.37 1.54 1.57 3.02 4.49 4.60 3.78
Average 0.17 0.23 2.57 1.26 1.53 2.39 4.05 5.04 3.00
(b) Joint moment [Nm]
Ankle Knee Hip
M1 M2 M3 M1 M2 M3 M1 M2 M3
Test1 Subject1 0.98 1.53 1.15 2.72 3.65 1.21 8.06 8.72 1.79
Subject2 1.80 1.97 4.63 4.09 4.56 4.49 7.14 4.80 2.94
Test2 Subject3 1.37 2.41 1.54 6.21 7.47 1.67 10.94 12.03 2.08
Subject4 1.13 1.30 3.97 3.62 3.15 3.14 10.5 12.25 2.44
Test3 Subject5 2.19 2.67 1.85 2.48 6.42 3.48 4.28 8.64 4.77
Subject6 1.74 5.09 2.61 3.01 5.40 3.08 6.60 9.84 4.89
Average 1.54 2.50 2.63 3.69 5.11 2.84 7.92 9.38 3.15
Table 1 Averaged RMSE of the (a) joint force and (b) moment estimation