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

관성센서 기반 상대위치 추정 시 연조직 변형 보상을 위한 인공신경망 적용

Application of Artificial Neural Network for Compensation of Soft Tissue Artifacts in Inertial Sensor-Based Relative Position Estimation

Journal of the Korean Society for Precision Engineering 2022;39(3):233-241.
Published online: March 1, 2022

1 한경대학교 ICT로봇기계공학부

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

#E-mail: jklee@hknu.ac.kr, TEL: +82-31-670-5112
• Received: January 10, 2022   • Revised: February 3, 2022   • Accepted: February 6, 2022

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.

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

Citations

Citations to this article as recorded by  Crossref logo
  • Wearable Inertial Sensors-based Joint Kinetics Estimation of Lower Extremity Using a Recurrent Neural Network
    Ji Seok Choi, Chang June Lee, Jung Keun Lee
    Journal of the Korean Society for Precision Engineering.2023; 40(8): 655.     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:

Application of Artificial Neural Network for Compensation of Soft Tissue Artifacts in Inertial Sensor-Based Relative Position Estimation
J. Korean Soc. Precis. Eng.. 2022;39(3):233-241.   Published online March 1, 2022
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:
Application of Artificial Neural Network for Compensation of Soft Tissue Artifacts in Inertial Sensor-Based Relative Position Estimation
J. Korean Soc. Precis. Eng.. 2022;39(3):233-241.   Published online March 1, 2022
Close

Figure

  • 0
  • 1
  • 2
  • 3
  • 4
  • 5
Application of Artificial Neural Network for Compensation of Soft Tissue Artifacts in Inertial Sensor-Based Relative Position Estimation
Image Image Image Image Image Image
Fig. 1 Relative positions between body segments
Fig. 2 Architecture of the proposed deep ANNs
Fig. 3 Experimental setup with inertial sensors and optical markers
Fig. 4 Test motions
Fig. 5 Estimation results of test 2 from subject 2
Fig. 6 Pelvis-to-foot reference position and estimation error of test 2 from subject 2
Application of Artificial Neural Network for Compensation of Soft Tissue Artifacts in Inertial Sensor-Based Relative Position Estimation

Averaged RMSEs of relative position estimations

(Unit: mm)

Pelvis-to-thigh Thigh-to-shank Shank-to-foot Pelvis-to-foot
Test 1 M1 M2 M3 M1 M2 M3 M1 M2 M3 M1 M2 M3 M4
Subject 1 8.23 7.27 6.74 7.42 7.07 6.42 4.43 5.14 3.41 13.66 13.49 12.98 12.32
Subject 2 11.77 10.50 8.09 15.83 13.76 11.53 6.80 7.76 3.81 23.59 23.57 18.34 21.52
Subject 3 12.43 10.50 9.44 8.16 8.13 6.85 8.66 8.49 3.35 22.74 21.18 17.58 19.44
Average 10.81 9.42 8.09 10.47 9.65 8.27 6.63 7.13 3.52 20.00 19.41 16.30 17.76
Test 2 M1 M2 M3 M1 M2 M3 M1 M2 M3 M1 M2 M3 M4
Subject 1 8.72 9.76 5.04 6.00 5.23 4.64 3.45 3.00 1.93 15.74 13.96 10.67 11.84
Subject 2 11.54 8.80 4.77 12.53 13.99 6.94 5.96 3.39 1.66 22.97 20.66 12.69 16.50
Subject 3 7.76 6.39 6.00 5.73 6.25 6.04 5.16 4.17 2.02 14.07 13.49 13.72 15.04
Average 9.34 8.32 5.27 8.09 8.49 5.87 4.86 3.52 1.87 17.59 16.04 12.36 14.46
Test 3 M1 M2 M3 M1 M2 M3 M1 M2 M3 M1 M2 M3 M4
Subject 1 5.26 5.25 4.33 5.14 5.58 5.01 2.44 2.42 1.97 9.50 9.48 7.51 7.35
Subject 2 10.01 7.81 7.29 15.13 9.30 7.32 4.37 2.28 1.91 24.82 15.84 14.31 15.87
Subject 3 8.23 7.57 6.15 6.39 6.80 5.38 3.98 2.90 2.19 11.59 12.66 11.36 12.97
Average 7.83 6.88 5.92 8.89 7.23 5.90 3.60 2.53 2.02 15.30 12.66 11.06 12.06
Test 4 M1 M2 M3 M1 M2 M3 M1 M2 M3 M1 M2 M3 M4
Subject 1 7.37 4.97 3.70 4.30 5.20 4.99 3.42 2.59 2.44 10.50 7.35 6.66 8.32
Subject 2 11.42 8.01 6.57 15.44 10.26 8.11 4.72 2.57 1.79 28.40 18.93 17.10 17.45
Subject 3 7.62 5.29 5.29 7.22 8.89 5.99 7.87 11.69 5.89 10.95 14.75 9.62 10.75
Average 8.80 6.09 5.19 8.99 8.12 6.36 5.34 5.62 3.37 16.62 13.68 11.13 12.17
Table 1 Averaged RMSEs of relative position estimations (Unit: mm)