Estimation of vertical ground reaction forces and sagittal knee kinematics during running using three inertial sensors

Frank J. Wouda (Corresponding Author), Matteo Giuberti, Giovanni Bellusci, Erik Maartens, Jasper Reenalda, Bernhard J.F. van Beijnum, Peter H. Veltink

Research output: Contribution to journalArticleAcademicpeer-review

12 Citations (Scopus)
37 Downloads (Pure)

Abstract

Analysis of running mechanics has traditionally been limited to a gait laboratory using either force plates or an instrumented treadmill in combination with a full-body optical motion capture system. With the introduction of inertial motion capture systems, it becomes possible to measure kinematics in any environment. However, kinetic information could not be provided with such technology. Furthermore, numerous body-worn sensors are required for a full-body motion analysis. The aim of this study is to examine the validity of a method to estimate sagittal knee joint angles and vertical ground reaction forces during running using an ambulatory minimal body-worn sensor setup. Two concatenated artificial neural networks were trained (using data from eight healthy subjects) to estimate the kinematics and kinetics of the runners. The first artificial neural network maps the information (orientation and acceleration) of three inertial sensors (placed at the lower legs and pelvis) to lower-body joint angles. The estimated joint angles in combination with measured vertical accelerations are input to a second artificial neural network that estimates vertical ground reaction forces. To validate our approach, estimated joint angles were compared to both inertial and optical references, while kinetic output was compared to measured vertical ground reaction forces from an instrumented treadmill. Performance was evaluated using two scenarios: training and evaluating on a single subject and training on multiple subjects and evaluating on a different subject. The estimated kinematics and kinetics of most subjects show excellent agreement (ρ > 0.99) with the reference, for single subject training. Knee flexion/extension angles are estimated with a mean RMSE < 5°. Ground reaction forces are estimated with a mean RMSE < 0.27 BW. Additionaly, peak vertical ground reaction force, loading rate and maximal knee flexion during stance were compared, however, no significant differences were found. With multiple subject training the accuracy of estimating discrete and continuous outcomes decreases, however, good agreement (ρ > 0.9) is still achieved for seven of the eight different evaluated subjects. The performance of multiple subject learning depends on the diversity in the training dataset, as differences in accuracy were found for the different evaluated subjects.

Original languageEnglish
Article number218
JournalFrontiers in Physiology
Volume9
Issue numberMAR
DOIs
Publication statusPublished - 22 Mar 2018

Fingerprint

Biomechanical Phenomena
Knee
Joints
Information Services
Knee Joint
Mechanics
Pelvis
Gait
Leg
Healthy Volunteers
Learning
Technology

Keywords

  • Artificial neural networks
  • Inertial motion capture
  • Kinetics
  • Machine learning
  • Reduced sensor set
  • Running

Cite this

@article{ddaef28281474815a1e6e48d479e19a2,
title = "Estimation of vertical ground reaction forces and sagittal knee kinematics during running using three inertial sensors",
abstract = "Analysis of running mechanics has traditionally been limited to a gait laboratory using either force plates or an instrumented treadmill in combination with a full-body optical motion capture system. With the introduction of inertial motion capture systems, it becomes possible to measure kinematics in any environment. However, kinetic information could not be provided with such technology. Furthermore, numerous body-worn sensors are required for a full-body motion analysis. The aim of this study is to examine the validity of a method to estimate sagittal knee joint angles and vertical ground reaction forces during running using an ambulatory minimal body-worn sensor setup. Two concatenated artificial neural networks were trained (using data from eight healthy subjects) to estimate the kinematics and kinetics of the runners. The first artificial neural network maps the information (orientation and acceleration) of three inertial sensors (placed at the lower legs and pelvis) to lower-body joint angles. The estimated joint angles in combination with measured vertical accelerations are input to a second artificial neural network that estimates vertical ground reaction forces. To validate our approach, estimated joint angles were compared to both inertial and optical references, while kinetic output was compared to measured vertical ground reaction forces from an instrumented treadmill. Performance was evaluated using two scenarios: training and evaluating on a single subject and training on multiple subjects and evaluating on a different subject. The estimated kinematics and kinetics of most subjects show excellent agreement (ρ > 0.99) with the reference, for single subject training. Knee flexion/extension angles are estimated with a mean RMSE < 5°. Ground reaction forces are estimated with a mean RMSE < 0.27 BW. Additionaly, peak vertical ground reaction force, loading rate and maximal knee flexion during stance were compared, however, no significant differences were found. With multiple subject training the accuracy of estimating discrete and continuous outcomes decreases, however, good agreement (ρ > 0.9) is still achieved for seven of the eight different evaluated subjects. The performance of multiple subject learning depends on the diversity in the training dataset, as differences in accuracy were found for the different evaluated subjects.",
keywords = "Artificial neural networks, Inertial motion capture, Kinetics, Machine learning, Reduced sensor set, Running",
author = "Wouda, {Frank J.} and Matteo Giuberti and Giovanni Bellusci and Erik Maartens and Jasper Reenalda and {van Beijnum}, {Bernhard J.F.} and Veltink, {Peter H.}",
year = "2018",
month = "3",
day = "22",
doi = "10.3389/fphys.2018.00218",
language = "English",
volume = "9",
journal = "Frontiers in Physiology",
issn = "1664-042X",
publisher = "Frontiers Media S.A.",
number = "MAR",

}

Estimation of vertical ground reaction forces and sagittal knee kinematics during running using three inertial sensors. / Wouda, Frank J. (Corresponding Author); Giuberti, Matteo; Bellusci, Giovanni; Maartens, Erik; Reenalda, Jasper; van Beijnum, Bernhard J.F.; Veltink, Peter H.

In: Frontiers in Physiology, Vol. 9, No. MAR, 218, 22.03.2018.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Estimation of vertical ground reaction forces and sagittal knee kinematics during running using three inertial sensors

AU - Wouda, Frank J.

AU - Giuberti, Matteo

AU - Bellusci, Giovanni

AU - Maartens, Erik

AU - Reenalda, Jasper

AU - van Beijnum, Bernhard J.F.

AU - Veltink, Peter H.

PY - 2018/3/22

Y1 - 2018/3/22

N2 - Analysis of running mechanics has traditionally been limited to a gait laboratory using either force plates or an instrumented treadmill in combination with a full-body optical motion capture system. With the introduction of inertial motion capture systems, it becomes possible to measure kinematics in any environment. However, kinetic information could not be provided with such technology. Furthermore, numerous body-worn sensors are required for a full-body motion analysis. The aim of this study is to examine the validity of a method to estimate sagittal knee joint angles and vertical ground reaction forces during running using an ambulatory minimal body-worn sensor setup. Two concatenated artificial neural networks were trained (using data from eight healthy subjects) to estimate the kinematics and kinetics of the runners. The first artificial neural network maps the information (orientation and acceleration) of three inertial sensors (placed at the lower legs and pelvis) to lower-body joint angles. The estimated joint angles in combination with measured vertical accelerations are input to a second artificial neural network that estimates vertical ground reaction forces. To validate our approach, estimated joint angles were compared to both inertial and optical references, while kinetic output was compared to measured vertical ground reaction forces from an instrumented treadmill. Performance was evaluated using two scenarios: training and evaluating on a single subject and training on multiple subjects and evaluating on a different subject. The estimated kinematics and kinetics of most subjects show excellent agreement (ρ > 0.99) with the reference, for single subject training. Knee flexion/extension angles are estimated with a mean RMSE < 5°. Ground reaction forces are estimated with a mean RMSE < 0.27 BW. Additionaly, peak vertical ground reaction force, loading rate and maximal knee flexion during stance were compared, however, no significant differences were found. With multiple subject training the accuracy of estimating discrete and continuous outcomes decreases, however, good agreement (ρ > 0.9) is still achieved for seven of the eight different evaluated subjects. The performance of multiple subject learning depends on the diversity in the training dataset, as differences in accuracy were found for the different evaluated subjects.

AB - Analysis of running mechanics has traditionally been limited to a gait laboratory using either force plates or an instrumented treadmill in combination with a full-body optical motion capture system. With the introduction of inertial motion capture systems, it becomes possible to measure kinematics in any environment. However, kinetic information could not be provided with such technology. Furthermore, numerous body-worn sensors are required for a full-body motion analysis. The aim of this study is to examine the validity of a method to estimate sagittal knee joint angles and vertical ground reaction forces during running using an ambulatory minimal body-worn sensor setup. Two concatenated artificial neural networks were trained (using data from eight healthy subjects) to estimate the kinematics and kinetics of the runners. The first artificial neural network maps the information (orientation and acceleration) of three inertial sensors (placed at the lower legs and pelvis) to lower-body joint angles. The estimated joint angles in combination with measured vertical accelerations are input to a second artificial neural network that estimates vertical ground reaction forces. To validate our approach, estimated joint angles were compared to both inertial and optical references, while kinetic output was compared to measured vertical ground reaction forces from an instrumented treadmill. Performance was evaluated using two scenarios: training and evaluating on a single subject and training on multiple subjects and evaluating on a different subject. The estimated kinematics and kinetics of most subjects show excellent agreement (ρ > 0.99) with the reference, for single subject training. Knee flexion/extension angles are estimated with a mean RMSE < 5°. Ground reaction forces are estimated with a mean RMSE < 0.27 BW. Additionaly, peak vertical ground reaction force, loading rate and maximal knee flexion during stance were compared, however, no significant differences were found. With multiple subject training the accuracy of estimating discrete and continuous outcomes decreases, however, good agreement (ρ > 0.9) is still achieved for seven of the eight different evaluated subjects. The performance of multiple subject learning depends on the diversity in the training dataset, as differences in accuracy were found for the different evaluated subjects.

KW - Artificial neural networks

KW - Inertial motion capture

KW - Kinetics

KW - Machine learning

KW - Reduced sensor set

KW - Running

UR - http://www.scopus.com/inward/record.url?scp=85044350200&partnerID=8YFLogxK

U2 - 10.3389/fphys.2018.00218

DO - 10.3389/fphys.2018.00218

M3 - Article

VL - 9

JO - Frontiers in Physiology

JF - Frontiers in Physiology

SN - 1664-042X

IS - MAR

M1 - 218

ER -