Wearable motion sensors and artificial neural network for the estimation of vertical ground reaction forces in running

Salvatore Tedesco; Eduardo Perez-Valero; Dimitrios Sokratis Komaris; Luke Jordan; John Barton; Liam Hennessy; Brendan O'Flynn

doi:10.1109/SENSORS47125.2020.9278796

Wearable motion sensors and artificial neural network for the estimation of vertical ground reaction forces in running

Salvatore Tedesco^*, Eduardo Perez-Valero, Dimitrios Sokratis Komaris, Luke Jordan, John Barton, Liam Hennessy, Brendan O'Flynn

^*Corresponding author for this work

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Biomechanical load assessments are becoming increasingly important in the sporting community; however, there are still numerous difficulties in monitoring them in a field environment outside of specialized biomechanical monitoring laboratories. Inertial Measurements Units (IMUs) have been showing promising results in the modeling of biomechanical variables. This study explores the application of an artificial neural network (ANN) in the estimation of runners' vertical ground reaction forces (GRFs) based on the accelerometry collected from two wearable motion sensors developed in-house and attached on the shanks. Data collected from fourteen runners running at three different speeds (8, 10, 12 km/h) were used to train and validate the ANN. Predictions were compared against gold-standard measurements from a pair of pressure in-soles. Root mean square error (RMSE) was used to evaluate the performance of the models. Further investigations, e.g., the use of principal components analysis (PCA) and the impact on the estimation of several GRF-related variables, were carried out to provide useful insights regarding the portability of the model to low-power resource-constrained devices. Findings indicate that ANNs in conjunction with accelerometry may be used to compute vertical ground reaction forces (RMSE: 0.148 BW) and related loading metrics in running accurately.

Original language	English
Title of host publication	IEEE Sensors, SENSORS 2020 - Conference Proceedings
Publisher	IEEE
ISBN (Electronic)	9781728168012
DOIs	https://doi.org/10.1109/SENSORS47125.2020.9278796
Publication status	Published - 9 Dec 2020
Event	2020 IEEE Sensors, SENSORS 2020 - Virtual, Rotterdam, Netherlands Duration: 25 Oct 2020 → 28 Oct 2020

Publication series

Name	Proceedings of IEEE Sensors
Volume	2020-October
ISSN (Print)	1930-0395
ISSN (Electronic)	2168-9229

Conference

Conference	2020 IEEE Sensors, SENSORS 2020
Country/Territory	Netherlands
City	Virtual, Rotterdam
Period	25/10/20 → 28/10/20

Bibliographical note

Copyright © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Funding Information: This publication was supported by Enterprise Ireland and Setanta College Ltd under grant agreement no. IP 2017 0606. This project is co-funded by the European Regional Development Fund (ERDF) under Ireland’s European Structural and Investment Funds Programmes 2014-2020. Aspects of this publication have emanated from research conducted with the financial support of Science Foundation Ireland under Grant number 12/RC/2289-P2 INSIGHT-2 which is co-funded under the ERDF.

Keywords

Accelerometers
Ground Reaction Forces
IMU
Running
Wearable

Access to Document

10.1109/SENSORS47125.2020.9278796

S Tedesco et al_AAM_Wearable motion sensors neural network for estimation of ground reaction forces Running
Copyright © 2020, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 1.4 MBLicence: Unspecified

Cite this

Tedesco, S., Perez-Valero, E., Komaris, D. S., Jordan, L., Barton, J., Hennessy, L., & O'Flynn, B. (2020). Wearable motion sensors and artificial neural network for the estimation of vertical ground reaction forces in running. In IEEE Sensors, SENSORS 2020 - Conference Proceedings (Proceedings of IEEE Sensors; Vol. 2020-October). IEEE. https://doi.org/10.1109/SENSORS47125.2020.9278796

@inproceedings{385988d674bd4b3e80e3110a2485dd0d,

title = "Wearable motion sensors and artificial neural network for the estimation of vertical ground reaction forces in running",

abstract = "Biomechanical load assessments are becoming increasingly important in the sporting community; however, there are still numerous difficulties in monitoring them in a field environment outside of specialized biomechanical monitoring laboratories. Inertial Measurements Units (IMUs) have been showing promising results in the modeling of biomechanical variables. This study explores the application of an artificial neural network (ANN) in the estimation of runners' vertical ground reaction forces (GRFs) based on the accelerometry collected from two wearable motion sensors developed in-house and attached on the shanks. Data collected from fourteen runners running at three different speeds (8, 10, 12 km/h) were used to train and validate the ANN. Predictions were compared against gold-standard measurements from a pair of pressure in-soles. Root mean square error (RMSE) was used to evaluate the performance of the models. Further investigations, e.g., the use of principal components analysis (PCA) and the impact on the estimation of several GRF-related variables, were carried out to provide useful insights regarding the portability of the model to low-power resource-constrained devices. Findings indicate that ANNs in conjunction with accelerometry may be used to compute vertical ground reaction forces (RMSE: 0.148 BW) and related loading metrics in running accurately.",

keywords = "Accelerometers, Ground Reaction Forces, IMU, Running, Wearable",

author = "Salvatore Tedesco and Eduardo Perez-Valero and Komaris, {Dimitrios Sokratis} and Luke Jordan and John Barton and Liam Hennessy and Brendan O'Flynn",

note = "Copyright {\textcopyright} 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Funding Information: This publication was supported by Enterprise Ireland and Setanta College Ltd under grant agreement no. IP 2017 0606. This project is co-funded by the European Regional Development Fund (ERDF) under Ireland{\textquoteright}s European Structural and Investment Funds Programmes 2014-2020. Aspects of this publication have emanated from research conducted with the financial support of Science Foundation Ireland under Grant number 12/RC/2289-P2 INSIGHT-2 which is co-funded under the ERDF. ; 2020 IEEE Sensors, SENSORS 2020 ; Conference date: 25-10-2020 Through 28-10-2020",

year = "2020",

month = dec,

day = "9",

doi = "10.1109/SENSORS47125.2020.9278796",

language = "English",

series = "Proceedings of IEEE Sensors",

publisher = "IEEE",

booktitle = "IEEE Sensors, SENSORS 2020 - Conference Proceedings",

address = "United States",

}

Tedesco, S, Perez-Valero, E, Komaris, DS, Jordan, L, Barton, J, Hennessy, L & O'Flynn, B 2020, Wearable motion sensors and artificial neural network for the estimation of vertical ground reaction forces in running. in IEEE Sensors, SENSORS 2020 - Conference Proceedings. Proceedings of IEEE Sensors, vol. 2020-October, IEEE, 2020 IEEE Sensors, SENSORS 2020, Virtual, Rotterdam, Netherlands, 25/10/20. https://doi.org/10.1109/SENSORS47125.2020.9278796

Wearable motion sensors and artificial neural network for the estimation of vertical ground reaction forces in running. / Tedesco, Salvatore; Perez-Valero, Eduardo; Komaris, Dimitrios Sokratis et al.
IEEE Sensors, SENSORS 2020 - Conference Proceedings. IEEE, 2020. (Proceedings of IEEE Sensors; Vol. 2020-October).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Wearable motion sensors and artificial neural network for the estimation of vertical ground reaction forces in running

AU - Tedesco, Salvatore

AU - Perez-Valero, Eduardo

AU - Komaris, Dimitrios Sokratis

AU - Jordan, Luke

AU - Barton, John

AU - Hennessy, Liam

AU - O'Flynn, Brendan

N1 - Copyright © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Funding Information: This publication was supported by Enterprise Ireland and Setanta College Ltd under grant agreement no. IP 2017 0606. This project is co-funded by the European Regional Development Fund (ERDF) under Ireland’s European Structural and Investment Funds Programmes 2014-2020. Aspects of this publication have emanated from research conducted with the financial support of Science Foundation Ireland under Grant number 12/RC/2289-P2 INSIGHT-2 which is co-funded under the ERDF.

PY - 2020/12/9

Y1 - 2020/12/9

N2 - Biomechanical load assessments are becoming increasingly important in the sporting community; however, there are still numerous difficulties in monitoring them in a field environment outside of specialized biomechanical monitoring laboratories. Inertial Measurements Units (IMUs) have been showing promising results in the modeling of biomechanical variables. This study explores the application of an artificial neural network (ANN) in the estimation of runners' vertical ground reaction forces (GRFs) based on the accelerometry collected from two wearable motion sensors developed in-house and attached on the shanks. Data collected from fourteen runners running at three different speeds (8, 10, 12 km/h) were used to train and validate the ANN. Predictions were compared against gold-standard measurements from a pair of pressure in-soles. Root mean square error (RMSE) was used to evaluate the performance of the models. Further investigations, e.g., the use of principal components analysis (PCA) and the impact on the estimation of several GRF-related variables, were carried out to provide useful insights regarding the portability of the model to low-power resource-constrained devices. Findings indicate that ANNs in conjunction with accelerometry may be used to compute vertical ground reaction forces (RMSE: 0.148 BW) and related loading metrics in running accurately.

AB - Biomechanical load assessments are becoming increasingly important in the sporting community; however, there are still numerous difficulties in monitoring them in a field environment outside of specialized biomechanical monitoring laboratories. Inertial Measurements Units (IMUs) have been showing promising results in the modeling of biomechanical variables. This study explores the application of an artificial neural network (ANN) in the estimation of runners' vertical ground reaction forces (GRFs) based on the accelerometry collected from two wearable motion sensors developed in-house and attached on the shanks. Data collected from fourteen runners running at three different speeds (8, 10, 12 km/h) were used to train and validate the ANN. Predictions were compared against gold-standard measurements from a pair of pressure in-soles. Root mean square error (RMSE) was used to evaluate the performance of the models. Further investigations, e.g., the use of principal components analysis (PCA) and the impact on the estimation of several GRF-related variables, were carried out to provide useful insights regarding the portability of the model to low-power resource-constrained devices. Findings indicate that ANNs in conjunction with accelerometry may be used to compute vertical ground reaction forces (RMSE: 0.148 BW) and related loading metrics in running accurately.

KW - Accelerometers

KW - Ground Reaction Forces

KW - IMU

KW - Running

KW - Wearable

UR - https://ieeexplore.ieee.org/document/9278796

UR - http://www.scopus.com/inward/record.url?scp=85098727218&partnerID=8YFLogxK

U2 - 10.1109/SENSORS47125.2020.9278796

DO - 10.1109/SENSORS47125.2020.9278796

M3 - Conference publication

AN - SCOPUS:85098727218

T3 - Proceedings of IEEE Sensors

BT - IEEE Sensors, SENSORS 2020 - Conference Proceedings

PB - IEEE

T2 - 2020 IEEE Sensors, SENSORS 2020

Y2 - 25 October 2020 through 28 October 2020

ER -

Wearable motion sensors and artificial neural network for the estimation of vertical ground reaction forces in running

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this