A Multivariate Polynomial Regression to Reconstruct Ground Contact and Flight Times Based on a Sine Wave Model for Vertical Ground Reaction Force and Measured Effective Timings.

Details

Ressource 1Download: 2021_Patoz-Malatesta_e.pdf (1649.62 [Ko])
State: Public
Version: Final published version
License: CC BY 4.0
Serval ID
serval:BIB_401DFBEE6697
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
A Multivariate Polynomial Regression to Reconstruct Ground Contact and Flight Times Based on a Sine Wave Model for Vertical Ground Reaction Force and Measured Effective Timings.
Journal
Frontiers in bioengineering and biotechnology
Author(s)
Patoz A., Lussiana T., Breine B., Gindre C., Malatesta D.
ISSN
2296-4185 (Print)
ISSN-L
2296-4185
Publication state
Published
Issued date
2021
Peer-reviewed
Oui
Volume
9
Pages
687951
Language
english
Notes
Publication types: Journal Article
Publication Status: epublish
Abstract
Effective contact ( ) and flight ( ) times, instead of ground contact ( ) and flight ( ) times, are usually collected outside the laboratory using inertial sensors. Unfortunately, and cannot be related to and because the exact shape of vertical ground reaction force is unknown. However, using a sine wave approximation for vertical force, and as well as and could be related. Indeed, under this approximation, a transcendental equation was obtained and solved numerically over a grid. Then, a multivariate polynomial regression was applied to the numerical outcome. In order to reach a root-mean-square error of 0.5 ms, the final model was given by an eighth-order polynomial. As a direct application, this model was applied to experimentally measured values. Then, reconstructed (using the model) was compared to corresponding experimental ground truth. A systematic bias of 35 ms was depicted, demonstrating that ground truth values were larger than reconstructed ones. Nonetheless, error in the reconstruction of from was coming from the sine wave approximation, while the polynomial regression did not introduce further error. The presented model could be added to algorithms within sports watches to provide robust estimations of and in real time, which would allow coaches and practitioners to better evaluate running performance and to prevent running-related injuries.
Keywords
biomechanics, inertial measurement unit, machine learning, running, sensors
Pubmed
Web of science
Open Access
Yes
Create date
04/11/2021 9:18
Last modification date
05/12/2021 7:38
Usage data