Abstract
Wearable devices are being increasingly used to objectively monitor and evaluate physical variables related to human movements, such as sports. Although wearables for kinematic measurements are widely used nowadays, many dynamic studies still employ force platforms to have reliable and valid data for estimating vertical ground reaction forces (vGRFs). Not only are force platforms quite expensive, but they also cannot be easily accommodated in a practical scenario and significantly restrict the user’s freedom of movement to a small fixed area. This article presents a smart insole sensor capable of providing a reliable and valid measurement of vGRFs. Regarding the hardware, the wearable is comprised of piezoresistive force sensors distributed along with the insole, which provides plantar force distribution measurements, and an embedded system for data collection and communication worn on the lower leg. In order to make the system more affordable, we made the prototype enclosure using 3D-printing technology. Finally, to monitor the wearable outputs, the insole sensor uses a mobile application connected to the wearable via Bluetooth 4.0. The prototype underwent both unit and value calibration at the lab using gold standard force plates to guarantee accurate outputs. Regarding the software, we implemented a novel deep learning algorithm for vGRF estimation and insole sensor calibration. This research provides an advancement toward developing a wearable monitoring system for vGRF reporting in real-life scenarios.
Author Contributions
Conceptualization, L.B.-T., D.S.M. and E.R.V.; methodology, L.B.-T. and D.S.M.; software, D.S.M.; validation, L.B.-T., D.S.M. and E.R.V.; formal analysis, L.B.-T., D.S.M. and E.R.V.; investigation, L.B.-T.; resources, L.B.-T. and E.R.V.; data curation, L.B.-T.; writing—original draft preparation, L.B.-T.; writing—review and editing, L.B.-T., D.S.M. and E.R.V.; supervision, E.R.V.; project administration, E.R.V.; funding acquisition, E.R.V. All authors have read and agreed to the published version of the manuscript.
Funding
This research was funded by Funding Agency ProCiencia (Project Concytec—World Bank) under contract number 58-2018-FONDECYT-BM-IADT-AV.
Institutional Review Board Statement
Not applicable.
Informed Consent Statement
Not applicable.
Data Availability Statement
The preprocessed datasets are available online at https://drive.google.com/drive/folders/1e0G64qBbbD1yBokAM_PWX9ERIEk9Qrlv?usp=sharing (accessed on 24 August 2022). These datasets are ready to be used by the machine learning inference models.
Conflicts of Interest
The authors declare no conflict of interest.
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).