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.
Autor(es):LEONARDO GABRIEL BRAVO THAIS (Autor); DANIEL ALCIDES SAROMO MORI (Autor); ELIZABETH ROXANA VILLOTA CERNA (Autor).
Año: 2022
Título de la revista: Engineering Proceedings
Ciudad: -, Suiza
Volumen: 21
Número: 1
ISSN: 2673-4591
Url: https://www.mdpi.com/2673-4591/21/1/47