Walking speed in real-life conditions is typically estimated through wearable inertial sensors mounted on waist, lower limbs, or wrists. Very recently, head-mounted inertial sensors are emerging for gait assessment. The present study explores the feasibility of measuring the stride speed with a head-mounted inertial sensor in both laboratory and real-world settings. The developed algorithm exploits a Temporal Convolutional Network for the detection of the gait events and a Gaussian Process Regression for the stride speed estimation. The experimental evaluation was carried out on healthy young participants during both standardised indoor and real-world walking trials. For indoor trials, errors were smaller than previous studies (0.05 m/s). As expected, errors increased at lower speed regimes due to a reduced signals amplitude. During 2.5-hours real-world evaluation, errors were slightly larger but acceptable (0.1 m/s). Reported results are encouraging and show the feasibility of estimating gait speed with a single head-worn inertial sensor.

A machine learning approach for stride speed estimation based on a head-mounted IMU / Tasca, Paolo; Salis, Francesca; Rosati, Samanta; Balestra, Gabriella; Cereatti, Andrea. - ELETTRONICO. - (2023). (Intervento presentato al convegno Eighth National Congress of Bioengineering, GNB tenutosi a Padova; Italy nel 21 - 23 Giugno 2023).

A machine learning approach for stride speed estimation based on a head-mounted IMU

Tasca, Paolo;Rosati, Samanta;Balestra, Gabriella;Cereatti, Andrea
2023

Abstract

Walking speed in real-life conditions is typically estimated through wearable inertial sensors mounted on waist, lower limbs, or wrists. Very recently, head-mounted inertial sensors are emerging for gait assessment. The present study explores the feasibility of measuring the stride speed with a head-mounted inertial sensor in both laboratory and real-world settings. The developed algorithm exploits a Temporal Convolutional Network for the detection of the gait events and a Gaussian Process Regression for the stride speed estimation. The experimental evaluation was carried out on healthy young participants during both standardised indoor and real-world walking trials. For indoor trials, errors were smaller than previous studies (0.05 m/s). As expected, errors increased at lower speed regimes due to a reduced signals amplitude. During 2.5-hours real-world evaluation, errors were slightly larger but acceptable (0.1 m/s). Reported results are encouraging and show the feasibility of estimating gait speed with a single head-worn inertial sensor.
2023
9788855580113
File in questo prodotto:
File Dimensione Formato  
GNB2023_reviewed_19_04_2023.pdf

accesso aperto

Descrizione: Documento dell'articolo in formato PDF
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 864.46 kB
Formato Adobe PDF
864.46 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2981790