Home // HEALTHINFO 2024, The Ninth International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing // View article


AI-based Estimation of Lower Limb Joint Moments in Stance Phase Using a Single Wearable Inertial Sensor

Authors:
Kyoko Shibata
Kohei Watanabe

Keywords: Self-healthcare; Gait analysis; Wearable sensing; LSTM.

Abstract:
Walking is an easy way to exercise that can maintain and improve health. Quantifying the benefits of walking exercise would make health promotion more effective. The purpose of this study is to estimate lower limb joint moments during daily walking in order to support active healthcare by oneself. Using acceleration data acquired from a large number of wearable sensors, it is not possible to estimate joint moments based on kinetic theory alone. Therefore, this study proposes a method for estimating joint moments using deep learning from measured single-axis acceleration data only, considering the ease of measurement. The accuracy of estimation on the three lower limb joint moments in the stance phase is shown and the possibility of the proposed method is discussed.

Pages: 53 to 56

Copyright: Copyright (c) IARIA, 2024

Publication date: November 3, 2024

Published in: conference

ISSN: 2519-8491

ISBN: 978-1-68558-204-3

Location: Nice, France

Dates: from November 3, 2024 to November 7, 2024