Get Up!: Assessing Postural Activity and Transitions using Bi-Directional Gated Recurrent Units (Bi-GRUs) on Smartphone Motion Data

Details

12:15 - 14:15 | Wed 20 Nov | Upper Foyer Balcony | A1P-B.7

Session: Poster Session - Health and Wellness Across the Lifespan 1

Abstract

A variety of health conditions can affect a person’s mobility. Consequently, the ability of a person to perform transitions between activity states (e.g. sit-to-stand) are accurate measures of their mobility and general health. The Timed up and Go is an important clinical test that assesses patients’ sit-to-stand abilities. To run Timed up and Go autonomously, we need a method to detect postural transitions. We introduce Get Up!, a novel method to detect whether a person is performing a certain postural activity or transitioning between activities. Get Up! analyzes data from the accelerometer and gyroscope of the patient’s smartphone using a deep learning approach and is able to outperform TAHAR, the current state of the art method.