Deep CHORES: Estimating Hallmark Measures of Physical Activity Using Deep Learning

TL;DR

This paper presents a deep learning approach to accurately recognize physical activity types and estimate energy expenditure from wrist accelerometer data, demonstrating high performance across diverse activities and age groups.

Contribution

It introduces a novel deep learning framework for analyzing wrist accelerometer data to classify activity types and estimate energy expenditure across the lifespan.

Findings

F1 scores of 0.82, 0.81, and 0.95 for activity recognition

EE estimation with RMSE of 1.1 kcal/min

Effective across a wide age range

Abstract

Wrist accelerometers for assessing hallmark measures of physical activity (PA) are rapidly growing with the advent of smartwatch technology. Given the growing popularity of wrist-worn accelerometers, there needs to be a rigorous evaluation for recognizing (PA) type and estimating energy expenditure (EE) across the lifespan. Participants (66% women, aged 20-89 yrs) performed a battery of 33 daily activities in a standardized laboratory setting while a tri-axial accelerometer collected data from the right wrist. A portable metabolic unit was worn to measure metabolic intensity. We built deep learning networks to extract spatial and temporal representations from the time-series data, and used them to recognize PA type and estimate EE. The deep learning models resulted in high performance; the F1 score was: 0.82, 0.81, and 95 for recognizing sedentary, locomotor, and lifestyle activities, respectively. The root mean square error was 1.1 (+/-0.13) for the estimation of EE.