Smartwatch-Based Sitting Time Estimation in Real-World Office Settings
2026-04-09 • Machine Learning
Machine LearningHuman-Computer Interaction
AI summaryⓘ
The authors studied how to measure sitting time accurately using smartwatches worn by office workers during their usual day. They used special signals from the watch's sensors called rotation vector sequences, which show how a person moves or stays still. Their new method improved the accuracy of estimating how long someone sits, tested on over 30 hours of real-world data. This work helps better track sitting habits to support health monitoring in everyday settings.
sedentary behaviorsitting time estimationinertial measurement unit (IMU)smartwatch sensorsrotation vector sequenceEuler anglesmovement dynamicswearable technologyreal-world dataalgorithm performance
Authors
Olivia Zhang, Zhilin Zhang
Abstract
Sedentary behavior poses a major public health risk, being strongly linked to obesity, cardiovascular disease, and other chronic conditions. Accurately estimating sitting time is therefore critical for monitoring and improving individual health. This work addresses the problem in real-world office settings, where signals from the inertial measurement units (IMU) on a smartwatch were collected from office workers during their daily routines. We propose a method that estimates sitting time from the IMU signals by introducing the use of rotation vector sequences, derived from Euler angles, as a novel representation of movement dynamics. Experiments on a 34-hour dataset demonstrate that exploiting rotation vector sequences improves algorithm performance, highlighting their potential for robust sitting time estimation in natural environments.