Sedentary Behavior Estimation with Hip-worn Accelerometer Data: Segmentation, Classification and Thresholding
Abstract
Cohort studies are increasingly using accelerometers for physical activity and sedentary behavior estimation. These devices tend to be less error-prone than self-report, can capture activity throughout the day, and are economical. However, previous methods for estimating sedentary behavior based on hip-worn data are often invalid or suboptimal under free-living situations and subject-to-subject variation. In this paper, we propose a local Markov switching model that takes this situation into account, and introduce a general procedure for posture classification and sedentary behavior analysis that fits the model naturally. Our method features changepoint detection methods in time series and also a two stage classification step that labels data into 3 classes(sitting, standing, stepping). Through a rigorous training-testing paradigm, we showed that our approach achieves > 80% accuracy. In addition, our method is robust and easy to interpret.
Cite
@article{arxiv.2207.01809,
title = {Sedentary Behavior Estimation with Hip-worn Accelerometer Data: Segmentation, Classification and Thresholding},
author = {Yiren Wang and Fatima Tuz-Zahra and Rong Zablocki and Chongzhi Di and Marta M. Jankowska and John Bellettiere and Jordan A. Carlson and Andrea Z. LaCroix and Sheri J. Hartman and Dori E. Rosenberg and Jingjing Zou and Loki Natarajan},
journal= {arXiv preprint arXiv:2207.01809},
year = {2022}
}