Sedentary Behavior Estimation with Hip-worn Accelerometer Data: Segmentation, Classification and Thresholding

• Main Authors: Wang, Yiren, Tuz-Zahra, Fatima, Zablocki, Rong, Di, Chongzhi, Jankowska, Marta M, Bellettiere, John, Carlson, Jordan A, LaCroix, Andrea Z, Hartman, Sheri J, Rosenberg, Dori E, Zou, Jingjing, Natarajan, Loki
• Format: Journal Article
• Language: English
• Published: 05.07.2022
• Subjects: Computer Science - Learning; Statistics - Applications
• DOI: 10.48550/arxiv.2207.01809

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.