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

• Activity Number: 319 - Innovative Statistical and Machine Learning Methods for Wearable Device Data
• Type: Topic Contributed
• Date/Time: Tuesday, August 9, 2022 : 2:00 PM to 3:50 PM
• Sponsor: Section on Medical Devices and Diagnostics
• Author(s): Loki Natarajan* and Jingjing Zou and Yiren Wang
• Companies: University of California at San Diego (UCSD) and University of California at San Diego (UCSD) and University of California San Diego
• Keywords: Time series changepoint detection; hypothesis testing; Markov switching model; sedentary behavior estimation; two stage classification

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 through- out 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, step- ping). Through a rigorous training-testing paradigm, we showed that our approach achieves over 80% accuracy. In addition, our method is robust and easy to interpret.