Learning Behavioral Representations from Wearable Sensors

TL;DR

This paper presents a non-parametric Bayesian method to extract interpretable behavioral states from wearable sensor data, enabling better clustering of individuals and prediction of psychological states.

Contribution

It introduces a novel approach for modeling and interpreting behavioral patterns from multivariate physiological data using non-parametric Bayesian techniques.

Findings

Learned states effectively cluster participants into meaningful groups

Improved prediction of cognitive and psychological states

Provides interpretable behavioral representations from sensor data

Abstract

Continuous collection of physiological data from wearable sensors enables temporal characterization of individual behaviors. Understanding the relation between an individual's behavioral patterns and psychological states can help identify strategies to improve quality of life. One challenge in analyzing physiological data is extracting the underlying behavioral states from the temporal sensor signals and interpreting them. Here, we use a non-parametric Bayesian approach to model sensor data from multiple people and discover the dynamic behaviors they share. We apply this method to data collected from sensors worn by a population of hospital workers and show that the learned states can cluster participants into meaningful groups and better predict their cognitive and psychological states. This method offers a way to learn interpretable compact behavioral representations from multivariate sensor signals.