A Bayesian Hidden Semi-Markov Model with Covariate-Dependent State Duration Parameters for High-Frequency Data from Wearable Devices

TL;DR

This paper introduces an advanced Bayesian HSMM that incorporates covariate-dependent duration parameters and a data subsampling method to analyze high-frequency wearable device data, improving activity and physiological response modeling.

Contribution

It extends traditional HSMMs by allowing duration parameters to vary with covariates and proposes a subsampling approach for high-frequency data analysis.

Findings

Identified time-varying effects of game demands on referee physiology.

Improved modeling of state durations with covariate dependence.

Validated approach on real sports wearable data.

Abstract

Data collected by wearable devices in sports provide valuable information about an athlete's behavior such as their activity, performance, and ability. These time series data can be studied with approaches such as hidden Markov and semi-Markov models (HMM and HSMM) for varied purposes including activity recognition and event detection. HSMMs extend the HMM by explicitly modeling the time spent in each state. In a discrete-time HSMM, the duration in each state can be modeled with a zero-truncated Poisson distribution, where the duration parameter may be state-specific but constant in time. We extend the HSMM by allowing the state-specific duration parameters to vary in time and model them as a function of known covariates derived from the wearable device and observed over a period of time leading up to a state transition. In addition, we propose a data subsampling approach given that high-frequency data from wearable devices can violate the conditional independence assumption of the HSMM. We apply the model to wearable device data collected on a soccer referee in a Major League Soccer game. We model the referee's physiological response to the game demands and identify important time-varying effects of these demands associated with the duration in each state.