Self-supervision of wearable sensors time-series data for influenza detection

TL;DR

This paper explores how self-supervised learning on wearable sensor data can improve influenza detection, finding that predicting next-day resting heart rate or sleep metrics yields the best representations for health prediction tasks.

Contribution

It introduces an empirical analysis of different self-supervised objectives on wearable sensor data for influenza detection, identifying the most effective pretext tasks.

Findings

Predicting next-day resting heart rate improves influenza detection accuracy.

Predicting time-in-bed during sleep also enhances model performance.

Self-supervised representations are adaptable for health-related prediction tasks.

Abstract

Self-supervision may boost model performance in downstream tasks. However, there is no principled way of selecting the self-supervised objectives that yield the most adaptable models. Here, we study this problem on daily time-series data generated from wearable sensors used to detect onset of influenza-like illness (ILI). We first show that using self-supervised learning to predict next-day time-series values allows us to learn rich representations which can be adapted to perform accurate ILI prediction. Second, we perform an empirical analysis of three different self-supervised objectives to assess their adaptability to ILI prediction. Our results show that predicting the next day's resting heart rate or time-in-bed during sleep provides better representations for ILI prediction. These findings add to previous work demonstrating the practical application of self-supervised learning from activity data to improve health predictions.