The Effect of Person-Specific Biometrics in Improving Generic Stress Predictive Models

TL;DR

This paper introduces a cost-effective calibration method that personalizes generic stress prediction models using physiological data, significantly improving accuracy with minimal samples, and provides a blueprint for practical stress monitoring systems.

Contribution

The paper presents a novel calibration technique to personalize generic stress models efficiently, reducing data requirements and enhancing prediction accuracy.

Findings

Calibration with 100 samples raises accuracy from 42.5% to 95.2%.

The approach outperforms generic models significantly.

Source code and datasets are publicly available.

Abstract

Because stress is subjective and is expressed differently from one person to another, generic stress prediction models (i.e., models that predict the stress of any person) perform crudely. Only person-specific ones (i.e., models that predict the stress of a preordained person) yield reliable predictions, but they are not adaptable and costly to deploy in real-world environments. For illustration, in an office environment, a stress monitoring system that uses person-specific models would require collecting new data and training a new model for every employee. Moreover, once deployed, the models would deteriorate and need expensive periodic upgrades because stress is dynamic and depends on unforeseeable factors. We propose a simple, yet practical and cost effective calibration technique that derives an accurate and personalized stress prediction model from physiological samples collected from a large population. We validate our approach on two stress datasets. The results show that our technique performs much better than a generic model. For instance, a generic model achieved only a 42.5% accuracy. However, with only 100 calibration samples, we raised its accuracy to 95.2% We also propose a blueprint for a stress monitoring system based on our strategy, and we debate its merits and limitation. Finally, we made public our source code and the relevant datasets to allow other researchers to replicate our findings.