StressNAS: Affect State and Stress Detection Using Neural Architecture Search

TL;DR

This paper introduces StressNAS, a neural architecture search method that automatically designs deep neural networks for stress detection using wrist-worn physiological data, outperforming traditional methods.

Contribution

The paper presents a novel neural architecture search approach tailored for stress detection, reducing manual DNN design and improving accuracy on wrist-worn data.

Findings

Outperforms traditional ML methods by 8.22% and 6.02% in multi-class and binary stress classification.

Reduces human effort in DNN design while enhancing performance by up to 8.99%.

Demonstrates effectiveness on WESAD dataset with wrist signals.

Abstract

Smartwatches have rapidly evolved towards capabilities to accurately capture physiological signals. As an appealing application, stress detection attracts many studies due to its potential benefits to human health. It is propitious to investigate the applicability of deep neural networks (DNN) to enhance human decision-making through physiological signals. However, manually engineering DNN proves a tedious task especially in stress detection due to the complex nature of this phenomenon. To this end, we propose an optimized deep neural network training scheme using neural architecture search merely using wrist-worn data from WESAD. Experiments show that our approach outperforms traditional ML methods by 8.22% and 6.02% in the three-state and two-state classifiers, respectively, using the combination of WESAD wrist signals. Moreover, the proposed method can minimize the need for human-design DNN while improving performance by 4.39% (three-state) and 8.99% (binary).