Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Adaptive System for Wearable Devices to Detect Stress Using Physiological Signals

Gelei Xu, Ruiyang Qin, Zhi Zheng, Yiyu Shi

TL;DR

The paper tackles the challenge of real-world stress detection from wearable physiological signals, where inter-user variability causes domain shifts that degrade performance. It proposes a three-stage adaptive framework: (1) offline training of a generalized backbone on labeled PPG/EDA data, (2) unsupervised domain-adversarial adaptation to a new user's unlabeled data, and (3) targeted fine-tuning with a small amount of user-labeled feedback via human-in-the-loop interactions. The approach leverages a 1D-CNN backbone and Domain Adversarial Neural Networks to learn domain-invariant features, enabling personalized stress detection without heavy labeling. It also discusses critical aspects such as privacy, on-device training constraints, and potential extensions to broader mental-health monitoring, highlighting practical impact for mobile health interventions.

Abstract

Timely stress detection is crucial for protecting vulnerable groups from long-term detrimental effects by enabling early intervention. Wearable devices, by collecting real-time physiological signals, offer a solution for accurate stress detection accommodating individual differences. This position paper introduces an adaptive framework for personalized stress detection using PPG and EDA signals. Unlike traditional methods that rely on a generalized model, which may suffer performance drops when applied to new users due to domain shifts, this framework aims to provide each user with a personalized model for higher stress detection accuracy. The framework involves three stages: developing a generalized model offline with an initial dataset, adapting the model to the user's unlabeled data, and fine-tuning it with a small set of labeled data obtained through user interaction. This approach not only offers a foundation for mobile applications that provide personalized stress detection and intervention but also has the potential to address a wider range of mental health issues beyond stress detection using physiological signals.

An Adaptive System for Wearable Devices to Detect Stress Using Physiological Signals

TL;DR

The paper tackles the challenge of real-world stress detection from wearable physiological signals, where inter-user variability causes domain shifts that degrade performance. It proposes a three-stage adaptive framework: (1) offline training of a generalized backbone on labeled PPG/EDA data, (2) unsupervised domain-adversarial adaptation to a new user's unlabeled data, and (3) targeted fine-tuning with a small amount of user-labeled feedback via human-in-the-loop interactions. The approach leverages a 1D-CNN backbone and Domain Adversarial Neural Networks to learn domain-invariant features, enabling personalized stress detection without heavy labeling. It also discusses critical aspects such as privacy, on-device training constraints, and potential extensions to broader mental-health monitoring, highlighting practical impact for mobile health interventions.

Abstract

Timely stress detection is crucial for protecting vulnerable groups from long-term detrimental effects by enabling early intervention. Wearable devices, by collecting real-time physiological signals, offer a solution for accurate stress detection accommodating individual differences. This position paper introduces an adaptive framework for personalized stress detection using PPG and EDA signals. Unlike traditional methods that rely on a generalized model, which may suffer performance drops when applied to new users due to domain shifts, this framework aims to provide each user with a personalized model for higher stress detection accuracy. The framework involves three stages: developing a generalized model offline with an initial dataset, adapting the model to the user's unlabeled data, and fine-tuning it with a small set of labeled data obtained through user interaction. This approach not only offers a foundation for mobile applications that provide personalized stress detection and intervention but also has the potential to address a wider range of mental health issues beyond stress detection using physiological signals.
Paper Structure (16 sections, 3 figures)

This paper contains 16 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Related Works
  3. PPG and EDA for Stress Indication
  4. Domain Adaptation and Personalization
  5. Methodology
  6. Generalizable Model Development
  7. Preprocessing
  8. Data Preperation
  9. Backbone Model
  10. Adapted Model Training
  11. Fine-tuning through Human-in-the-loop
  12. Discussion
  13. User Data Privacy Concern
  14. On-device Training Constraint
  15. Beyond Stress Detection
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Overview Framework
  • Figure 2: Framework for Training a Generalizable Model
  • Figure 3: Architecture of the Domain Adversarial Neural Network Model