Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 26, 2026Computer Methods in Biomechanics & Biomedical Engineering

Wearable ECG ensemble learning outperforms single baseline models for automated stress detection.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Driven by the rising prevalence of mental health issues, there is a need for automated stress monitoring using wearable ECG signals that overcomes individual physiological variability.

Does an automated stress monitoring system using wearable ECG signals and ensemble learning improve stress detection accuracy compared to baseline single models?

Population

Subjects from the standard WESAD dataset

Comparison

Proposed stacking ensemble framework vs baseline single models

Key result

An automated stress monitoring system using wearable ECG signals and stacking ensemble learning achieved high accuracy on the WESAD dataset, outperforming baseline single models.

Authors

THTrong-Thanh HanDTDat Tran TienTPThanh Loan Pham-Nguyen

Discussion

Loading...

Member takes

Overview

May enable wearable ECG stress monitoring; leaves open prospective clinical validation before any practice change.

Key Points

  • The aim is to develop an automated system for detecting stress using wearable ECG signals while addressing individual physiological differences.
  • Implemented a framework integrating subject-specific normalization and multi-domain feature extraction strategies.
  • Utilized a Stacking Ensemble model combining XGBoost, Random Forest, and SVM for classification.
  • Evaluated performance on the WESAD dataset.
  • Achieved high accuracy in stress detection, significantly outperforming baseline single models.
  • Demonstrated robust capability for real-time monitoring of stress using personal wearable devices.

Structured PICO

Does an automated stress monitoring system using wearable ECG signals and ensemble learning improve stress detection accuracy compared to baseline single models?

P
Population
Subjects from the standard WESAD dataset
I
Intervention
Automated stress monitoring system using wearable ECG signals, combining subject-specific normalization with multi-domain feature extraction (HRV, P-Q-R-S-T morphology, EDR) and a Stacking Ensemble architecture (XGBoost, Random Forest, SVM)
C
Comparator
Baseline single models
O
Outcome
Accuracy of stress detection

A novel wearable ECG-based stress detection framework using ensemble learning demonstrates high accuracy, suggesting potential for real-time personal stress monitoring.

Cite This Study

Han et al. (2026) studied Stress. Automated stress monitoring system using wearable ECG signals and stacking ensemble learning vs. Baseline single models was evaluated on Accuracy of stress detection. An automated stress monitoring system using wearable ECG signals and stacking ensemble learning achieved high accuracy on the WESAD dataset, outperforming baseline single models.

synapsesocial.com/papers/6a65aafdd3aea3239cd794d1https://doi.org/10.1080/10255842.2026.2704681
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Stress Detection Using Heart Rate Variability and Respiratory Signals Derived From a Single-Lead ECG2026 · 1 citations
  2. 2Wearable Flexible Electronics Based Cardiac Electrode for Researcher Mental Stress Detection System Using Machine Learning Models on Single Lead Electrocardiogram Signal2022 · 116 citations
  3. 3An attention-based multimodal deep learning framework integrating EEG and ECG for enhanced stress detection2026
  4. 4Personalized Electrocardiographic and HRV Dynamics for Acute Stress Detection: A Leave-One-Subject-Out Benchmark on WESAD2026
  5. 5Human Stress Classification Using Cardiovascular and Respiratory Data Based on Machine Learning Techniques2025 · 1 citations