Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 13, 2026

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students
12:51

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Published on: June 16, 2018

Hybrid Feature Learning for Wearable Stress Detection: Combining Domain Knowledge with Supervised Deep Learning.

Dennis Birkenmaier1, Shanthan Rao Kanuganti1, Wilhelm Stork2

  • 1FZI Research Center for Information Technology, 76131 Karlsruhe, Germany.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Predicting Momentary Mood in Daily Life from Accelerometer Data: Evaluating Single vs. Multiple Sensor Locations Using Machine Learning.

Sensors (Basel, Switzerland)·2026
Same author

Patient Perceptions of Blockchain-Based Health Information Exchange: User-Centered Design Study.

Journal of medical Internet research·2026
Same author

C-Scrum: Agile and Automated Software Development for Digital Health.

Studies in health technology and informatics·2025
Same author

Effective Requirements Engineering in Early-Stage Digital Health Startups.

Studies in health technology and informatics·2025
Same author

A Medical Decision Support System for Automatic Treatment Plan Generation Using Machine Learning Algorithms.

Studies in health technology and informatics·2025
Same author

Applying AI in the Context of the Association Between Device-Based Assessment of Physical Activity and Mental Health: Systematic Review.

JMIR mHealth and uHealth·2025
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

This study introduces a hybrid system for accurate stress detection using electrodermal activity (EDA) in wearable devices. The novel approach significantly improves stress monitoring for high-risk professions, achieving 98.62% accuracy.

Area of Science:

  • Biomedical Engineering
  • Physiological Computing
  • Wearable Technology

Background:

  • Accurate stress monitoring is crucial for high-risk professions, but current wearable solutions struggle with usability and precision.
  • Electrodermal activity (EDA) is a promising non-invasive biosignal for stress detection, yet automated feature extraction remains a challenge.

Purpose of the Study:

  • To develop and validate a hybrid stress detection pipeline combining hand-crafted and deep-learned features from EDA.
  • To enhance the accuracy and practical usability of stress monitoring in wearable devices for first responders.

Main Methods:

  • A hybrid pipeline integrating 20 hand-crafted physiological features with 32 deep-learned features from a supervised convolutional autoencoder was developed.
  • A dual-head architecture with weighted classification loss guided feature learning for stress discrimination.
Keywords:
WESAD datasetartifact detectioncvxEDA decompositiondeep learningelectrodermal activityfeature extractionstress detectionsupervised learningwearable sensors

Related Experiment Videos

Last Updated: Jun 13, 2026

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students
12:51

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Published on: June 16, 2018

  • The system was validated using leave-one-subject-out cross-validation on the WESAD dataset, incorporating advanced preprocessing techniques.

    • Main Results:

    • The optimized K-Nearest Neighbors classifier achieved 98.62% accuracy, outperforming the PyEDA benchmark by 1.62%.
    • The model demonstrated high sensitivity (97.58%) and specificity (98.92%), with minimal false negatives (2.42%).
    • Ablation studies showed a significant improvement from 55% (unsupervised autoencoder alone) to 98.62% (hybrid approach).

    Conclusions:

    • Combining domain-specific physiological knowledge with label-aware deep learning yields more discriminative features than either method alone.
    • The developed system provides a practical, interpretable 1-10 stress score for real-time monitoring.
    • This research lays the foundation for advanced wearable stress monitoring systems for safety-critical applications.