Hybrid Feature Learning for Wearable Stress Detection: Combining Domain Knowledge with Supervised Deep Learning
Sensors · 29.05.2026 · 26 (11) · 3451
DOI: 10.3390/s26113451 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.05.2026. Verfasst von Dennis Birkenmaier und 2 weiteren Autor:innen. Beteiligte Einrichtung: FZI Research Center for Information Technology, 76131 Karlsruhe, Germany. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Deep Learning, Supervised Machine Learning, Stress, Physiological. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate stress monitoring is critical for high-risk professions like firefighting, yet existing wearable solutions face challenges balancing accuracy with practical usability. While electrodermal activity (EDA) offers a non-invasive, single-sensor approach, current automated feature extraction methods fail to capture stress-discriminative patterns effectively. We developed a hybrid stress detection pipeline combining 20 hand-crafted physiological features with 32 deep-learned features from a supervised convolutional autoencoder. Unlike traditional unsupervised approaches optimized solely for signal reconstruction, our architecture employs a dual-head design with weighted classification loss to guide feature learning toward stress discrimination. The system was validated on the WESAD dataset (15 subjects) using rigorous leave-one-subject-out (LOSO) cross-validation, along with comprehensive preprocessing, including cvxEDA decomposition, adaptive artifact detection, and physiological peak validation. Our optimized K-Nearest Neighbors classifier achieved 98.62% accuracy, surpassing the industry-standard PyEDA benchmark (97.0%) by 1.62 percentage points. The model demonstrated 97.58% sensitivity (true positive rate) and 98.92% specificity (true negative rate), with only 2.42% false negatives—critical for safety-critical applications. Ablation studies revealed that unsupervised autoencoder features alone achieved only 55% accuracy, increasing to 89% with supervised learning and 98.62% with the hybrid approach, representing a 43.62-percentage-point improvement. This work demonstrates that combining domain-specific physiological knowledge with label-aware deep learning produces more discriminative features than either approach alone. The resulting system successfully translates complex probabilistic outputs into an interpretable 1–10 stress score, providing a practical foundation for real-time stress monitoring in wearable devices for first responders.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- FZI Research Center for Information Technology, 76131 Karlsruhe, Germany.
- Institute for Information Processing Technologies, Karlsruhe Institute of Technology KIT, 76131 Karlsruhe, Germany.
ORCID-Profile: Dennis Birkenmaier
Zitieren
APA
Birkenmaier, D., Kanuganti, S. R., & Stork, W. (2026). Hybrid Feature Learning for Wearable Stress Detection: Combining Domain Knowledge with Supervised Deep Learning. Sensors, 26(11), 3451. https://doi.org/10.3390/s26113451
Vancouver
Birkenmaier D, Kanuganti SR, Stork W. Hybrid Feature Learning for Wearable Stress Detection: Combining Domain Knowledge with Supervised Deep Learning. Sensors. 2026;26(11):3451. doi:10.3390/s26113451
BibTeX
@article{Birkenmaier2026,
author = {Birkenmaier, Dennis and Kanuganti, Shanthan Rao and Stork, Wilhelm},
title = {Hybrid Feature Learning for Wearable Stress Detection: Combining Domain Knowledge with Supervised Deep Learning},
journal = {Sensors},
year = {2026},
volume = {26},
number = {11},
pages = {3451},
doi = {10.3390/s26113451}
}
EUVIMED