Transformer-Based Decomposition of Electrodermal Activity for Real-World Mental Health Applications
Sensors · 2025
DOI: 10.3390/s25144406 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Sensors, 2025. Verfasst von Charalampos Tsirmpas und 4 weiteren Autor:innen. Beteiligte Einrichtung: Feel Therapeutics Inc., San Francisco, CA 94108, USA. Hauptthemen laut MEDLINE: Deep Learning, Galvanic Skin Response, Signal Processing, Computer-Assisted, Wearable Electronic Devices. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Decomposing Electrodermal Activity (EDA) into phasic (short-term, stimulus-linked responses) and tonic (longer-term baseline) components is essential for extracting meaningful emotional and physiological biomarkers. This study presents a comparative analysis of knowledge-driven, statistical, and deep learning-based methods for EDA signal decomposition, with a focus on in-the-wild data collected from wearable devices. In particular, the authors introduce the Feel Transformer, a novel Transformer-based model adapted from the Autoformer architecture, designed to separate phasic and tonic components without explicit supervision. The model leverages pooling and trend-removal mechanisms to enforce physiologically meaningful decompositions. Comparative experiments against methods such as Ledalab, cvxEDA, and conventional detrending show that the Feel Transformer achieves a balance between feature fidelity (SCR frequency, amplitude, and tonic slope) and robustness to noisy, real-world data. The model demonstrates potential for real-time biosignal analysis and future applications in stress prediction, digital mental health interventions, and physiological forecasting.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Feel Therapeutics Inc., San Francisco, CA 94108, USA.
- Siglyx, 151 22 Athens, Greece.
- Institute for Machine Learning, Johannes Kepler University, 4040 Linz, Austria.
ORCID-Profile: Charalampos Tsirmpas, Stasinos Konstantopoulos, Dimitris Andrikopoulos, Konstantina Kyriakouli, Panagiotis Fatouros
Zitieren
APA
Tsirmpas, C., Konstantopoulos, S., Andrikopoulos, D., Kyriakouli, K., & Fatouros, P. (2025). Transformer-Based Decomposition of Electrodermal Activity for Real-World Mental Health Applications. Sensors. https://doi.org/10.3390/s25144406
Vancouver
Tsirmpas C, Konstantopoulos S, Andrikopoulos D, Kyriakouli K, Fatouros P. Transformer-Based Decomposition of Electrodermal Activity for Real-World Mental Health Applications. Sensors. 2025. doi:10.3390/s25144406
BibTeX
@article{Tsirmpas2025,
author = {Tsirmpas, Charalampos and Konstantopoulos, Stasinos and Andrikopoulos, Dimitris and Kyriakouli, Konstantina and Fatouros, Panagiotis},
title = {Transformer-Based Decomposition of Electrodermal Activity for Real-World Mental Health Applications},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25144406}
}
EUVIMED