Saved in:
Bibliographic Details
Main Authors: Tsirmpas, Charalampos, Konstantopoulos, Stasinos, Andrikopoulos, Dimitris, Kyriakouli, Konstantina, Fatouros, Panagiotis
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.06378
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915331808690176
author Tsirmpas, Charalampos
Konstantopoulos, Stasinos
Andrikopoulos, Dimitris
Kyriakouli, Konstantina
Fatouros, Panagiotis
author_facet Tsirmpas, Charalampos
Konstantopoulos, Stasinos
Andrikopoulos, Dimitris
Kyriakouli, Konstantina
Fatouros, Panagiotis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06378
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transformer-Based Decomposition of Electrodermal Activity for Real-World Mental Health Applications
Tsirmpas, Charalampos
Konstantopoulos, Stasinos
Andrikopoulos, Dimitris
Kyriakouli, Konstantina
Fatouros, Panagiotis
Signal Processing
Machine Learning
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.
title Transformer-Based Decomposition of Electrodermal Activity for Real-World Mental Health Applications
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2506.06378