Transformer-Based Decomposition of Electrodermal Activity for Real-World Mental Health Applications

2025/06/04 by Charalampos Tsirmpas, Tsirmpas, Charalampos, Stasinos Konstantopoulos +6
Neuroscience · Psychology · #Digital Mental Health Interventions #EEG and Brain-Computer Interfaces #Emotion and Mood Recognition #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.06378

openalex publication_date 2025/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Reformer: The Efficient Transformer
• Recurrent Neural Networks for Time Series Forecasting: Current status and future directions
• Attention Is All You Need
• Conditional Time Series Forecasting with Convolutional Neural Networks
• Autonomic nervous system activity in emotion: A review
• Long Short-Term Memory

Related

• Interpretable Multi-Task PINN for Emotion Recognition and EDA Prediction
• PhysioFormer: Integrating Multimodal Physiological Signals and Symbolic Regression for Explainable Affective State Prediction
• PULSE: Privileged Knowledge Transfer from Electrodermal Activity to Low-Cost Sensors for Stress Monitoring
• Reproducible Physiological Features in Affective Computing: A Preliminary Analysis on Arousal Modeling
• Cross-Modality Investigation on WESAD Stress Classification