FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition

This supplementary material is divided into two main sections: Benchmarking Results and Cross-Data Results. The Benchmarking Results section reports average model performance using a Leave-OneSubject-Out (LOSO) validation strategy, calculated across all participants within each dataset. Results are reported as mean standard deviation, capturing both central tendency and variability, across all modeling paradigms for arousal, valence, and four-class classification using the EDA, PPG, and combined EDA+PPG modalities, see section 2. The Cross-Data Results section evaluates model generalizability across datasets. It begins with individual transfer experiments, where models trained on all datasets within a group (device, label, or setting) are tested on the remaining two datasets group. This is followed by a Leave-One-Dataset-Out (LODO) in-cohort analysis, in which models are trained on all but one dataset within a group and evaluated on the held-out dataset, and a zero-short analysis.