The physiological recordings used in this study are drawn from the dataset introduced by Liapis et al. (2021), collected using the NEXUS‑10 MKII medical device during controlled baseline and stress‑inducing tasks. The dataset includes annotations based on the established Valence–Arousal model, derived from participant self‑reports, and has been used in affective computing and classification studies. However, these labels do not directly correspond to discrete stress levels, and the dataset was not originally designed for three‑class stress prediction.
To address this gap, we introduce a clinically aligned quantile‑based labeling scheme that transforms continuous autonomic responses into three stress levels. To obtain subject‑adaptive stress levels, we derive a quantile‑based score reflecting the characteristic sympathetic activation pattern—higher Electrodermal Activity and Heart Rate combined with lower Blood Volume Pulse amplitude and peripheral temperature. The proposed pipeline segments the signals into short windows (15 s, 5 s step), extracts eight physiologically meaningful features, and trains a lightweight Temporal Convolutional Network (TCN) under a strict Leave‑One‑Subject‑Out protocol. Despite its compact architecture, the TCN demonstrates strong cross‑subject generalization.
In the three‑class setting, our model achieves macro‑F1 scores above 0.80 and accuracy above 80%, showing that graded autonomic activation can be reliably captured from high‑fidelity biosignals. When reduced to a post‑hoc binary stress decision, performance increases further, reaching a macro‑F1 of approximately 0.90 and accuracy around 90%, confirming that the model effectively captures the underlying stress continuum. We also show that z‑score normalization outperforms median‑based MAD scaling, while temporal smoothing and post‑hoc calibration do not provide measurable improvements due to the low noise and high signal fidelity.
Overall, our results demonstrate that stress is better modeled as a graded autonomic response, that quantile‑based labeling provides a clinically grounded and subject‑adaptive strategy for generating stress levels, and that lightweight TCNs effectively capture stress‑related temporal dynamics in high‑quality biosignal environments.