Stressor Type Matters! -- Exploring Factors Influencing Cross-Dataset Generalizability of Physiological Stress Detection

arXiv:2405.09563v1 Announce Type: cross
Abstract: Automatic stress detection using heart rate variability (HRV) features has gained significant traction as it utilizes unobtrusive wearable sensors measuring signals like electrocardiogram (ECG) or blood volume pulse (BVP). However, detecting stress through such physiological signals presents a considerable challenge owing to the variations in recorded signals influenced by factors, such as perceived stress intensity and measurement devices. Consequently, stress detection models developed on one dataset may perform poorly on unseen data collected under different …

abstract arxiv challenge cs.ai cs.lg dataset detection eess.sp features heart however measuring rate sensors stress through type wearable wearable sensors