Cross-Modal Correlation Fusion for End-to-End ECG–PPG Stress Classification
Abdelrhman Y. Soliman, Loay Hassan, Domenec Puig, Hatem A. Rashwan
Frontiers in Artificial Intelligence and A· 2026
Summary
Dual parallel encoders extract morphological features from ECG and PPG; a cross-modal correlation fusion layer models electro-mechanical alignment (cardiac electrical triggers ↔ peripheral BVP). Evaluated on WESAD with subject-independent 5-fold CV: mean Accuracy 90.34%, AUC-ROC 97.29%, Stress Recall 94.07%.
Key facts
- Form Factor
- wrist
Reported benchmarks
Mental workload / stress
WESAD · Accuracy ↑
#1 of 2
0.9034
WESAD subject-independent 5-fold CV; mean Accuracy 90.34%; Stress Recall 94.07%
Mental workload / stress
WESAD · AUROC ↑
#1 of 5
0.9729
WESAD subject-independent 5-fold CV; dual ECG+PPG encoders + cross-modal correlation fusion; paper AUC-ROC 97.29%
Updated: Oct 2, 2026