Abstract
Automated stress detection is critical for clinical monitoring; however, developing robust models that address the non-stationary nature and inter-subject variability. This paper presents a multimodal deep learning framework that lever-ages the synergy between Electrocardiogram (ECG) and Photoplethysmography (PPG) signals for reliable stress identification. The proposed architecture utilizes dual parallel encoders to autonomously extract high-level morphological features from both cardiovascular streams. To bridge these heterogeneous modalities, we introduce a cross-modal correlation fusion layer that explicitly models the electro-mechanical alignment between cardiac electrical triggers and peripheral blood volume pulses. We rigorously evaluated the framework on the publicly available WESAD dataset using a subject-independent 5-fold cross-validation protocol. Our method achieved a mean Accuracy of 90.34%, an AUC-ROC of 97.29%, and a Stress Recall of 94.07%. These results demonstrate that the framework offers a scalable, high-performance solution for real-time monitoring systems that facilitates proactive interventions in healthcare and automotive environments without requiring manual feature engineering.