Stress detection through wearable EEG technology: A signal-based approach

Abstract

Accurate and non-invasive stress detection is critical for mental health monitoring and early intervention. Among various physiological signals, electroencephalography (EEG) offers a unique advantage as it captures direct neural activity, making it more responsive to cognitive and emotional stress compared to peripheral markers like heart rate or skin conductance. In this work, we propose a novel EEG-based stress detection framework that combines Fuzzy Attention-based Fully Convolutional Network (FA-FCN) for dynamic signal segmentation, Hybrid Wavelet-Short-Time Fourier Transform (HW-STFT) for rich time–frequency feature extraction, Recursive LASSO (RLASSO) for optimal feature selection, and an Adam-Optimized Sequential Generative Adversarial Network (AOS-GAN) for robust classification. Each component is specifically designed to address the limitations of existing methods FA-FCN enhances signal relevance by focusing on stress-related EEG regions, while HW-STFT captures transient frequency shifts with high resolution. RLASSO improves computational efficiency by reducing dimensionality, and AOS-GAN enhances classification in imbalanced conditions using adversarial learning. Our model achieves an accuracy of 94%, significantly outperforming other state-of-the-art methods, which typically report accuracies around 85%–89%. This demonstrates the model’s strong potential for real-world deployment in high-stress environments such as emergency response, cognitive workload monitoring, or workplace mental health systems. Future work will focus on validating this approach across larger and more diverse EEG datasets, enabling real-time deployment on edge devices, and exploring multimodal integration with other physiological signals for holistic stress assessment.