A Survey of EEG-Based Stress Detection Using Machine Learning and Deep Learning Techniques

This survey paper delves into the emerging realm of stress detection through Electroencephalogram (EEG) signals to employ Deep Learning algorithms. Identifying stress is pivotal for promoting mental well-being, and EEG signals provide a non-invasive method to explore neural activity. The paper assesses various approaches, including preprocessing methods, feature extraction, and various deep-learning models applied to EEG data. It sheds light on the obstacles and opportunities linked with stress detection using EEG signals, underscoring the importance of robust models in practical contexts. This thorough survey aims to assist researchers, practitioners, and technology enthusiasts in grasping the current fostering progress and shaping the trajectory of EEG-based stress detection with Deep Learning.