Abstract
This study addresses limitations in EEG-based stress detection research by developing an
novel approach to differentiate multiple mental states in different stress baselines population samples.
Utilizing EEG signals, graph convolutional neural networks (GCNs), and binaural beats stimulation (BBs),
the research investigates stress detection and reduction in two population sample groups with distinct
baselines (group 1: low daily baseline, and group 2: stressed daily baseline). The experiment comprises four
phases: rest state, control alertness, stress induction, and stress mitigation. Mental states were assessed using
combination of measures: behavioral data (reaction time (RT) to stimuli and target detection accuracy),
subjective reports (Perceived Stress Scale (PSS-10) scores), biochemical indicators (salivary cortisol levels),
and neurophysiological (EEG effective connectivity via Partial Directed Coherence (PDC). BBs significantly
improved target detection accuracy by 31.6% and 22.8% for low and high-stress groups, respectively. PDC
connectivity showed a shift to the temporal region during mitigation, indicating a return to a more balanced
state. GCN classification achieved accuracies of 76.43 ± 9.01% and 76.32 ± 7.79% for each group, and 76.37
± 8.40% for a common baseline. While, 16-Hz BBs enhanced focusing abilities they did not significantly
reduce subjective stress scores. This study highlights the complex relationship between cognitive
performance, perceived stress, and neurophysiological measures, emphasizing the need for multifaceted
stress research and management approaches.
INDEX TERMS mental stress. EEG, deep learning, GCN, PDC, Binaural Beats Stimulation
Authors
Badr, Y., Al-Shargie, F., Khan, M. A., Ali, N. F., Tariq, U., Almughairbi, F., ... & Al-Nashash, H.
https://doi.org/10.1109/ACCESS.2025.3553932