A Review on Mental Stress Assessment Methods Using EEG Signals

Area of Science:

• Neuroscience
• Biomedical Engineering
• Psychology

Background:

• Mental stress is a significant health concern.
• Neuroimaging tools are used for early mental stress detection.
• Electroencephalogram (EEG) signals offer rich data on mental states.

Purpose of the Study:

• To review existing EEG signal analysis methods for mental stress assessment.
• To identify factors contributing to contradictory findings in EEG-based stress research.
• To propose an integrated approach for improved mental stress recognition.

Main Methods:

• Systematic review of literature on EEG signal analysis for mental stress.
• Analysis of variations in data processing, feature extraction, and classification methods.
• Exploration of different EEG features, including time-varying and connectivity measures.

Main Results:

• Significant variations in research findings due to diverse methodologies.
• Lack of standardized protocols, brain region focus, stressor types, and analysis techniques contribute to inconsistencies.
• The choice of features is critical for accurate mental stress recognition.

Conclusions:

• Integrating cortical activations, connectivity networks, and deep learning can enhance mental stress assessment accuracy.
• Standardization of protocols and advanced feature integration are crucial for reliable EEG-based stress detection.
• Further research should focus on combining diverse EEG analysis techniques for robust mental stress evaluation.