A Review of EEG Signal Features and their Application in Driver Drowsiness Detection Systems

Area of Science:

• Neuroscience
• Artificial Intelligence
• Transportation Safety

Background:

• Driver drowsiness is a major cause of road accidents.
• Neurophysiological signals, particularly electroencephalogram (EEG), are vital for detecting drowsiness.
• Existing methods often struggle with multi-level drowsiness detection.

Purpose of the Study:

• To review EEG signal features used in drowsiness detection.
• To examine deep learning applications in driver drowsiness detection.
• To discuss challenges and opportunities for improving EEG-based systems.

Main Methods:

• Literature review of EEG features for various tasks.
• Focused review on EEG features and deep learning in driver drowsiness detection.
• Analysis of current challenges and future directions.

Main Results:

• The use of EEG signal features and deep learning in driver drowsiness detection is increasing.
• A wide variety of EEG features and deep learning techniques are being explored.
• Accuracy improvements are linked to considering diverse EEG features and deep learning approaches.

Conclusions:

• EEG is a key data source for reliable driver drowsiness detection.
• Future systems must integrate a broad spectrum of EEG features and deep learning models.
• Continued research is needed to enhance the accuracy and robustness of these systems.