Research on Driver Fatigue Detection in Real Driving Environments Based on Semi-Dry Electrodes with Automatic...

Area of Science:

• Biomedical Engineering
• Neuroscience
• Transportation Safety

Background:

• Driving fatigue is a significant risk factor for road accidents.
• Current fatigue monitoring methods face challenges with electrode lifespan and signal interference.
• Accurate, real-time fatigue detection is crucial for enhancing vehicle and road safety.

Purpose of the Study:

• To develop and evaluate a novel semi-dry electrode system for continuous driving fatigue monitoring.
• To implement a transfer learning algorithm for accurate electroencephalography (EEG) signal analysis in fatigue detection.
• To improve the reliability and efficiency of driving fatigue detection systems.

Main Methods:

• Design of a semi-dry electrode with an automatic conductive fluid replenishment mechanism.
• Utilizing electroencephalography (EEG) signals for fatigue monitoring.
• Application of a transfer learning approach for analyzing EEG data and detecting fatigue.

Main Results:

• The novel semi-dry electrode extends operational lifespan and reduces signal interference.
• The transfer learning method effectively addresses data sparsity in real-time monitoring.
• The proposed system demonstrates strong generalization, cross-domain adaptability, faster response times, and enhanced accuracy.

Conclusions:

• The developed semi-dry electrode and transfer learning algorithm enable rapid and accurate driving fatigue detection.
• This technology can provide timely alerts, mitigating traffic accident risks.
• The approach significantly enhances overall vehicle and road traffic safety.