Mining the Potential Temporal Features Based on Wearable EEG Signals for Driving State Analysis

Fatigue driving is considered to be one of the main factors causing traffic accidents, so fatigue driving detection technology has an important role in road safety. Currently, EEG-based detection is one of the most intuitive and effective means for fatigue driving. We introduce a model known as EFDD (EEG-based Fatigue Driving Detection Model), in our study, by analyzing EEG signals, we extract time-domain and frequency-domain features respectively, explore the potential of different temporal EEG features for fatigue driving detection, Classification using LightGBM machine learning models, and then realize fatigue driving detection. Experiments demonstrate that our extracted features perform well in fatigue driving detection. Meanwhile, our study provides technical support for the feasibility of applying portable detection devices in the future.