Does brain connectivity hold the key to safer roads? EEG-based fatigue detection in young drivers using interpretable deep learning

Mental fatigue is a significant risk factor for fatal road accidents among young drivers, but its underlying neural mechanisms are still poorly understood. To fill this gap, we explored the neurophysiological basis of driver fatigue using electroencephalography (EEG)-based brain connectivity analysis and designed an accurate, interpretable detection model specifically for young drivers. We collected EEG data from 32 young drivers on real roads and compared them with data obtained in a simulated laboratory environment to verify their reliability. The EEG signals were processed to construct brain functional networks characterised by topological features such as the small-world attribute and node strength. To capture the complex spatial–temporal dynamics of neural activity associated with fatigue, we designed a deep learning model integrating multi-head self-attention with long short-term memory (MHSA-xLSTM). We used the Shapley Additive exPlanation method to analyse the contribution of individual features to driver fatigue recognition, increasing our model's interpretability. The novel MHSA-xLSTM model achieved an accuracy of 94.39 % (±2.52 %) in detecting mental fatigue amongst young drivers. The small-world attribute and node strength significantly influenced the model's performance in recognising fatigue. In addition, we found that the brain's self-regulatory capabilities can mitigate fatigue-related impairments. Young drivers who accumulate driving experience can enhance their driving performance, reducing the likelihood of fatigue-induced impairments and the associated risk of accidents. The findings highlight the potential of EEG-based brain network analysis and advanced deep learning models to enable accurate real-time detection of driver fatigue, informing targeted interventions to reduce accident risks among young drivers.