Key result
The combination of basic scale entropy and MVAR-PSI method effectively detected driving fatigue, with the prefrontal cortex transitioning from a causal source to a target during fatigue.
Why the study?
Driving fatigue is the main cause of traffic accidents during long-term continuous driving, making accurate and rapid detection of driver mental fatigue critical for traffic safety.
The combination of basic scale entropy and MVAR-PSI method based on EEG signals can effectively detect a driver's long-term driving fatigue state.
Supports EEG entropy features for driver fatigue detection; leaves open prospective validation before safety applications.
In long-term continuous driving, driving fatigue is the main cause of traffic accidents. Therefore, accurate and rapid detection of driver mental fatigue is of great significance to traffic safety. In our study, the electroencephalogram (EEG) signals of subjects were preprocessed to remove interference signals. The Butterworth band-pass filter is used to extract the EEG signals of α and β rhythms, and then the basic scale entropy of α and β rhythms is used as driving fatigue characteristics. In addition, combined with the fast multiple autoregressive (MVAR) model and phase slope index (PSI), short-term data is used to accurately estimate the effective connectivity of EEG signals between different channels, and analyzed the causality flow direction in the left and right prefrontal regions of drivers at different driving stages. Further comprehensive analysis of the driver’s driving fatigue state in the continuous driving phase. Finally, the correlation coefficient value between the parameter pairs (basic scale entropy, clustering coefficient, global efficiency) is calculated. The results showed that the causality flow outflow degree of prefrontal lobe decreased during the transition from sober driving state to tired driving state. The left and right prefrontal lobes were the source of causality in sober driving state, and gradually became the target of causality with the occurrence of driving fatigue. The results showed that when transitioning from a waking state to a fatigued driving state, the causal flow direction out-degree value of the prefrontal cortex on a declining curve, and the left and right prefrontal cortex exhibited the causal source in the awake driving state, which gradually changed into the causal target along with the occurrence of driving fatigue. The three parameters of basic scale entropy, clustering coefficient and global efficiency are used as driving fatigue characteristics, and every two parameters have strong correlation. It shows that the combination of basic scale entropy and MVAR-PSI method can effectively detect the driver’s long-term driving fatigue state in continuous driving mode.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2022) studied Driving fatigue. Basic scale entropy and MVAR-PSI method was evaluated on Detection of driving fatigue state. The combination of basic scale entropy and MVAR-PSI method effectively detected driving fatigue, with the prefrontal cortex transitioning from a causal source to a target during fatigue.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: