EEG Spectral Comparison Between Occipital and Prefrontal Cortices for Early Detection of Driver Drowsiness

Abstract

A passive brain-computer interface (BCI) based upon electroencephalography (EEG) brain signals was developed to classify alert and drowsy states during the driving task. This BCI modality acquired electrical neuronal activity of five healthy male subjects from prefrontal and occipital cortices of the human brain for earlier drowsiness detection. Brain activity is recorded using a 16-channel EEG headset from these brain locations. Sleep-deprived subjects drove the vehicle in a simulated driving environment while neuronal activity was continuously monitored in prefrontal and occipital regions. Spectral band power and power spectral density estimate for $\alpha$ and $\beta$ frequency bands were used as features along with k-nearest neighbor (kNN) and support vector machine (SVM) classifiers. Average classification accuracies are 95.8% for kNN and 93.8% for SVM with a 10-fold cross-validation model. Spectral analysis shows that $\alpha$-rhythms are more prominent in the occipital region as compared to the prefrontal region during drowsy driving and hence vision-based brain data is more effective for earlier detection as compared to the focus-based brain data. The proposed EEG-based passive BCI scheme is promising for earlier differentiation between drowsy and alert states from the occipital region of the human brain.