Drowsiness Detection in Dorsolateral-Prefrontal Cortex using fNIRS for a Passive-BCI

In this paper, we have investigated the feasibility of detecting drowsiness using hemodynamic brain signals for a passive brain-computer interface (BCI). Functional near-infrared spectroscopy (fNIRS) is used to measure the right dorsolateral-prefrontal brain region in order to investigate the hemodynamic changes corresponding to drowsy and alert states. The data is recorded using five drowsy subjects during a simulated car driving task. The recoded data are converted into oxy- and deoxy-hemoglobin (HBO and HbR) using the modified Beer-Lambert law (MBLL) for feature extraction and classification. Signal mean and signal slope are extracted using the spatio-temporal time windows as features. Linear discriminant analysis (LDA) and support vector machines (SVM) are used for the training and testing of the brain data. The classification accuracy obtained using offline analyses is 74% and 77% respectively. The results show that drowsy and alert states are distinguishable from the right dorsolateral prefrontal brain region. Also, fNIRS modality can be used for drowsiness detection for a passive BCI.