| General note |
Background: Each year millions of vehicles suffer crashes on the roads globally due to<br/>deteriorated mental state of the drivers during driving tasks which result in higher casualties.<br/>Drowsy driving is the leading cause of high fatality rate which is instigated due to sleep<br/>deprivation, fatigue, and anxiety, etc. Vehicular, and driver’s behavioral data-dependent<br/>systems detect the drowsiness after its onset when an accident is more likely, and they are also<br/>subject to false identification. The drowsy mental state of drivers must be detected earlier for<br/>in-time warning to avoid fatal losses, and also the system must be less intrusive, and adaptable<br/>for normal driving tasks. Detection systems using physiological signals from human organs are<br/>comparatively underexplored in which bodily states of the subject can be identified earlier and<br/>with more reliability. It is postulated that all the bodily states are primarily originated from the<br/>human brain which could be a promising region to detect drowsiness at an earlier stage. Among<br/>many physiological signals, electroencephalography (EEG), and functional near-infrared<br/>spectroscopy (fNIRS) are chosen for this study because they are proved to be more portable,<br/>easy to use, non-invasive, and reliable brain modalities for human mental state detection.<br/>Aim and Objectives: This study aimed to design a passive brain-computer interface (pBCI)<br/>scheme for the earlier detection of driver drowsiness with minimum intrusion into the driving<br/>task. Design objectives for the pBCI scheme were to select the channel of interest (COI), online<br/>detection with a shorter time window, minimum recalibration and setup time, and development<br/>of a widely applicable standard as an inter-subject transfer framework (iSTF) to cater to the<br/>inter-subject variability. All these objectives lead to such a pBCI system that is readily available<br/>for any subject, anytime, easy to use with minimal design, and yet detecting the drowsiness<br/>correctly at an earlier stage to avoid life losses.<br/>Methodology: Multichannel EEG and fNIRS brain signals from anterior, posterior, and lateral<br/>brain regions of sleep-deprived drowsy subjects were acquired during the simulated driving<br/>task for post hoc analysis. Initial pBCIschemes used labeled EEG data acquired from prefrontal<br/>(PFC), frontal, and occipital cortices for extracting the eight spectral, and eight temporal<br/>xvi<br/>features of EEG signals. Seven supervised machine learning classifiers were used to do the<br/>cross-validated binary classification of drowsy, and alert brain states. Initial design only<br/>achieved a few objectives and generated the need to use different modalities to meet all the<br/>requirements. The final pBCI scheme used labeled fNIRS data acquired from PFC and<br/>dorsolateral prefrontal cortices (DLPFC) for extracting the six cerebral oxygen regulation<br/>(CORE) and three hemodynamic signal features. CORE states of wakefulness and non-rapid<br/>eye movement (NREM) sleep stages were used to design a novel standard framework for wide<br/>applicability, and sleep stage classification using the vector phase analysis (VPA) approach.<br/>VPA was used for classifying microsleep/lapse, and drowsiness detection was done using the<br/>proposed brain hemodynamic patterns.<br/>Results: 𝛿, 𝜃, 𝛼, 𝛽 band powers as EEG spectral features achieved 82% accuracy in 10 s<br/>detection window. Signal skewness, variance, mean, peak as EEG temporal features achieved<br/>87.2% accuracy in 1 s detection window. Ensemble classifier declared F8 as COI for earlier<br/>drowsiness detection using both the EEG pBCI schemes. Only the objectives of the short<br/>detection window and COI were achieved with the initial designs. In the final design with<br/>fNIRS, the novel VPA features: CORE vector gradients, achieved 94.1% accuracy in 5 s<br/>detection window for NREM sleep stage classification using ensemble classifier with the least<br/>computation time of 44 ms. Precise spatial localization of fNIRS declared AF8 position in right<br/>DLPFC as COI. The novel sleep stages-based threshold criteria along with VPA were crossvalidated as a standard iSTF for online microsleep detection with the least recalibration and<br/>setup time. Feature selection and achieved results were validated with various statistical<br/>significance tests. All the design objectives were attained with the fNIRS-based pBCI scheme.<br/>Conclusion: The aim to detect the driver's drowsiness earlier with minimum intrusion into the<br/>driving task, is accomplished. The presented fNIRS-based adaptive pBCI scheme is readily<br/>available for any subject, anytime, easy to wear with minimal ergonomic design, capable of<br/>real-time, correct, and early detection of the driver drowsiness to lessen the life losses in<br/>vehicular driving scenarios. The recommended research directions will surely justify, improve,<br/>and broaden the application horizons of the presented design |
