Electroencephalogram-Based Approaches for Driver Drowsiness Detection and Management: A Review

Abstract

Drowsiness is not only a core challenge to safe driving in traditional driving conditions but also a serious obstacle for the wide acceptance of added services of self-driving cars (because drowsiness is, in fact, one of the most representative early-stage symptoms of self-driving carsickness). In view of the importance of detecting drivers’ drowsiness, this paper reviews the algorithms of electroencephalogram (EEG)-based drivers’ drowsiness detection (DDD). To facilitate the review, the EEG-based DDD approaches are organized into a tree structure taxonomy, having two main categories, namely “detection only (open-loop)” and “management (closed-loop)”, both aimed at designing better DDD systems that ensure early detection, reliability and practical utility. To achieve this goal, we addressed seven questions, the answers of which helped in developing an EEG-based DDD system that is superior to the existing ones. A basic assumption in this review article is that although driver drowsiness and carsickness-induced drowsiness are caused by different factors, the brain network that regulates drowsiness is the same.

Designing an Embedded Feature Selection Algorithm for a Drowsiness Detector Model Based on Electroencephalogram Data

“…The most widely used decision-making models are radial basis functions (RBF), support vector machines (SVM), artificial neural networks (ANN), fuzzy inference systems (FIS), linear discriminant analysis (LDA), receiver support vector regression (SVR), multiple linear regression (MLR), self-organizing neural fuzzy inference networks (SONFIN), etc. [ 2 ].…”

“…Having a reliable ground truth is crucial as its precision directly implies the exact characteristics of the decision-making model. Ground truth can be obtained by subjects’ self-assessment, expert rating, reaction time, and physiological signals [ 2 ]. In many studies, EEG has been reported to be the most reliable indicator of drowsiness, as it directly describes the drivers’ physical state [ 5 , 7 ].…”

“…Nevertheless, various methods have been proposed for the identification of drivers’ drowsiness using different indicators, such as subjective self-assessment, expert assessment, reaction time measurements, the percentage of eyelid closure over the pupils (PERCLOS) and other physiological signals, like electroencephalograms (EEG) describing brain function, electrooculograms (EOG) representing eye movements, electrocardiogram (ECG) representing heart waves, breathing, etc. [ 2 ]. Unfortunately, in practice, all these indicators can be described as large feature vectors at every timestamp, which enlarges the input data’s dimensionality significantly, also it is likely to contain redundancy.…”

Evaluation of a New Lightweight EEG Technology for Translational Applications of Passive Brain-Computer Interfaces

“…A physiological decrease in vigilance over time is associated with performance degradation, such as slower reaction times and loss of situation awareness, whereas optimal performance is ensured by an adequate level of activation throughout the task (Parasuraman et al, 1998 ). EEG measures have been used as features for machine learning models to monitor vigilance levels in different contexts (Sebastiani et al, 2020 ; Kamrud et al, 2021 ; Li and Chung, 2022 ).…”

Attention Detection by Heartbeat and Respiratory Features from Radio-Frequency Sensor

“…While EEG frequency bands contain important information to detect sustained or selective attention [ 19 ], degree of inattentiveness is more difficult to identify [ 18 ]. Electrooculography (EOG) can measure long blink durations and slow eye movements, which are indicators of sleepiness and reduced attention [ 20 ]. Furthermore, SC, measured from electrodes on fingers or hands has also been used for mental workload assessment [ 21 ].…”