Driver drowsiness detection methods using EEG signals: a systematic review

Abstract

Electroencephalography (EEG) is a complex signal that may require several years of training, advanced signal processing, and feature extraction methodologies to interpret correctly. Recently, many methods have been used to extract and classify EEG data. This study reviews 62 papers that used EEG signals to detect driver drowsiness, published between January 2018 and 2022. We extract trends and highlight interesting approaches from this large body of literature to inform future research and formulate recommendations. To find relevant papers published in scientific journals, conferences, and electronic preprint repositories, researchers searched major databases covering the domains of science and engineering. For each investigation, many data items about (1) the data, (2) the channels used, (3) the extraction and classification procedure, and (4) the outcomes were extracted. These items were then analyzed one by one to uncover trends. Our analysis reveals that the amount of EEG data used across studies varies. We saw that more than half the studies used simulation driving experimental. About 21% of the studies used support vector machine (SVM), while 19% used convolutional neural networks (CNN). Overall, we can conclude that drowsiness and fatigue impair driving performance, resulting in drivers who are more exposed to risky situations.

Keywords:

• Drowsy driving detection
• electroencephalography
• electrical activity
• power spectral density
• machine learning
• medical signal processing

Disclosure statement

No potential conflict of interest was reported by the authors.

Abbreviations: PSD: power spectrum density; CNN: convolution neural network; SVR: Support Vector Regression; CNBLS: complex network based broad learning system; MSSA: a multi-source signal alignment; TN: tensor network; IEEG: integral EEG; SSI: simple square integral; SF: spectral flatness; CF: crest factor; LSTM—long-short term memory; AVMD: adaptive variational mode decomposition; BT: ensemble boosted tree; TE: Tsallis Entropy; RE: Renyi Entropy; PE: Permutation Entropy; LEE: Log Energy Entropy; SE: Shannon Entropy; AMCNN-DGCN: multiscale convolutional neural network-dynamical graph convolutional network; GA-SVM: Genetic algorithm based support vector machine; CSPT: Combination of shortest path tree; KNN—k nearest neighbor; SVM—support vector machine; RF—random forest; ELM—extreme learning machine; DCT-discrete cosine transform; FFT: fast Fourier transform; O-TQWT: Optimized tunable Q wavelet transform; HM-Hjorth Mobility; HC: Hjorth complexity; TM: Tukey's trimean; SD: Standard deviation; DT: decision tree; CV: coefficient of variation; SD; Log: logarithm of the amplitude; IQR: interquartile range; TCRFN: TSK-type convolution recurrent fuzzy network; CBNs: clustering on brain networks; PCNN-pulse-coupled neural networks; WPT: Wavelet packet transform; ET: Extra Trees; HFD: Higuchi Fractal Dimension; RN-CNN: recurrence network-based convolutional neural network; sWGAN: semi-supervised Wasserstein Generative Adversarial Networks; CSP: common spatial pattern; MLNN: Multilayer Neural Network; AAC: average amplitude change; COV: coefficient of variation; TM: trimean; Ac: activity; Cx: complexity; J: neg-entropy; and RWECN –relative wavelet entropy complex network.

Funding

The author(s) reported there is no funding associated with the work featured in this article.