Recent Advances in Fatigue Detection Algorithm Based on EEG

Abstract

Fatigue is a state commonly caused by overworked, which seriously affects daily work and life. How to detect mental fatigue has always been a hot spot for researchers to explore. Electroencephalogram (EEG) is considered one of the most accurate and objective indicators. This article investigated the development of classification algorithms applied in EEG-based fatigue detection in recent years. According to the different source of the data, we can divide these classification algorithms into two categories, intra-subject (within the same subject) and cross-subject (across different subjects). In most studies, traditional machine learning algorithms with artificial feature extraction methods were commonly used for fatigue detection as intra-subject algorithms. Besides, deep learning algorithms have been applied to fatigue detection and could achieve effective result based on large-scale dataset. However, it is difficult to perform long-term calibration training on the subjects in practical applications. With the lack of large samples, transfer learning algorithms as a cross-subject algorithm could promote the practical application of fatigue detection methods. We found that the research based on deep learning and transfer learning has gradually increased in recent years. But as a field with increasing requirements, researchers still need to continue to explore efficient decoding algorithms, design effective experimental paradigms, and collect and accumulate valid standard data, to achieve fast and accurate fatigue detection methods or systems to further widely apply.

Efficient Generalized EEG-Based Drowsiness Detection Approach with Minimal Electrodes

“…This part will present the methods of analyzing EEG signals to detect drowsiness from three perspectives: time domain analysis, frequency domain analysis, and TF.  Time analysis Time domain analysis [42] has been used in the study of brain function for a long time. Commonly utilized time domain analysis methods encompass statistical characteristics, histogram analysis, Hjorth parameters, fractal dimension, event-related potentials, and more.…”

Driver Attention Detection Based on Improved YOLOv5

“…Currently, there are two main methods of personnel attention detection: detection methods based on wearable devices and detection methods based on machine vision. Detection methods based on wearable devices collect physiological signals such as electroencephalograms [6], electrocardiograms, and electromyograms [7] of the tested person through medical detection equipment, which can directly reflect the physical state of the tested personnel with high accuracy. However, due to the limited number of use scenarios, this kind of wearable device has low applicability, complicated operation, and high cost, which may seriously affect the accuracy of detection in practical work.…”

Utilizing EEG and fNIRS for the detection of sleep-deprivation-induced fatigue and its inhibition using colored light stimulation

“…A more direct and objective assessment of alertness level is provided by evaluating physiological parameters, those can be assessed continually. Fatigue-related signals may also be monitored using functional Near-Infrared Spectroscopy (fNIRS), Electroencephalogram (EEG), and functional Magnetic Resonance Imaging (fMRI) [13][14][15][16] . Several studies have employed fNIRS for drowsiness detection and also to discover association between neurophysiological responses and driver's mental state.…”