Automatic Detection of Driver Fatigue Based on EEG Signals Using a Developed Deep Neural Network

EEG-based fatigue state evaluation by combining complex network and frequency-spatial features

BACKGROUND

The proportion of traffic accidents caused by fatigue driving is increasing year by year, which has aroused wide concerns for researchers. In order to rapidly and accurately detect drivers' fatigue, this paper proposed an electroencephalogram (EEG)-based fatigue state evaluation method by combining complex network and frequency-spatial features.

NEW METHOD

First, this paper constructed a complex network model based on the relative wavelet entropy to characterize the correlation strength information between channels. Then, the differential entropy and symmetry quotient were respectively calculated to extract frequency and spatial features. Then, the brain heat map combined the complex network and frequency-spatial features with different dimensions together as the fusion features. Finally, a convolutional neural network-long short-term memory (CNN-LSTM) neural network was used to evaluate the three-class fatigue states of the EEG data in the Shanghai Jiao Tong University (SJTU) Emotion EEG Dataset (SEED)-VIG dataset, and it was validated on the dataset on the Mendeley Data website.

RESULTS

The experimental results of SEED-VIG dataset show that the average classification accuracy of three-class fatigue states, namely, awake, tired and drowsy, reaches 96.57 %. The average classification accuracy on the dataset on the Mendeley Data website reaches 99.23 %.

COMPARISON WITH EXISTING METHODS

This method has a best evaluation performance compared with the state-of-the-art methods for the three-class fatigue states recognition.

CONCLUSIONS

The experiment results validated the feasibility of the fatigue state evaluation method based on the correlations between channels and the frequency-spatial features, which is of great significance for developing a driver fatigue detection system.

Application of Additive Manufacturing and Deep Learning in Exercise State Discrimination

With the rapid development of sports technology, smart wearable devices play a crucial role in athletic training and health management. Sports fatigue is a key factor affecting athletic performance. Using smart wearable devices to detect the onset of fatigue can optimize training, prevent excessive fatigue and resultant injury, and increase efficiency and safety. However, current wearable sensing devices are often uncomfortable and imprecise. Furthermore, stable methods for fatigue detection are not yet established. To address these challenges, this paper introduces 3D printing and deep learning to design a smart wearable sensing device to detect different states of sports fatigue. First, to meet the need for comfort and improved accuracy in data collection, we utilized reverse engineering and additive manufacturing technologies. Second, we designed a prototype based on the long short-term memory (LSTM) neural network to analyze the collected bioelectrical signals for the identification of sports fatigue states and the extraction of related indicators. Finally, we conducted a large number of numerical experiments. The results demonstrated that our prototype and related equipment could collect signals and mine information as well as identify indicators associated with sports fatigue in the signals, thereby improving accuracy in the classification of fatigue states.

A Novel Approach for Automatic Detection of Driver Fatigue Using EEG Signals Based on Graph Convolutional Networks

Nowadays, the automatic detection of driver fatigue has become one of the important measures to prevent traffic accidents. For this purpose, a lot of research has been conducted in this field in recent years. However, the diagnosis of fatigue in recent research is binary and has no operational capability. This research presents a multi-class driver fatigue detection system based on electroencephalography (EEG) signals using deep learning networks. In the proposed system, a standard driving simulator has been designed, and a database has been collected based on the recording of EEG signals from 20 participants in five different classes of fatigue. In addition to self-report questionnaires, changes in physiological patterns are used to confirm the various stages of weariness in the suggested model. To pre-process and process the signal, a combination of generative adversarial networks (GAN) and graph convolutional networks (GCN) has been used. The proposed deep model includes five convolutional graph layers, one dense layer, and one fully connected layer. The accuracy obtained for the proposed model is 99%, 97%, 96%, and 91%, respectively, for the four different considered practical cases. The proposed model is compared to one developed through recent methods and research and has a promising performance.

Fatigue factors and fatigue indices in SSVEP-based brain-computer interfaces: a systematic review and meta-analysis

Background

Fatigue is a serious challenge when applying a steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) in the real world. Many researchers have used quantitative indices to study the effect of visual stimuli on fatigue. According to a wide range of studies in fatigue analysis, there are contradictions and inconsistencies in the behavior of fatigue indicators.

New method

In this study, for the first time, a systematic review and meta-analysis were performed on fatigue indices and fatigue caused by stimulation paradigm. We queried three scientific search engines for studies published between 2000 and 2022. The inclusion criteria were papers investigating mental and visual fatigue from performing a visual task using electroencephalogram (EEG) signals.

Results

Attractiveness and variation are the most effective ways to reduce BCI fatigue. Therefore, zoom motion, Newton's ring motion, and cue patterns reduce fatigue. While the color of the cue could effectively reduce fatigue, its shape and background had no effect on fatigue. Additionally, the questionnaire and quantitative indicators such as frequency indices, signal-to-noise ratio (SNR), SSVEP amplitude, and multiscale entropy were utilized to assess fatigue. Meta-analysis indicated that when a person is fatigued, the spectrum amplitude of alpha, theta, and α + θ / β increase significantly, while SNR and SSVEP amplitude decrease significantly.

Conclusion

The outcomes of this study can be used to design more optimal stimulation protocols that cause less fatigue. Moreover, the level of fatigue can be quantitatively assessed with indicators without the participant's self-reports.

Miner Fatigue Detection from Electroencephalogram-Based Relative Power Spectral Topography Using Convolutional Neural Network

Fatigue of miners is caused by intensive workloads, long working hours, and shift-work schedules. It is one of the major factors increasing the risk of safety problems and work mistakes. Examining the detection of miner fatigue is important because it can potentially prevent work accidents and improve working efficiency in underground coal mines. Many previous studies have introduced feature-based machine-learning methods to estimate miner fatigue. This work proposes a method that uses electroencephalogram (EEG) signals to generate topographic maps containing frequency and spatial information. It utilizes a convolutional neural network (CNN) to classify the normal state, critical state, and fatigue state of miners. The topographic maps are generated from the EEG signals and contrasted using power spectral density (PSD) and relative power spectral density (RPSD). These two feature extraction methods were applied to feature recognition and four representative deep-learning methods. The results showthat RPSD achieves better performance than PSD in classification accuracy with all deep-learning methods. The CNN achieved superior results to the other deep-learning methods, with an accuracy of 94.5%, precision of 97.0%, sensitivity of 94.8%, and F1 score of 96.3%. Our results also show that the RPSD-CNN method outperforms the current state of the art. Thus, this method might be a useful and effective miner fatigue detection tool for coal companies in the near future.

Deep Learning for Detecting Multi-Level Driver Fatigue Using Physiological Signals: A Comprehensive Approach

A large share of traffic accidents is related to driver fatigue. In recent years, many studies have been organized in order to diagnose and warn drivers. In this research, a new approach was presented in order to detect multi-level driver fatigue. A multi-level driver tiredness diagnostic database based on physiological signals including ECG, EEG, EMG, and respiratory effort was developed for this aim. The EEG signal was used for processing and other recorded signals were used to confirm the driver's fatigue so that fatigue was not confirmed based on self-report questionnaires. A customized architecture based on adversarial generative networks and convolutional neural networks (end-to-end) was utilized to select/extract features and classify different levels of fatigue. In the customized architecture, with the objective of eliminating uncertainty, type 2 fuzzy sets were used instead of activation functions such as Relu and Leaky Relu, and the performance of each was investigated. The final accuracy obtained in the three scenarios considered, two-level, three-level, and five-level, were 96.8%, 95.1%, and 89.1%, respectively. Given the suggested model's optimal performance, which can identify five various levels of driver fatigue with high accuracy, it can be employed in practical applications of driver fatigue to warn drivers.

A regression model combined convolutional neural network and recurrent neural network for electroencephalogram-based cross-subject fatigue detection

Fatigue, one of the most important factors affecting road safety, has attracted many researchers' attention. Most existing fatigue detection methods are based on feature engineering and classification models. The feature engineering is greatly influenced by researchers' domain knowledge, which will lead to a poor performance in fatigue detection, especially in cross-subject experiment design. In addition, fatigue detection is often simplified as a classification problem of several discrete states. Models based on deep learning can realize automatic feature extraction without the limitation of researcher's domain knowledge. Therefore, this paper proposes a regression model combined convolutional neural network and recurrent neural network for electroencephalogram-based (EEG-based) cross-subject fatigue detection. At the same time, a twofold random-offset zero-overlapping sampling method is proposed to train a bigger model and reduce overfitting. Compared with existing results, the proposed method achieves a much better result of 0.94 correlation coefficient (COR) and 0.09 root mean square error (RMSE) in a within-subject experiment design. What is more, there is no misclassification between awake and drowsy states. For cross-subject experiment design, the COR and RMSE are 0.79 and 0.15, respectively, which are close to the existing within-subject results and better than similar cross-subject results. The cross-subject regression model is very important for fatigue detection application since the fatigue indication is more precise than several discrete states and no model calibration is required for a new user. The twofold random-offset zero-overlapping sampling method can also be used as a reference by other EEG-based deep learning research.

Analysis of Relation between Brainwave Activity and Reaction Time of Short-Haul Pilots Based on EEG Data

The purpose of this research is to examine and assess the relation between a pilot's concentration and reaction time with specific brain activity during short-haul flights. Participants took part in one-hour long flight sessions performed on the FNPT II class flight simulator. Subjects were instructed to respond to unexpected events that occurred during the flight. The brainwaves of each participant were recorded with the Emotiv EPOC+ Scientific Contextual EEG device. The majority of participants showed a statistically significant, positive correlation between Theta Power in the frontal lobe and response time. Additionally, most subjects exhibited statistically significant, positive correlations between band-power and reaction times in the Theta range for the temporal and parietal lobes. Statistically significant event-related changes (ERC) were observed for the majority of subjects in the frontal lobe for Theta frequencies, Beta waves in the frontal lobe and in all lobes for the Gamma band. Notably, significant ERC was also observed for Theta and Beta frequencies in the temporal and occipital Lobes, Alpha waves in the frontal, parietal and occipital lobes for most participants. A difference in brain activity patterns was observed, depending on the performance in time-restricted tasks.

PET-validated EEG-machine learning algorithm predicts brain amyloid pathology in pre-dementia Alzheimer's disease

Developing reliable biomarkers is important for screening Alzheimer's disease (AD) and monitoring its progression. Although EEG is non-invasive direct measurement of brain neural activity and has potentials for various neurologic disorders, vulnerability to noise, difficulty in clinical interpretation and quantification of signal information have limited its clinical application. There have been many research about machine learning (ML) adoption with EEG, but the accuracy of detecting AD is not so high or not validated with Aβ PET scan. We developed EEG-ML algorithm to detect brain Aβ pathology among subjective cognitive decline (SCD) or mild cognitive impairment (MCI) population, and validated it with Aβ PET. 19-channel resting-state EEG and Aβ PET were collected from 311 subjects: 196 SCD(36 Aβ +, 160 Aβ -), 115 MCI(54 Aβ +, 61Aβ -). 235 EEG data were used for training ML, and 76 for validation. EEG features were standardized for age and sex. Multiple important features sets were selected by 6 statistics analysis. Then, we trained 8 multiple machine learning for each important features set. Meanwhile, we conducted paired t-test to find statistically different features between amyloid positive and negative group. The best model showed 90.9% sensitivity, 76.7% specificity and 82.9% accuracy in MCI + SCD (33 Aβ +, 43 Aβ -). Limited to SCD, 92.3% sensitivity, 75.0% specificity, 81.1% accuracy (13 Aβ +, 24 Aβ -). 90% sensitivity, 78.9% specificity and 84.6% accuracy for MCI (20 Aβ +, 19 Aβ -). Similar trends of EEG power have been observed from the group comparison between Aβ + and Aβ -, and between MCI and SCD: enhancement of frontal/ frontotemporal theta; attenuation of mid-beta in centroparietal areas. The present findings suggest that accurate classification for beta-amyloid accumulation in the brain based on QEEG alone could be possible, which implies that QEEG is a promising biomarker for beta-amyloid. Since QEEG is more accessible, cost-effective, and safer than amyloid PET, QEEG-based biomarkers may play an important role in the diagnosis and treatment of AD. We expect specific patterns in QEEG could play an important role to predict future progression of cognitive impairment in the preclinical stage of AD. Further feature engineering and validation with larger dataset is recommended.