End-to-end fatigue driving EEG signal detection model based on improved temporal-graph convolution network

Jia, Huijie; Xiao, Zhongjun; Ji, Peng

doi:10.1016/j.compbiomed.2022.106431

Cited by 16 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different DL-based approaches have been used to extract deep features from EEG signals for drowsiness detection and classification, such as CNN [4,5,[26][27][28][29], Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) [30,31], and other DL approaches [32].…”

Section: Deep Learning (Dl)-based Methodsmentioning

confidence: 99%

“…In another method, Zue et al [5] used the 1D CNNs with the Inception module and modified the AlexNet module to classify the EEG signals as awake or drowsy. Cui et al [26] introduced a compact and interpretable 1D CNN model for discovering shared EEG features by combining the global average pooling (GAP) layer in the model structure and the Class Activation Map (CAM) method for localizing regions of the input signal to classify EEG signals. In another study, Cui et al [27] introduced an interpretable 1D CNN to allow a sample-wise analysis of important features to classify EEG signals and take advantage of separable convolutions to process the EEG signals in a spatial-temporal sequence.…”

Section: Deep Learning (Dl)-based Methodsmentioning

confidence: 99%

“…In another study, Cui et al [27] introduced an interpretable 1D CNN to allow a sample-wise analysis of important features to classify EEG signals and take advantage of separable convolutions to process the EEG signals in a spatial-temporal sequence. In another study, Liqianga et al [29] proposed a novel cross-dataset driver drowsiness recognition by introducing an entropy-guided robust feature (EGRF) adaptation framework that is based on an ICNN [26] as a baseline network to extract important features from the EEG signal. They proposed a deep unsupervised domain adaptation (UDA) technique to minimize the group-level drifts of EEG signal distribution.…”

Section: Deep Learning (Dl)-based Methodsmentioning

confidence: 99%

See 2 more Smart Citations

EEG_DMNet: A Deep Multi-Scale Convolutional Neural Network for Electroencephalography-Based Driver Drowsiness Detection

Obaidan,

Hussain,

AlMajed

2024

Electronics

View full text Add to dashboard Cite

Drowsy driving is one of the major causes of traffic accidents, injuries, and deaths on roads worldwide. One of the best physiological signals that are useful in detecting a driver’s drowsiness is electroencephalography (EEG), a kind of brain signal that directly measures neurophysiological activities in the brain and is widely utilized for brain–computer interfaces (BCIs). However, designing a drowsiness detection method using EEG signals is still challenging because of their non-stationary nature. Deep learning, specifically convolutional neural networks (CNNs), has recently shown promising results in driver’s drowsiness. However, state-of-the-art CNN-based methods extract features sequentially and discard multi-scale spectral-temporal features, which are important in tackling the non-stationarity of EEG signals. This paper proposes a deep multi-scale convolutional neural network (EEG_DMNet) for driver’s drowsiness detection that learns spectral-temporal features. It consists of two main modules. First, the multi-scale spectral-temporal features are extracted from EEG trials using 1D temporal convolutions. Second, the spatial feature representation module calculates spatial patterns from the extracted multi-scale features using 1D spatial convolutions. The experimental results on the public domain benchmark SEED-VIG EEG dataset showed that it learns discriminative features, resulting in an average accuracy of 97.03%, outperforming the state-of-the-art methods that used the same dataset. The findings demonstrate that the proposed method effectively and efficiently detects drivers’ drowsiness based on EEG and can be helpful for safe driving.

show abstract

Section: Deep Learning (Dl)-based Methodsmentioning

confidence: 99%

Section: Deep Learning (Dl)-based Methodsmentioning

confidence: 99%

Section: Deep Learning (Dl)-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

EEG_DMNet: A Deep Multi-Scale Convolutional Neural Network for Electroencephalography-Based Driver Drowsiness Detection

Obaidan,

Hussain,

AlMajed

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Fatigued driving is a significant cause of traffic accidents [4,18,19]. Thus, detecting fatigued driving is an effective approach to preventing traffic accidents [20,21]. In previous studies, the fatigued driving state in a low-voltage and hypoxia plateau environment was studied with drivers' real-time electroencephalogram signals [20].…”

Section: Introductionmentioning

confidence: 99%

“…The deep learning-based fatigue detection method was investigated, and a multimodal signal fatigue detection method was proposed [25]. A fatigued driving detection algorithm was proposed based on an end-to-end temporal and graph convolution [21]. A communication-efficient federated learning method was proposed for fatigued driving supervision [26].…”

Section: Introductionmentioning

confidence: 99%

Driving Risk Identification of Truck Drivers Based on China’s Highway Toll Data

Yang

2024

Sustainability

View full text Add to dashboard Cite

Dangerous or illegal driving may disrupt the traffic safety management of public security organs, damage road infrastructure, lead to traffic accidents, or result in economic losses. This paper proposes a framework based on China’s highway toll data to identify dangerous or illegal driving risks, such as unfamiliarity with road conditions, overload, driving over the speed limit, fatigued driving, fake license plates, and other risks. The unfamiliarity with road conditions is identified with the frequency of driving routes. When the total weight of a vehicle and its cargo is greater than the upper limit of the total weight of the vehicle and its cargo, the vehicle can be judged as overloaded. When the actual travel time is less than the minimum travel time, it can be inferred that the vehicle has a risk of fatigued driving, driving over the speed limit, a fake license plate, or other risks. Two accidents are used to demonstrate the process of the proposed framework for identifying driving risks based on China’s highway toll data. Additional analysis proves that the proposed framework can be used to identify dangerous or illegal driving risks, and it provides a scientific basis for the traffic safety management of public security organs, reducing infrastructure damage, and avoiding the loss of national taxes and fees.

show abstract

Multi‐parameter fusion driver fatigue detection method based on facial fatigue features

Du,

Yu,

Sun

2024

J Soc Info Display

View full text Add to dashboard Cite

Fatigued driving is one of the main causes of traffic accidents. In order to improve the detection speed of fatigue driving recognition, this paper proposes a driver fatigue detection method based on multi‐parameter fusion of facial features. It uses a cascaded Adaboost object classifier to detect faces in video streams. The DliB library is employed for facial key point detection, which locates the driver's eyes and mouth to determine their states. The eye aspect ratio (EAR) is calculated to detect eye closure, and the mouth aspect ratio (MAR) is calculated to detect yawning frequency and count. The detected percentage of eye closure (PERCLOS) value is combined with yawning frequency and count, and a multi‐feature fusion approach is used for fatigue detection. Experimental results show that the accuracy of blink detection is 91% and the accuracy of yawn detection is 96.43%. Furthermore, compared to the models mentioned in the comparative experiments, this model achieves two to four times faster detection times while maintaining accuracy.

show abstract

End-to-end fatigue driving EEG signal detection model based on improved temporal-graph convolution network

Cited by 16 publications

References 30 publications

EEG_DMNet: A Deep Multi-Scale Convolutional Neural Network for Electroencephalography-Based Driver Drowsiness Detection

EEG_DMNet: A Deep Multi-Scale Convolutional Neural Network for Electroencephalography-Based Driver Drowsiness Detection

Driving Risk Identification of Truck Drivers Based on China’s Highway Toll Data

Multi‐parameter fusion driver fatigue detection method based on facial fatigue features

Contact Info

Product

Resources

About