Partial directed coherence based graph convolutional neural networks for driving fatigue detection

Driving fatigue detection based on brain source activity and ARMA model

Fatigue among drivers is a significant issue in society, and according to organizational reports, it substantially contributes to accidents. So accurate fatigue detection in drivers plays a crucial role in reducing the number of people fatalities or injured resulting from accidents. Several methods are proposed for fatigue driver recognition among which electroencephalography (EEG) is one. This paper proposed a method for fatigue recognition by EEG signals with extracted features from source and sensor spaces. The proposed method starts with preprocessing by applying filtering and artifact rejection. Then source localization methods are applied to EEG signals for active source extraction. A multivariate autoregressive (MVAR) model is fitted to selected sources, and a dual Kalman filter is applied to estimate the source activity and their relationships. Then multivariate autoregressive moving average (ARMA) is fitted between EEG and source activity signals. Features are extracted from model parameters, source relationship matrix, and wavelet transform of EEG and source activity signals. The novelty of this approach is the use of ARMA model between source activities (as input) and EEG signals (as output) and feature extraction from source relations. Relevant features are selected using a combination of RelifF and neighborhood component analysis (NCA) methods. Three classifiers, namely k-nearest neighbor (KNN), support vector machine (SVM), and naive Bayesian (NB) classifiers, are employed to classify drivers. To improve performance, the final label for fatigue detection is calculated by combining these classifiers using the voting method. The results demonstrate that the proposed method accurately recognizes and classifies fatigued drivers with the ensemble classifiers in comparison with other methods.

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

Fatigue driving is one of the leading causes of traffic accidents, so fatigue driving detection technology plays a crucial role in road safety. The physiological information-based fatigue detection methods have the advantage of objectivity and accuracy. Among many physiological signals, EEG signals are considered to be the most direct and promising ones. Most traditional methods are challenging to train and do not meet real-time requirements. To this end, we propose an end-to-end temporal and graph convolution-based (MATCN-GT) fatigue driving detection algorithm. The MATCN-GT model consists of a multi-scale attentional temporal convolutional neural network block (MATCN block) and a graph convolutional-Transformer block (GT block). Among them, the MATCN block extracts features directly from the original EEG signal without a priori information, and the GT block processes the features of EEG signals between different electrodes. In addition, we design a multi-scale attention module to ensure that valuable information on electrode correlations will not be lost. We add a Transformer module to the graph convolutional network, which can better capture the dependencies between long-distance electrodes. We conduct experiments on the public dataset SEED-VIG, and the accuracy of the MATCN-GT model reached 93.67%, outperforming existing algorithms. Furthermore, compared with the traditional graph convolutional neural network, the GT block has improved the accuracy rate by 3.25%. The accuracy of the MATCN block on different subjects is higher than the existing feature extraction methods.

A graph convolutional neural network for the automated detection of seizures in the neonatal EEG

BACKGROUND AND OBJECTIVE

Neonatal seizures are the most common clinical presentation of neurological conditions and can have adverse effects on the neurodevelopment of the neonatal brain. Visual detection of these events from continuous EEG recordings is a laborious and time-consuming task. We propose a novel algorithm for the automated detection of neonatal seizures.

METHODS

In this study, we propose a novel deep learning model based on Graph Convolutional Neural Networks for the automated detection of neonatal seizures. Unlike other methods exploiting mainly the temporal information contained in EEG signals, our method also considers long-range spatial information, i.e., the interdependencies across EEG signals. The temporal information is embedded as graph signals in the graph representation of the EEG recordings and includes EEG features extracted from the EEG signals in the time and frequency domains. The spatial information is represented as functional connections among the EEG channels (calculated by the phase-locking value and the mean squared coherence) or as maps of Euclidean distances. These different spatial representations were evaluated to assess their efficiency in providing more discriminative features for an effective detection of neonatal seizures. The model performance was assessed on a publicly available dataset of continuous EEG signals recorded from 39 neonates by means of the area under the curve (AUC) and the AUC for specificity values greater than 90% (AUC90).

RESULTS

After applying post-processing, consisting in smoothing the output of the classifiers, the models based on the mean squared coherence, the phase-locking value, and the Euclidean distance respectively reached a median AUC of 99.1% (IQR: 96.8%-99.6%), 99% (IQR: 95.2%-99.7%), and 97.3% (IQR: 86.3%-99.6%), and a median AUC90 of 96%, 95.7%, and 94.9%. These values are superior or comparable to those reached by methods considered as state-of-the-art in this field.

CONCLUSIONS

Our results show that the EEG graph representations drawn from functional connectivity measures can effectively leverage interdependencies among EEG signals and lead to reliable detection of neonatal seizures. Furthermore, our model has the advantage of requiring only temporal annotations on seizures for the training phase, making it more appealing for clinical applications.

Wearable Flexible Electronics Based Cardiac Electrode for Researcher Mental Stress Detection System Using Machine Learning Models on Single Lead Electrocardiogram Signal

In the modern world, wearable smart devices are continuously used to monitor people's health. This study aims to develop an automatic mental stress detection system for researchers based on Electrocardiogram (ECG) signals from smart T-shirts using machine learning classifiers. We used 20 subjects, including 10 from mental stress (after twelve hours of continuous work in the laboratory) and 10 from normal (after completing the sleep or without any work). We also applied three scoring techniques: Chalder Fatigue Scale (CFS), Specific Fatigue Scale (SFS), Depression, Anxiety, and Stress Scale (DASS), to confirm the mental stress. The total duration of ECG recording was 1800 min, including 1200 min during mental stress and 600 min during normal. We calculated two types of features, such as demographic and extracted by ECG signal. In addition, we used Decision Tree (DT), Naive Bayes (NB), Random Forest (RF), and Logistic Regression (LR) to classify the intra-subject (mental stress and normal) and inter-subject classification. The DT leave-one-out model has better performance in terms of recall (93.30%), specificity (96.70%), precision (94.40%), accuracy (93.30%), and F1 (93.50%) in the intra-subject classification. Additionally, The classification accuracy of the system in classifying inter-subjects is 94.10% when using a DT classifier. However, our findings suggest that the wearable smart T-shirt based on the DT classifier may be used in big data applications and health monitoring. Mental stress can lead to mitochondrial dysfunction, oxidative stress, blood pressure, cardiovascular disease, and various health problems. Therefore, real-time ECG signals help assess cardiovascular and related risk factors in the initial stage based on machine learning techniques.

AI-Based Publicity Strategies for Medical Colleges: A Case Study of Healthcare Analysis

The health status and cognition of undergraduates, especially the scientific concept of healthcare, are particularly important for the overall development of society and themselves. The survey shows that there is a significant lack of knowledge about healthcare among undergraduates in medical college, even among medical undergraduates, not to mention non-medical undergraduates. Therefore, it is a good way to publicize healthcare lectures or electives for undergraduates in medical college, which can strengthen undergraduates' cognition of healthcare and strengthen the concept of healthcare. In addition, undergraduates' emotional and mental state in healthcare lectures or electives can be analyzed to determine whether undergraduates have hidden illnesses and how well they understand the healthcare content. In this study, at first, a mental state recognition method of undergraduates in medical college based on data mining technology is proposed. Then, the vision-based expression and posture are used for expanding the channels of emotion recognition, and a dual-channel emotion recognition model based on artificial intelligence (AI) during healthcare lectures or electives in a medical college is proposed. Finally, the simulation is driven by TensorFlow with respect to mental state recognition of undergraduates in medical college and emotion recognition. The simulation results show that the recognition accuracy of mental state recognition of undergraduates in a medical college is more than 92%, and the rejection rate and misrecognition rate are very low, and false match rate and false non-match rate of mental state recognition is significantly better than the other three benchmarks. The emotion recognition of the dual-channel emotion recognition method is over 96%, which effectively integrates the emotional information expressed by facial expressions and postures.

Applications of deep learning methods in digital biomarker research using noninvasive sensing data

Introduction: Noninvasive digital biomarkers are critical elements in digital healthcare in terms of not only the ease of measurement but also their use of raw data. In recent years, deep learning methods have been put to use to analyze these diverse heterogeneous data; these methods include representation learning for feature extraction and supervised learning for the prediction of these biomarkers. Methods: We introduce clinical cases of digital biomarkers and various deep-learning methods applied according to each data type. In addition, deep learning methods for the integrated analysis of multidimensional heterogeneous data are introduced, and the utility of these data as an integrated digital biomarker is presented. The current status of digital biomarker research is examined by surveying research cases applied to various types of data as well as modeling methods. Results: We present a future research direction for using data from heterogeneous sources together by introducing deep learning methods for dimensionality reduction and mode integration from multimodal digital biomarker studies covering related domains. The integration of multimodality has led to advances in research through the improvement of performance and complementarity between modes. Discussion: The integrative digital biomarker will be more useful for research on diseases that require data from multiple sources to be treated together. Since delicate signals from patients are not missed and the interaction effects between signals are also considered, it will be helpful for immediate detection and more accurate prediction of symptoms.

Motor Intention Decoding from the Upper Limb by Graph Convolutional Network Based on Functional Connectivity

Decoding brain intention from noninvasively measured neural signals has recently been a hot topic in brain-computer interface (BCI). The motor commands about the movements of fine parts can increase the degrees of freedom under control and be applied to external equipment without stimulus. In the decoding process, the classifier is one of the key factors, and the graph information of the EEG was ignored by most researchers. In this paper, a graph convolutional network (GCN) based on functional connectivity was proposed to decode the motor intention of four fine parts movements (shoulder, elbow, wrist, hand). First, event-related desynchronization was analyzed to reveal the differences between the four classes. Second, functional connectivity was constructed by using synchronization likelihood (SL), phase-locking value (PLV), H index (H), mutual information (MI), and weighted phase-lag index (WPLI) to acquire the electrode pairs with a difference. Subsequently, a GCN and convolutional neural networks (CNN) were performed based on functional topological structures and time points, respectively. The results demonstrated that the proposed method achieved a decoding accuracy of up to 92.81% in the four-class task. Besides, the combination of GCN and functional connectivity can promote the development of BCI.

Phase lag index-based graph attention networks for detecting driving fatigue

It is important to understand the changes in the characteristics of the brain network in the state of driving fatigue and to reveal the pattern of functional connectivity between brain regions when fatigue occurs. This paper proposes a method for the detection of driving fatigue based on electroencephalogram (EEG) signals using a phase lag index graph attention network (PLI-GAT). Phase synchronization between EEG signals is a key attribute for establishing communication links among different regions of the brain, and so, the PLI is used to construct a functional brain network reflecting the relationship between EEG signals from different channels. Multi-channel EEG time-frequency features are then modeled as graph data, and the driving fatigue monitoring model is trained using a GAT. Compared with traditional graph neural networks, the GAT applies an aggregation operation to adjacent EEG channel features through the attention mechanism. This enables the adaptive assignment of different neighbor weights, which greatly improves the expressiveness of the graph neural network model. The proposed method is validated on the publicly available SEED-VIG dataset, and the accuracy of fatigue state recognition is found to reach 85.53%. The results show that the functional connectivity among different channels is significantly enhanced in the fatigue state.

Applications of brain imaging methods in driving behaviour research

Applications of neuroimaging methods have substantially contributed to the scientific understanding of human factors during driving by providing a deeper insight into the neuro-cognitive aspects of driver brain. This has been achieved by conducting simulated (and occasionally, field) driving experiments while collecting driver brain signals of various types. Here, this sector of studies is comprehensively reviewed at both macro and micro scales. At the macro scale, bibliometric aspects of these studies are analysed. At the micro scale, different themes of neuroimaging driving behaviour research are identified and the findings within each theme are synthesised. The surveyed literature has reported on applications of four major brain imaging methods. These include Functional Magnetic Resonance Imaging (fMRI), Electroencephalography (EEG), Functional Near-Infrared Spectroscopy (fNIRS) and Magnetoencephalography (MEG), with the first two being the most common methods in this domain. While collecting driver fMRI signal has been particularly instrumental in studying neural correlates of intoxicated driving (e.g. alcohol or cannabis) or distracted driving, the EEG method has been predominantly utilised in relation to the efforts aiming at development of automatic fatigue/drowsiness detection systems, a topic to which the literature on neuro-ergonomics of driving particularly has shown a spike of interest within the last few years. The survey also reveals that topics such as driver brain activity in semi-automated settings or neural activity of drivers with brain injuries or chronic neurological conditions have by contrast been investigated to a very limited extent. Potential topics in driving behaviour research are identified that could benefit from the adoption of neuroimaging methods in future studies. In terms of practicality, while fMRI and MEG experiments have proven rather invasive and technologically challenging for adoption in driving behaviour research, EEG and fNIRS applications have been more diverse. They have even been tested beyond simulated driving settings, in field driving experiments. Advantages and limitations of each of these four neuroimaging methods in the context of driving behaviour experiments are outlined in the paper.