Narrow Results

This study aims to classify sleep stages using electroencephalogram (EEG) signals to investigate the potential impact of entrepreneurial stress on the sleep quality of entrepreneurial students. Due to high stress and irregular schedules, entrepreneurial students are prone to sleep issues, making accurate detection and analysis of their sleep states highly significant in practice. This study proposes a lightweight deep learning model that combines Depthwise Separable Convolution (DSC) with a Bidirectional Long Short-Term Memory (Bi-LSTM) network to capture the spatiotemporal features of EEG signals. DSC effectively extracts spatial features from EEG data, reducing model complexity and computational cost, while Bi-LSTM enhances the model’s ability to capture temporal dependencies, thereby improving the identification of different sleep stages (W, N1, N2, N3, and REM). This approach balances efficiency and accuracy, making it suitable for environments with limited computational resources. Experiments were conducted on both the public Sleep-EDF dataset and a custom dataset collected from entrepreneurial students. The results show that the model achieved a sleep stage classification accuracy of 93.59% on the Sleep-EDF dataset and 88.98% on the custom entrepreneurial student dataset, demonstrating strong generalization and robustness. Additionally, the model maintained high F1-scores across different sleep stages, with particularly outstanding performance in the classification of N2 and REM stages. This study provides an efficient and interpretable tool for monitoring the sleep health of entrepreneurial students, contributing to further understanding of the relationship between sleep and entrepreneurial psychological states. It offers scientific support for enhancing the health management and learning efficiency of entrepreneurial students.

Neuromarketing is a blooming interdisciplinary field that tries to understand the biology of consumer behavior by combining neuroscience with marketing. This technique can be used to grasp consumers’ hidden choices, intentions and decisions by analyzing their physiological and brain signals. Electroencephalography (EEG) is one of the popular neuroimaging techniques to capture and record the neural activity of the brain. Numerous research projections have been made in this field to achieve better results. Earlier approaches did not prioritize effective EEG signal preprocessing and classification methods. This paper presents a model to recognize consumer preferences by analyzing and classifying EEG signals. In this model, EEG signals are decomposed into many subbands using wavelet transform. An enhanced wavelet thresholding method is proposed to eliminate noise from subbands. Several wavelet features are computed from each subband and then fed as input to classifiers. Finally, three different machine learning classifiers are used to classify the signal between like and dislike. The classifiers are K-Nearest Neighbor (KNN), Multilayer Perceptron (MLP) and Support Vector Machine (SVM). EEG signals from 25 people are collected to verify the developed system’s performance. The effectiveness of the developed method with different classifiers is validated by varying brain lobe features and band features. In comparison to other classifiers like KNN and MLP, the designed system with the SVM classifier performs better and achieves an accuracy of 98.21%. The experimental findings for the developed system suggest that research in this area has the potential to alter and enhance marketing tactics for the benefit of both manufacturers and consumers, ultimately leading to a mutually beneficial outcome.

The diagnosis and quantification of Multiple Sclerosis (MS) have typically depended on skilled doctors recognizing visual patterns, such as Magnetic Resonance Imaging (MRI) and Electroencephalography (EEG), which resulted in a costly, time-consuming and non-reproducible process. The application of Machine Learning (ML) in MS diagnosis has been getting a lot of attention in the last few years due to the volume of scientific data, the heterogeneity of disease courses, and the variety of diagnostic methods. The EEG has the capability to detect important changes in the brain’s inherent electrical activity, which are influenced by changes in the neural network connections associated with inflammatory demyelinating and neural damage characteristic of the MS. Utilizing multimodal machine learning over the clinically available data may be a contemporary strategy with amazing potential to facilitate early diagnosis. Considering recent EEG investigations as well as the accessibility to their datasets would be the initial steps in utilizing the ML in MS diagnosis. This paper provides a systematic review of the latest techniques for MS diagnostic based on PRISMA guidelines with the prospect of ML application in their investigations. The goal is to find if EEG could be considered a robust and accurate technique for MS diagnosis. In accordance with PRISMA guidelines, we consider 111 papers. In our review, 404 people are considered including 209 with MS and 195 healthy controls. As a result, we generated an updated investigation looking at the ML approaches as well as utilizing EEG as an accurate, but less often used method to help with early diagnosis of MS. We summarize, analyze, discuss, and synthesize the recently published works, current trends, and open research issues. The review also points out knowledge gaps about the necessity of validating results and addressing constraints such as limited sample number. Our investigation proves that the precision of the supervised strategies such as $k$NN and SVM is typically higher than that of the unsupervised strategies. On the other hand, by utilizing various techniques such as splitting EEG signal sub-bands, signal windowing, and identifying effective features from the data analysis approaches, we have been able to achieve significant classification accuracy higher than 99%. According to the high degree of accuracy of the results, this approach is becoming the focal point of the research works. The high diagnostic accuracy of the proposed machine learning techniques on the EEG signal analysis shows its potential capacity to become a more widespread procedure as the MS diagnostic techniques. To develop the reliability of these methods, gathering, and analyzing more EEG signals from MS patients and creating more suitable EEG protocols are essential in future studies. In the same way, for the dynamic and online analyses of the EEG signals, in-depth studies are needed to determine more effective EEG protocols and machine-learning techniques.

The biomedical field plays a pivotal role in advancing healthcare by leveraging technological innovations to enhance diagnostics and treatment strategies. In the context of neurological disorders, particularly epilepsy, automated EEG signal processing stands out as a critical facet of biomedical research. The ability to analyze and interpret vast amounts of electroencephalogram (EEG) data using sophisticated techniques, such as Continuous Wavelet Transform (CWT), contributes significantly to the timely and accurate detection of epileptic events. Automated EEG signal processing, which uses advanced algorithms and pattern recognition methods, enables the identification of subtle yet crucial patterns indicative of epileptic activity. This paper presents an in-depth exploration of epilepsy identification using the CWT on the CHB-MIT Scalp EEG database. The study uses nine complex mother wavelets from the Gaussian and Morlet families to look at 8920 EEG segments, including 197 seizure events. The performance of each wavelet in detecting epileptic convulsions within EEG signals is rigorously evaluated. Our study shows that the complex Gaussian wavelet of order 5 (cgau5) emerged as the optimal choice, with a sensitivity of 97.58% and a precision of 97.93%. To improve epilepsy detection, we introduce burst energy, a novel engineered feature. This method gets accurate information about brain activity from the CWT scalogram by detecting ictal and ictal-free EEGs at different energy levels. The use of burst energy has a significant impact on classification performance, highlighting its potential for improved accuracy in epilepsy identification. This comprehensive study contributes valuable insights into selecting appropriate wavelets and introduces an innovative feature for more effective EEG-based epilepsy detection.

Measuring the directionality of coupling between dynamical systems is one of the challenging problems in nonlinear time series analysis. We investigate the relative merit of two approaches to assess directionality, one based on phase dynamics modeling and one based on state space topography. We analyze unidirectionally coupled model systems to investigate the ability of the two approaches to detect driver-responder relationships and discuss certain problems and pitfalls. In addition we apply both approaches to the intracranial electroencephalogram (EEG) recorded from one epilepsy patient during the seizure-free interval to demonstrate the general suitability of directionality measures to reflect the pathological interaction of the epileptic focus with other brain areas.

Oscillatory phenomena in the brain activity and their synchronization are frequently studied using mathematical models and analytic tools derived from nonlinear dynamics. In many experimental situations, however, neural signals have a broadband character and if oscillatory activity is present, its dynamical origin is unknown. To cope with these problems, a framework for detecting nonlinear oscillatory activity in broadband time series is presented. First, a narrow-band oscillatory mode is extracted from a broadband background. Second, it is tested whether the extracted mode is significantly different from linearly filtered noise, modelled as a linear stochastic process possibly passed through a static nonlinear transformation. If a nonlinear oscillatory mode is positively detected, further analysis using nonlinear approaches such as the phase synchronization analysis can potentially bring new information. For linear processes, however, standard approaches such as the coherence analysis are more appropriate and provide sufficient description of underlying interactions with smaller computational effort. The method is illustrated in a numerical example and applied to analyze experimentally obtained human EEG time series from a sleeping subject.

Electroencephalogram (EEG) signals are widely used to study the activity of the brain, such as to determine sleep stages. These EEG signals are nonlinear and non-stationary in nature. It is difficult to perform sleep staging by visual interpretation and linear techniques. Thus, we use a nonlinear technique, higher order spectra (HOS), to extract hidden information in the sleep EEG signal. In this study, unique bispectrum and bicoherence plots for various sleep stages were proposed. These can be used as visual aid for various diagnostics application. A number of HOS based features were extracted from these plots during the various sleep stages (Wakefulness, Rapid Eye Movement (REM), Stage 1-4 Non-REM) and they were found to be statistically significant with p-value lower than 0.001 using ANOVA test. These features were fed to a Gaussian mixture model (GMM) classifier for automatic identification. Our results indicate that the proposed system is able to identify sleep stages with an accuracy of 88.7%.

Approximately 30% of epilepsy patients are medically intractable. Epilepsy surgery may offer cure or palliation, and neuromodulation and direct drug delivery are being developed as alternatives. Successful treatment requires correct localization of seizure onset zones and understanding surrounding functional cortex to avoid iatrogenic disability. Several neurophysiologic and imaging localization techniques have inherent individual weaknesses which can be overcome by multimodal analysis. We review common noninvasive techniques, then illustrate the value of multimodal analysis to localize seizure onset for targeted treatment.

Fully auditory Brain-computer interfaces based on the dichotic listening task (DL-BCIs) are suited for users unable to do any muscular movement, which includes gazing, exploration or coordination of their eyes looking for inputs in form of feedback, stimulation or visual support. However, one of their disadvantages, in contrast with the visual BCIs, is their lower performance that makes them not adequate in applications that require a high accuracy. To overcome this disadvantage, we employed a Bayesian approach in which the DL-BCI was modeled as a Binary phase shift keying receiver for which the accuracy can be estimated a priori as a function of the signal-to-noise ratio. The results showed the measured accuracy to match the predefined target accuracy, thus validating this model that made possible to estimate in advance the classification accuracy on a trial-by-trial basis. This constitutes a novel methodology in the design of fully auditory DL-BCIs that let us first, define the target accuracy for a specific application and second, classify when the signal-to-noise ratio guarantees that target accuracy.

We propose a complex-valued multilayer feedforward neural network classifier for decoding of phase-coded information from steady-state visual evoked potentials. To optimize the performance of the classifier we supply it with two filter-based feature selection strategies. The proposed approaches could be used for a phase-coded brain–computer interface, enabling to encode several targets using only one stimulation frequency. The proposed classifier is a multichannel one, which distinguishes our approach from the existing single-channel ones. We show that the proposed approach outperforms others in terms of accuracy and length of the data segments used for decoding. We show that the decoding based on one optimally selected channel yields an inferior performance compared to the one based on several features, which supports our argument for a multichannel approach.

Through exploiting temporal, spectral, time-frequency representations, and spatial properties of mismatch negativity (MMN) simultaneously, this study extracts a multi-domain feature of MMN mainly using non-negative tensor factorization. In our experiment, the peak amplitude of MMN between children with reading disability and children with attention deficit was not significantly different, whereas the new feature of MMN significantly discriminated the two groups of children. This is because the feature was derived from multi-domain information with significant reduction of the heterogeneous effect of datasets.

Non-negative Canonical Polyadic decomposition (NCPD) and non-negative Tucker decomposition (NTD) were compared for extracting the multi-domain feature of visual mismatch negativity (vMMN), a small event-related potential (ERP), for the cognitive research. Since signal-to-noise ratio in vMMN is low, NTD outperformed NCPD. Moreover, we proposed an approach to select the multi-domain feature of an ERP among all extracted features and discussed determination of numbers of extracted components in NCPD and NTD regarding the ERP context.

The model simulates the activity of three neural populations using a Lotka–Volterra predator–prey system and, based on neuro-anatomical and neuro-physiological recent findings, assumes that a functional thalamo-cortical gate should be crossed by 'queuing' thalamic signals and that a sleep promoting substance acts as a modulator. The resultant activity accounts for the sleep stage transitions. In accordance with sleep cycles timing, the model proves to be able to reproduce the clustering and randomness of those peculiar transient synchronized EEG patterns (TSEP) described in normal human sleep and supposed to be related to the dynamic building up of NREM sleep until its stabilization against perturbations.

This work proposes a methodology for sleep stage classification based on two main approaches: the combination of features extracted from electroencephalogram (EEG) signal by different extraction methods, and the use of stacked sequential learning to incorporate predicted information from nearby sleep stages in the final classifier. The feature extraction methods used in this work include three representative ways of extracting information from EEG signals: Hjorth features, wavelet transformation and symbolic representation. Feature selection was then used to evaluate the relevance of individual features from this set of methods. Stacked sequential learning uses a second-layer classifier to improve the classification by using previous and posterior first-layer predicted stages as additional features providing information to the model. Results show that both approaches enhance the sleep stage classification accuracy rate, thus leading to a closer approximation to the experts' opinion.

Integration of brain–computer interface (BCI) technique and assistive device is one of chief and promising applications of BCI system. With BCI technique, people with disabilities do not have to communicate with external environment through traditional and natural pathways like peripheral nerves and muscles, and could achieve it only by their brain activities. In this paper, we designed an electroencephalogram (EEG)-based wheelchair which can be steered by users' own thoughts without any other involvements. We evaluated the feasibility of BCI-based wheelchair in terms of accuracies and real-world testing. The results demonstrate that our BCI wheelchair is of good performance not only in accuracy, but also in practical running testing in a real environment. This fact implies that people can steer wheelchair only by their thoughts, and may have a potential perspective in daily application for disabled people.

Synthetic sounds, tone-beeps, vowels or syllables are typically used in the assessment of attention to auditory stimuli because they evoke a set of well-known event-related potentials, whose characteristics can be statistically contrasted. Such approach rules out the use of stimuli with non-predictable response, such as human speech. In this study we present a procedure based on the robust binary phase-shift keying (BPSK) receiver that permits the real-time detection of selective attention to human speeches in dichotic listening tasks. The goal was achieved by tagging the speeches with two barely-audible tags whose joined EEG response constitutes a reliable BPSK constellation, which can be detected by means of a BPSK receiver. The results confirmed the expected generation of the BPSK constellation by the human auditory system. Also, the bit-error rate and the information transmission rate achieved in the detection of attention fairly followed the expected curves and equations of the standard BPSK receiver. Actually, it was possible to detect attention as well as the estimation a priori of its accuracy based on the signal-to-noise ratio of the BPSK signals. This procedure, which permits the detection of the attention to human speeches, can be of interest for new potential applications, such as brain–computer interfaces, clinical assessment of the attention in real time or for entertainment.

Drug abusers typically consume not just one but several types of drugs, starting from alcohol and marijuana consumption, and then dramatically lapsing into addiction to harder drugs, such as cocaine, heroin, or amphetamine. The brain of drug abusers presents various structural and neurophysiological abnormalities, some of which may predate drug consumption onset. However, how these changes translate into modifications in functional brain connectivity is still poorly understood. To characterize functional connectivity patterns, we recorded Electroencephalogram (EEG) activity from 21 detoxified drug abusers and 20 age-matched control subjects performing a simple counting task and at rest activity. To evaluate the cortical brain connectivity network we applied the Synchronization Likelihood algorithm. The results showed that drug abusers had higher synchronization levels at low frequencies, mainly in the θ band (4–8 Hz) between frontal and posterior cortical regions. During the counting task, patients showed increased synchronization in the β (14–35 Hz), and γ (35–45 Hz) frequency bands, in fronto-posterior and interhemispheric temporal regions. Taken together 'slow-down' at rest and task-related 'over-exertion' could indicate that the brain of drug abusers is suffering from a premature form of ageing. Future studies will clarify whether this condition can be reversed following prolonged periods of abstinence.

Refractory epilepsy often has deleterious effects on an individual's health and quality of life. Early identification of patients whose seizures are refractory to antiepileptic drugs is important in considering the use of alternative treatments. Although idiopathic epilepsy is regarded as having a significantly lower risk factor of developing refractory epilepsy, still a subset of patients with idiopathic epilepsy might be refractory to medical treatment. In this study, we developed an effective method to predict the refractoriness of idiopathic epilepsy. Sixteen EEG segments from 12 well-controlled patients and 14 EEG segments from 11 refractory patients were analyzed at the time of first EEG recordings before antiepileptic drug treatment. Ten crucial EEG feature descriptors were selected for classification. Three of 10 were related to decorrelation time, and four of 10 were related to relative power of delta/gamma. There were significantly higher values in these seven feature descriptors in the well-controlled group as compared to the refractory group. On the contrary, the remaining three feature descriptors related to spectral edge frequency, kurtosis, and energy of wavelet coefficients demonstrated significantly lower values in the well-controlled group as compared to the refractory group. The analyses yielded a weighted precision rate of 94.2%, and a 93.3% recall rate. Therefore, the developed method is a useful tool in identifying the possibility of developing refractory epilepsy in patients with idiopathic epilepsy.

This paper proposes a real-time electroencephalogram (EEG)-based detection method of the potential danger during fatigue driving. To determine driver fatigue in real time, wavelet entropy with a sliding window and pulse coupled neural network (PCNN) were used to process the EEG signals in the visual area (the main information input route). To detect the fatigue danger, the neural mechanism of driver fatigue was analyzed. The functional brain networks were employed to track the fatigue impact on processing capacity of brain. The results show the overall functional connectivity of the subjects is weakened after long time driving tasks. The regularity is summarized as the fatigue convergence phenomenon. Based on the fatigue convergence phenomenon, we combined both the input and global synchronizations of brain together to calculate the residual amount of the information processing capacity of brain to obtain the dangerous points in real time. Finally, the danger detection system of the driver fatigue based on the neural mechanism was validated using accident EEG. The time distributions of the output danger points of the system have a good agreement with those of the real accident points.

Automatic seizure detection is of great significance in the monitoring and diagnosis of epilepsy. In this study, a novel method is proposed for automatic seizure detection in intracranial electroencephalogram (iEEG) recordings based on kernel collaborative representation (KCR). Firstly, the EEG recordings are divided into 4s epochs, and then wavelet decomposition with five scales is performed. After that, detail signals at scales 3, 4 and 5 are selected to be sparsely coded over the training sets using KCR. In KCR, l₂-minimization replaces l₁-minimization and the sparse coefficients are computed with regularized least square (RLS), and a kernel function is utilized to improve the separability between seizure and nonseizure signals. The reconstructed residuals of each EEG epoch associated with seizure and nonseizure training samples are compared and EEG epochs are categorized as the class that minimizes the reconstructed residual. At last, a multi-decision rule is applied to obtain the final detection decision. In total, 595 h of iEEG recordings from 21 patients with 87 seizures are employed to evaluate the system. The average sensitivity of 94.41%, specificity of 96.97%, and false detection rate of 0.26/h are achieved. The seizure detection system based on KCR yields both a high sensitivity and a low false detection rate for long-term EEG.

Current human-machine interfaces (HMIs) for users with severe disabilities often have difficulty distinguishing between intentional and inadvertent activations. Pre-movement neuro-cortical activity may aid in this elusive discrimination task but has not been exploited in HMIs. This work investigates the utility of the readiness potential (RP), a slow negative cortical potential preceding voluntary movement, for detecting the intention of self-initiated fine movements prior to their motoric realization. We recorded electroencephalography from the frontal, central, parietal and occipital lobes of 10 participants using a self-initiated switch activation protocol. Eye movement artifacts were removed by regression and the RP was detected on a single-trial basis, in a narrow frequency range (0.1–1 Hz). Common average reference was applied prior to windowed-averaging for feature extraction. Electrodes were selected according to a separability measure based on Fisher projection. Our findings demonstrate that feature fusion from an optimal number of electrodes achieves a statistically significant lower classification error than the best single classifier. Finally, voluntary fine movement intention was detected on a single-trial basis at above-chance levels approximately 396 ms before physical switch activation. These findings encourage the development of rapid-response, intention-aware HMIs for individuals with severe disabilities who struggle with executing voluntary fine motor movements.

Automatic seizure detection technology is of great significance for long-term electroencephalogram (EEG) monitoring of epilepsy patients. The aim of this work is to develop a seizure detection system with high accuracy. The proposed system was mainly based on multifractal analysis, which describes the local singular behavior of fractal objects and characterizes the multifractal structure using a continuous spectrum. Compared with computing the single fractal dimension, multifractal analysis can provide a better description on the transient behavior of EEG fractal time series during the evolvement from interictal stage to seizures. Thus both interictal EEG and ictal EEG were analyzed by multifractal formalism and their differences in the multifractal features were used to distinguish the two class of EEG and detect seizures. In the proposed detection system, eight features (α₀, α_min, α_max, Δα, f(α_min), f(α_max), Δf and R) were extracted from the multifractal spectrums of the preprocessed EEG to construct feature vectors. Subsequently, relevance vector machine (RVM) was applied for EEG patterns classification, and a series of post-processing operations were used to increase the accuracy and reduce false detections. Both epoch-based and event-based evaluation methods were performed to appraise the system's performance on the EEG recordings of 21 patients in the Freiburg database. The epoch-based sensitivity of 92.94% and specificity of 97.47% were achieved, and the proposed system obtained a sensitivity of 92.06% with a false detection rate of 0.34/h in event-based performance assessment.

Interaction between distant neuronal populations is essential for communication within the nervous system and can occur as a highly nonlinear process. To better understand the functional role of neural interactions, it is important to quantify the nonlinear connectivity in the nervous system. We introduce a general approach to measure nonlinear connectivity through phase coupling: the multi-spectral phase coherence (MSPC). Using simulated data, we compare MSPC with existing phase coupling measures, namely n : m synchronization index and bi-phase locking value. MSPC provides a system description, including (i) the order of the nonlinearity, (ii) the direction of interaction, (iii) the time delay in the system, and both (iv) harmonic and (v) intermodulation coupling beyond the second order; which are only partly revealed by other methods. We apply MSPC to analyze data from a motor control experiment, where subjects performed isotonic wrist flexions while receiving movement perturbations. MSPC between the perturbation, EEG and EMG was calculated. Our results reveal directional nonlinear connectivity in the afferent and efferent pathways, as well as the time delay $(43\pm 8\mathrm{\text{ms}})$ between the perturbation and the brain response. In conclusion, MSPC is a novel approach capable to assess high-order nonlinear interaction and timing in the nervous system.

Combining information from Electroencephalography (EEG) and Functional Magnetic Resonance Imaging (fMRI) has been a topic of increased interest recently. The main advantage of the EEG is its high temporal resolution, in the scale of milliseconds, while the main advantage of fMRI is the detection of functional activity with good spatial resolution. The advantages of each modality seem to complement each other, providing better insight in the neuronal activity of the brain. The main goal of combining information from both modalities is to increase the spatial and the temporal localization of the underlying neuronal activity captured by each modality. This paper presents a novel technique based on the combination of these two modalities (EEG, fMRI) that allow a better representation and understanding of brain activities in time. EEG is modeled as a sequence of topographies, based on the notion of microstates. Hidden Markov Models (HMMs) were used to model the temporal evolution of the topography of the average Event Related Potential (ERP). For each model the Fisher score of the sequence is calculated by taking the gradient of the trained model parameters. The Fisher score describes how this sequence deviates from the learned HMM. Canonical Partial Least Squares (CPLS) were used to decompose the two datasets and fuse the EEG and fMRI features. In order to test the effectiveness of this method, the results of this methodology were compared with the results of CPLS using the average ERP signal of a single channel. The presented methodology was able to derive components that co-vary between EEG and fMRI and present significant differences between the two tasks.

Motion sickness (MS) is a common experience of travelers. To provide insights into brain dynamics associated with MS, this study recruited 19 subjects to participate in an electroencephalogram (EEG) experiment in a virtual-reality driving environment. When riding on consecutive winding roads, subjects experienced postural instability and sensory conflict between visual and vestibular stimuli. Meanwhile, subjects rated their level of MS on a six-point scale. Independent component analysis (ICA) was used to separate the filtered EEG signals into maximally temporally independent components (ICs). Then, reduced logarithmic spectra of ICs of interest, using principal component analysis, were decomposed by ICA again to find spectrally fixed and temporally independent modulators (IMs). Results demonstrated that a higher degree of MS accompanied increased activation of alpha ($r=0.421$) and gamma ($r=0.478$) IMs across remote-independent brain processes, covering motor, parietal and occipital areas. This co-modulatory spectral change in alpha and gamma bands revealed the neurophysiological demand to regulate conflicts among multi-modal sensory systems during MS.

Complexity measures have been enormously used in schizophrenia patients to estimate brain dynamics. However, the conflicting results in terms of both increased and reduced complexity values have been reported in these studies depending on the patients’ clinical status or symptom severity or medication and age status. The objective of this study is to investigate the nonlinear brain dynamics of chronic and medicated schizophrenia patients using distinct complexity estimators. EEG data were collected from 22 relaxed eyes-closed patients and age-matched healthy controls. A single-trial EEG series of 2min was partitioned into identical epochs of 20s intervals. The EEG complexity of participants were investigated and compared using approximate entropy (ApEn), Shannon entropy (ShEn), Kolmogorov complexity (KC) and Lempel–Ziv complexity (LZC). Lower complexity values were obtained in schizophrenia patients. The most significant complexity differences between patients and controls were obtained in especially left frontal (F3) and parietal (P3) regions of the brain when all complexity measures were applied individually. Significantly, we found that KC was more sensitive for detecting EEG complexity of patients than other estimators in all investigated brain regions. Moreover, significant inter-hemispheric complexity differences were found in the frontal and parietal areas of schizophrenics’ brain. Our findings demonstrate that the utilizing of sensitive complexity estimators to analyze brain dynamics of patients might be a useful discriminative tool for diagnostic purposes. Therefore, we expect that nonlinear analysis will give us deeper understanding of schizophrenics’ brain.

Epileptic seizure detection plays an important role in the diagnosis of epilepsy and reducing the massive workload of reviewing electroencephalography (EEG) recordings. In this work, a novel algorithm is developed to detect seizures employing log-Euclidean Gaussian kernel-based sparse representation (SR) in long-term EEG recordings. Unlike the traditional SR for vector data in Euclidean space, the log-Euclidean Gaussian kernel-based SR framework is proposed for seizure detection in the space of the symmetric positive definite (SPD) matrices, which form a Riemannian manifold. Since the Riemannian manifold is nonlinear, the log-Euclidean Gaussian kernel function is applied to embed it into a reproducing kernel Hilbert space (RKHS) for performing SR. The EEG signals of all channels are divided into epochs and the SPD matrices representing EEG epochs are generated by covariance descriptors. Then, the testing samples are sparsely coded over the dictionary composed by training samples utilizing log-Euclidean Gaussian kernel-based SR. The classification of testing samples is achieved by computing the minimal reconstructed residuals. The proposed method is evaluated on the Freiburg EEG dataset of 21 patients and shows its notable performance on both epoch-based and event-based assessments. Moreover, this method handles multiple channels of EEG recordings synchronously which is more speedy and efficient than traditional seizure detection methods.

The linearly-constrained minimum-variance (LCMV) beamformer is traditionally used as a spatial filter for source localization, but here we consider its spatiotemporal extension for P300 classification. We compare two variants and show that the spatiotemporal LCMV beamformer is at par with state-of-the-art P300 classifiers, but several orders of magnitude faster in training the classifier.

Behavioral microsleeps are associated with complete disruption of responsiveness for $\sim 0.5$s to 15s. They can result in injury or death, especially in transport and military sectors. In this study, EEGs were obtained from five nonsleep-deprived healthy male subjects performing a 1h 2D tracking task. Microsleeps were detected in all subjects. Microsleep-related activities in the EEG were detected, characterized, separated from eye closure-related activity, and, via source-space-independent component analysis and power analysis, the associated sources were localized in the brain. Microsleeps were often, but not always, found to be associated with strong alpha-band spindles originating bilaterally from the anterior temporal gyri and hippocampi. Similarly, theta-related activity was identified as originating bilaterally from the frontal-orbital cortex. The alpha spindles were similar to sleep spindles in terms of frequency, duration, and amplitude-profile, indicating that microsleeps are equivalent to brief instances of Stage-2 sleep.

The proportion, number of bouts, and mean bout duration of different vigilance states (Wake, NREM, REM) are useful indices of dynamics in experimental sleep research. These metrics are estimated by first scoring state, sometimes using an algorithm, based on electrophysiological measurements such as the electroencephalogram (EEG) and electromyogram (EMG), and computing their values from the score sequence. Isolated errors in the scores can lead to large discrepancies in the estimated sleep metrics. But most algorithms score sleep by classifying the state from EEG/EMG features independently in each time epoch without considering the dynamics across epochs, which could provide contextual information. The objective here is to improve estimation of sleep metrics by fitting a probabilistic dynamical model to mouse EEG/EMG data and then predicting the metrics from the model parameters. Hidden Markov models (HMMs) with multivariate Gaussian observations and Markov state transitions were fitted to unlabeled 24-h EEG/EMG feature time series from 20 mice to model transitions between the latent vigilance states; a similar model with unbiased transition probabilities served as a reference. Sleep metrics predicted from the HMM parameters did not deviate significantly from manual estimates except for rapid eye movement sleep (REM) ($p<0.01$; Wilcoxon signed-rank test). Changes in value from Light to Dark conditions correlated well with manually estimated differences (Spearman’s rho 0.43–0.84) except for REM. HMMs also scored vigilance state with over 90% accuracy. HMMs of EEG/EMG features can therefore characterize sleep dynamics from EEG/EMG measurements, a prerequisite for characterizing the effects of perturbation in sleep monitoring and control applications.

Research has indicated that fatigue is a critical factor in cognitive lapses because it negatively affects an individual’s internal state, which is then manifested physiologically. This study explores neurophysiological changes, measured by electroencephalogram (EEG), due to fatigue. This study further demonstrates the feasibility of an online closed-loop EEG-based fatigue detection and mitigation system that detects physiological change and can thereby prevent fatigue-related cognitive lapses. More importantly, this work compares the efficacy of fatigue detection and mitigation between the EEG-based and a nonEEG-based random method. Twelve healthy subjects participated in a sustained-attention driving experiment. Each participant’s EEG signal was monitored continuously and a warning was delivered in real-time to participants once the EEG signature of fatigue was detected. Study results indicate suppression of the alpha- and theta-power of an occipital component and improved behavioral performance following a warning signal; these findings are in line with those in previous studies. However, study results also showed reduced warning efficacy (i.e. increased response times (RTs) to lane deviations) accompanied by increased alpha-power due to the fluctuation of warnings over time. Furthermore, a comparison of EEG-based and nonEEG-based random approaches clearly demonstrated the necessity of adaptive fatigue-mitigation systems, based on a subject’s cognitive level, to deliver warnings. Analytical results clearly demonstrate and validate the efficacy of this online closed-loop EEG-based fatigue detection and mitigation mechanism to identify cognitive lapses that may lead to catastrophic incidents in countless operational environments.

Nodes in large-scale epileptic networks that are crucial for seizure facilitation and termination can be regarded as potential targets for individualized focal therapies. Graph-theoretical approaches based on centrality concepts can help to identify such important nodes, however, they may be influenced by the way networks are derived from empirical data. Here we investigate evolving functional epileptic brain networks during 82 focal seizures with different anatomical onset locations that we derive from multichannel intracranial electroencephalographic recordings from 51 patients. We demonstrate how the various methodological steps (from the recording montage via node and link inference to the assessment of node centralities) affect importance estimation and discuss their impact on the interpretability of findings in the context of pathophysiological aspects of seizure dynamics.

We present a novel synergistic methodology for the spatio-temporal analysis of single Electroencephalogram (EEG) trials. This new methodology is based on the novel synergy of Local Global Graph (LG graph) to characterize define the structural features of the EEG topography as a global descriptor for robust comparison of dominant topographies (microstates) and Hidden Markov Models (HMM) to model the topographic sequence in a unique way. In particular, the LG graph descriptor defines similarity and distance measures that can be successfully used for the difficult comparison of the extracted LG graphs in the presence of noise. In addition, hidden states represent periods of stationary distribution of topographies that constitute the equivalent of the microstates in the model. The transitions between the different microstates and the formed syntactic patterns can reveal differences in the processing of the input stimulus between different pathologies. We train the HMM model to learn the transitions between the different microstates and express the syntactic patterns that appear in the single trials in a compact and efficient way. We applied this methodology in single trials consisting of normal subjects and patients with Progressive Mild Cognitive Impairment (PMCI) to discriminate these two groups. The classification results show that this approach is capable to efficiently discriminate between control and Progressive MCI single trials. Results indicate that HMMs provide physiologically meaningful results that can be used in the syntactic analysis of Event Related Potentials.

A novel technique of quantitative EEG for differentiating patients with early-stage Creutzfeldt–Jakob disease (CJD) from other forms of rapidly progressive dementia (RPD) is proposed. The discrimination is based on the extraction of suitable features from the time-frequency representation of the EEG signals through continuous wavelet transform (CWT). An average measure of complexity of the EEG signal obtained by permutation entropy (PE) is also included. The dimensionality of the feature space is reduced through a multilayer processing system based on the recently emerged deep learning (DL) concept. The DL processor includes a stacked auto-encoder, trained by unsupervised learning techniques, and a classifier whose parameters are determined in a supervised way by associating the known category labels to the reduced vector of high-level features generated by the previous processing blocks. The supervised learning step is carried out by using either support vector machines (SVM) or multilayer neural networks (MLP-NN). A subset of EEG from patients suffering from Alzheimer’s Disease (AD) and healthy controls (HC) is considered for differentiating CJD patients. When fine-tuning the parameters of the global processing system by a supervised learning procedure, the proposed system is able to achieve an average accuracy of 89%, an average sensitivity of 92%, and an average specificity of 89% in differentiating CJD from RPD. Similar results are obtained for CJD versus AD and CJD versus HC.

Communication between neuronal populations is facilitated by synchronization of their oscillatory activity. Although nonlinearity has been observed in the sensorimotor system, its nonlinear connectivity has not been widely investigated yet. This study investigates nonlinear connectivity during the human stretch reflex based on neuronal synchronization. Healthy participants generated isotonic wrist flexion while receiving a periodic mechanical perturbation to the wrist. Using a novel cross-frequency phase coupling metric, we estimate directional nonlinear connectivity, including time delay, from the perturbation to brain and to muscle, as well as from brain to muscle. Nonlinear phase coupling is significantly stronger from the perturbation to the muscle than to the brain, with a shorter time delay. The time delay from the perturbation to the muscle is 33 ms, similar to the reported latency of the spinal stretch reflex at the wrist. Source localization of nonlinear phase coupling from the brain to the muscle suggests activity originating from the motor cortex, although its effect on the stretch reflex is weak. As such nonlinear phase coupling between the perturbation and muscle activity is dominated by the spinal reflex loop. This study provides new evidence of nonlinear neuronal synchronization in the stretch reflex at the wrist joint with respect to spinal and transcortical loops.

Currently, there are no developed methods to detect sharp wave transients that exist in the latent phase after hypoxia-ischemia (HI) in the electroencephalogram (EEG) in order to determine if these micro-scale transients are potential biomarkers of HI. A major issue with sharp waves in the HI-EEG is that they possess a large variability in their sharp wave profile making it difficult to build a compact ‘footprint of uncertainty’ (FOU) required for ideal performance of a Type-2 fuzzy logic system (FLS) classifier. In this paper, we develop a novel computational EEG analysis method to robustly detect sharp waves using over 30h of post occlusion HI-EEG from an equivalent, in utero, preterm fetal sheep model cohort. We demonstrate that initial wavelet transform (WT) of the sharp waves stabilizes the variation in their profile and thus permits a highly compact FOU to be built, hence, optimizing the performance of a Type-2 FLS. We demonstrate that this method leads to higher overall performance of $94\%\pm 1$ for the clinical $64\mathrm{\text{Hz}}$ sampled EEG and $97\%\pm 1$ for the high resolution $1024\mathrm{\text{Hz}}$ sampled EEG that is improved upon over conventional standard wavelet $67\%\pm 5$ and $82\%\pm 3$, respectively, and fuzzy approaches $88\%\pm 2$ and $90\%\pm 3$, respectively, when performed in isolation.

Detecting epileptic seizure from EEG signals constitutes a challenging problem of significant importance. Combining adaptive optimal kernel time-frequency representation and visibility graph, we develop a novel method for detecting epileptic seizure from EEG signals. We construct complex networks from EEG signals recorded from healthy subjects and epilepsy patients. Then we employ clustering coefficient, clustering coefficient entropy and average degree to characterize the topological structure of the networks generated from different brain states. In addition, we combine energy deviation and network measures to recognize healthy subjects and epilepsy patients, and further distinguish brain states during seizure free interval and epileptic seizures. Three different experiments are designed to evaluate the performance of our method. The results suggest that our method allows a high-accurate classification of epileptiform EEG signals.

Vagus nerve stimulation (VNS) is a widely used neuromodulation technique that is currently used or being investigated as therapy for a wide array of human diseases such as epilepsy, depression, Alzheimer’s disease, tinnitus, inflammatory diseases, pain, heart failure and many others. Here, we report a pronounced decrease in brain and core temperature during VNS in freely moving rats. Two hours of rapid cycle VNS (7s on/18s off) decreased brain temperature by around $3^{\circ }$C, while standard cycle VNS (30s on/300s off) was associated with a decrease of around $1^{\circ }$C. Rectal temperature similarly decreased by more than $3^{\circ }$C during rapid cycle VNS. The hypothermic effect triggered by VNS was further associated with a vasodilation response in the tail, which reflects an active heat release mechanism. Despite previous evidence indicating an important role of the locus coeruleus-noradrenergic system in therapeutic effects of VNS, lesioning this system with the noradrenergic neurotoxin DSP-4 did not attenuate the hypothermic effect. Since body and brain temperature affect most physiological processes, this finding is of substantial importance for interpretation of several previously published VNS studies and for the future direction of research in the field.

Sleep state development in preterm neonates can provide crucial information regarding functional brain maturation and give insight into neurological well being. However, visual labeling of sleep stages from EEG requires expertise and is very time consuming, prompting the need for an automated procedure. We present a robust method for automated detection of preterm sleep from EEG, over a wide postmenstrual age ($\mathrm{\text{PMA}}=\mathrm{\text{gestational age}}+\mathrm{\text{postnatal}}$ age) range, focusing first on Quiet Sleep (QS) as an initial marker for sleep assessment. Our algorithm, CLuster-based Adaptive Sleep Staging (CLASS), detects QS if it remains relatively more discontinuous than non-QS over PMA. CLASS was optimized on a training set of 34 recordings aged 27–42 weeks PMA, and performance then assessed on a distinct test set of 55 recordings of the same age range. Results were compared to visual QS labeling from two independent raters (with inter-rater agreement $\mathrm{\text{Kappa}}=0.93$), using Sensitivity, Specificity, Detection Factor ($\mathrm{\text{DF}}=\mathrm{\text{proportion}}$ of visual QS periods correctly detected by CLASS) and Misclassification Factor ($\mathrm{\text{MF}}=\mathrm{\text{proportion}}$ of CLASS-detected QS periods that are misclassified). CLASS performance proved optimal across recordings at 31–38 weeks (median $\mathrm{\text{DF}}=1.0$, median MF 0–0.25, median Sensitivity 0.93–1.0, and median Specificity 0.80–0.91 across this age range), with minimal misclassifications at 35–36 weeks (median $\mathrm{\text{MF}}=0$). To illustrate the potential of CLASS in facilitating clinical research, normal maturational trends over PMA were derived from CLASS-estimated QS periods, visual QS estimates, and nonstate specific periods (containing QS and non-QS) in the EEG recording. CLASS QS trends agreed with those from visual QS, with both showing stronger correlations than nonstate specific trends. This highlights the benefit of automated QS detection for exploring brain maturation.

Electroencephalography (EEG) is an important method to investigate the neurophysiological mechanism underlying epileptogenesis to identify new therapies for the treatment of epilepsy. The neurophysiologically based neural mass model (NMM) can build a bridge between signal processing and neurophysiology, which can be used as a platform to explore the neurophysiological mechanism of epileptogenesis. Most EEG signals cannot be regarded as the outputs of a single NMM with identical model parameters. The outputs of NMM are simple because the diversity of neural signals in the same NMM is ignored. To improve the simulation of EEG signals, a multiple NMM is proposed, the output of which is the linear combination of the outputs of all NMMs. The NMM number is not fixed and is minimized under the premise of guaranteeing the fitting effect. Orthogonal matching pursuit is used to solve a constrained $l_0$ norm minimization problem for NMM number and the strength of every NMM. The results showed that the NMM number was significantly lower during the ictal period than during the interictal period, and the strength of major NMMs increased. This indicates that neural masses fuse into fewer larger neural masses with greater strength. The distribution of excitatory and inhibitory strength during the ictal and interictal periods was similar, whereas the excitation/inhibition ratio was higher during the ictal period than during the interictal period.

Brain–computer interfaces (BCIs) for communication can be nonintuitive, often requiring the performance of hand motor imagery or some other conversation-irrelevant task. In this paper, electroencephalography (EEG) was used to develop two intuitive online BCIs based solely on covert speech. The goal of the first BCI was to differentiate between 10s of mental repetitions of the word “no” and an equivalent duration of unconstrained rest. The second BCI was designed to discern between 10s each of covert repetition of the words “yes” and “no”. Twelve participants used these two BCIs to answer yes or no questions. Each participant completed four sessions, comprising two offline training sessions and two online sessions, one for testing each of the BCIs. With a support vector machine and a combination of spectral and time-frequency features, an average accuracy of $75.9\%\pm 11.4$ was reached across participants in the online classification of no versus rest, with 10 out of 12 participants surpassing the chance level (60.0% for $p<0.05$). The online classification of yes versus no yielded an average accuracy of $69.3\%\pm 14.1$, with eight participants exceeding the chance level. Task-specific changes in EEG beta and gamma power in language-related brain areas tended to provide discriminatory information. To our knowledge, this is the first report of online EEG classification of covert speech. Our findings support further study of covert speech as a BCI activation task, potentially leading to the development of more intuitive BCIs for communication.

Objectives: To model cortical connections in order to characterize their oscillatory behavior and role in the generation of spontaneous electroencephalogram (EEG). Methods: We studied averaged responses to single pulse electrical stimulation (SPES) from the non-epileptogenic hemisphere of five patients assessed with intracranial EEG who became seizure free after contralateral temporal lobectomy. Second-order control system equations were modified to characterize the systems generating a given response. SPES responses were modeled as responses to a unit step input. EEG power spectrum was calculated on the 20s preceding SPES. Results: 121 channels showed responses to 32 stimulation sites. A single system could model the response in 41.3% and two systems were required in 58.7%. Peaks in the frequency response of the models tended to occur within the frequency range of most activity on the spontaneous EEG. Discrepancies were noted between activity predicted by models and activity recorded in the spontaneous EEG. These discrepancies could be explained by the existence of alpha rhythm or interictal epileptiform discharges. Conclusions: Cortical interactions shown by SPES can be described as control systems which can predict cortical oscillatory behavior. The method is unique as it describes connectivity as well as dynamic interactions.

The electroencephalogram (EEG) signal analysis is a valuable tool in the evaluation of neurological disorders, which is commonly used for the diagnosis of epileptic seizures. This paper presents a novel automatic EEG signal classification method for epileptic seizure detection. The proposed method first employs a continuous wavelet transform (CWT) method for obtaining the time-frequency images (TFI) of EEG signals. The processed EEG signals are then decomposed into five sub-band frequency components of clinical interest since these sub-band frequency components indicate much better discriminative characteristics. Both Gaussian Mixture Model (GMM) features and Gray Level Co-occurrence Matrix (GLCM) descriptors are then extracted from these sub-band TFI. Additionally, in order to improve classification accuracy, a compact feature selection method by combining the ReliefF and the support vector machine-based recursive feature elimination (RFE-SVM) algorithm is adopted to select the most discriminative feature subset, which is an input to the SVM with the radial basis function (RBF) for classifying epileptic seizure EEG signals. The experimental results from a publicly available benchmark database demonstrate that the proposed approach provides better classification accuracy than the recently proposed methods in the literature, indicating the effectiveness of the proposed method in the detection of epileptic seizures.

Automatic seizure detection is extremely important in the monitoring and diagnosis of epilepsy. The paper presents a novel method based on dictionary pair learning (DPL) for seizure detection in the long-term intracranial electroencephalogram (EEG) recordings. First, for the EEG data, wavelet filtering and differential filtering are applied, and the kernel function is performed to make the signal linearly separable. In DPL, the synthesis dictionary and analysis dictionary are learned jointly from original training samples with alternating minimization method, and sparse coefficients are obtained by using of linear projection instead of costly $l_0$-norm or $l_1$-norm optimization. At last, the reconstructed residuals associated with seizure and nonseizure sub-dictionary pairs are calculated as the decision values, and the postprocessing is performed for improving the recognition rate and reducing the false detection rate of the system. A total of 530h from 20 patients with 81 seizures were used to evaluate the system. Our proposed method has achieved an average segment-based sensitivity of 93.39%, specificity of 98.51%, and event-based sensitivity of 96.36% with false detection rate of 0.236/h.

We adopted a fusion approach that combines features from simultaneously recorded electroencephalogram (EEG) and magnetoencephalogram (MEG) signals to improve classification performances in motor imagery-based brain–computer interfaces (BCIs). We applied our approach to a group of 15 healthy subjects and found a significant classification performance enhancement as compared to standard single-modality approaches in the alpha and beta bands. Taken together, our findings demonstrate the advantage of considering multimodal approaches as complementary tools for improving the impact of noninvasive BCIs.

Functional brain network (FBN) has become very popular to analyze the interaction between cortical regions in the last decade. But researchers always spend a long time to search the best way to compute FBN for their specific studies. The purpose of this study is to detect the proficiency of operators during their mineral grinding process controlling based on FBN. To save the search time, a novel semi-data-driven method of computing functional brain connection based on stacked autoencoder (BCSAE) is proposed in this paper. This method uses stacked autoencoder (SAE) to encode the multi-channel EEG data into codes and then computes the dissimilarity between the codes from every pair of electrodes to build FBN. The highlight of this method is that the SAE has a multi-layered structure and is semi-supervised, which means it can dig deeper information and generate better features. Then an experiment was performed, the EEG of the operators were collected while they were operating and analyzed to detect their proficiency. The results show that the BCSAE method generated more number of separable features with less redundancy, and the average accuracy of classification (96.18%) is higher than that of the control methods: PLV (92.19%) and PLI (78.39%).

The development of suitable EEG-based emotion recognition systems has become a main target in the last decades for Brain Computer Interface applications (BCI). However, there are scarce algorithms and procedures for real-time classification of emotions. The present study aims to investigate the feasibility of real-time emotion recognition implementation by the selection of parameters such as the appropriate time window segmentation and target bandwidths and cortical regions. We recorded the EEG-neural activity of 24 participants while they were looking and listening to an audiovisual database composed of positive and negative emotional video clips. We tested 12 different temporal window sizes, 6 ranges of frequency bands and 60 electrodes located along the entire scalp. Our results showed a correct classification of 86.96% for positive stimuli. The correct classification for negative stimuli was a little bit less (80.88%). The best time window size, from the tested 1s to 12s segments, was 12s. Although more studies are still needed, these preliminary results provide a reliable way to develop accurate EEG-based emotion classification.

Modulation of sensorimotor rhythm (SMR) power, a rhythmic brain oscillation physiologically linked to motor imagery, is a popular Brain–Machine Interface (BMI) paradigm, but its interplay with slower cortical rhythms, also involved in movement preparation and cognitive processing, is not entirely understood. In this study, we evaluated the changes in phase and power of slow cortical activity in delta and theta bands, during a motor imagery task controlled by an SMR-based BMI system. In Experiment I, EEG of 20 right-handed healthy volunteers was recorded performing a motor-imagery task using an SMR-based BMI controlling a visual animation, and during task-free intervals. In Experiment II, 10 subjects were evaluated along five daily sessions, while BMI-controlling same visual animation, a buzzer, and a robotic hand exoskeleton. In both experiments, feedback received from the controlled device was proportional to SMR power (11–14Hz) detected by a real-time EEG-based system. Synchronization of slow EEG frequencies along the trials was evaluated using inter-trial-phase coherence (ITPC). Results: cortical oscillations of EEG in delta and theta frequencies synchronized at the onset and at the end of both active and task-free trials; ITPC was significantly modulated by feedback sensory modality received during the tasks; and ITPC synchronization progressively increased along the training. These findings suggest that phase-locking of slow rhythms and resetting by sensory afferences might be a functionally relevant mechanism in cortical control of motor function. We propose that analysis of phase synchronization of slow cortical rhythms might also improve identification of temporal edges in BMI tasks and might help to develop physiological markers for identification of context task switching and practice-related changes in brain function, with potentially important implications for design and monitoring of motor imagery-based BMI systems, an emerging tool in neurorehabilitation of stroke.

Driver fatigue is an important contributor to road accidents, and driver fatigue detection has attracted a great deal of attention on account of its significant importance. Numerous methods have been proposed to fulfill this challenging task, though, the characterization of the fatigue mechanism still, to a large extent, remains to be investigated. To address this problem, we, in this work, develop a novel Multiplex Limited Penetrable Horizontal Visibility Graph (Multiplex LPHVG) method, which allows in not only detecting fatigue driving but also probing into the brain fatigue behavior. Importantly, we use the method to construct brain networks from EEG signals recorded from different subjects performing simulated driving tasks under alert and fatigue driving states. We then employ clustering coefficient, global efficiency and characteristic path length to characterize the topological structure of the networks generated from different brain states. In addition, we combine average edge overlap with the network measures to distinguish alert and mental fatigue states. The high-accurate classification results clearly demonstrate and validate the efficacy of our multiplex LPHVG method for the fatigue detection from EEG signals. Furthermore, our findings show a significant increase of the clustering coefficient as the brain evolves from alert state to mental fatigue state, which yields novel insights into the brain behavior associated with fatigue driving.

Numerous nonepileptic paroxysmal events, such as syncope and psychogenic nonepileptic seizures, may imitate seizures and impede diagnosis. Misdiagnosis can lead to mistreatment, affecting patients’ lives considerably. Electroencephalography is commonly used for diagnosing epilepsy. Although on electroencephalograms (EEGs), epileptiform discharges (ED) specifically indicate epilepsy, only approximately 50% of patients with epilepsy have ED in their first EEG. In this study, we developed a deep convolutional neural network (ConvNet)-based classifier to distinguish EEG between patients with epilepsy without ED and controls. Overall, 25 patients with epilepsy without ED in their EEGs and 25 age-matched patients with Tourette syndrome or syncope were enrolled. Their EEGs were classified using the deep ConvNet. When the EEG data without overlapping were used, the accuracy, sensitivity, and specificity were 65.00%, 48.00%, and 82.00%, respectively. The performance measures improved when the input EEG data were augmented through overlapping. With 95% EEG data overlapping, the accuracy, sensitivity, and specificity increased to 80.00%, 70.00%, and 90.00%, respectively. The proposed method could be regarded as a pilot study to demonstrate a proof of concept of a potential diagnostic value of deep ConvNet in patients with epilepsy without ED. Further studies are needed to assist neurologists in distinguishing nonepileptic paroxysmal events from epilepsy.