Traces of EEG-fMRI coupling reveals neurovascular dynamics on sleep inertia.

Upon emergence from sleep, individuals experience temporary hypo-vigilance and grogginess known as sleep inertia. During the transient period of vigilance recovery from prior nocturnal sleep, the neurovascular coupling (NVC) may not be static and constant as assumed by previous neuroimaging studies. Stemming from this viewpoint of sleep inertia, this study aims to probe the NVC changes as awakening time prolongs using simultaneous EEG-fMRI. The time-lagged coupling between EEG features of vigilance and BOLD-fMRI signals, in selected regions of interest, was calculated with one pre-sleep and three consecutive post-awakening resting-state measures. We found marginal changes in EEG theta/beta ratio and spectral slope across post-awakening sessions, demonstrating alterations of vigilance during sleep inertia. Time-varying EEG-fMRI coupling as awakening prolonged was evidenced by the changing time lags of the peak correlation between EEG alpha-vigilance and fMRI-thalamus, as well as EEG spectral slope and fMRI-anterior cingulate cortex. This study provides the first evidence of potential dynamicity of NVC occurred in sleep inertia and opens new avenues for non-invasive neuroimaging investigations into the neurophysiological mechanisms underlying brain state transitions.

Enhancing EEG Artifact Removal Efficiency by Introducing Dense Skip Connections to IC-U-Net.

Electroencephalographic (EEG) data is considered contaminated with various types of artifacts. Deep learning has been successfully applied to developing EEG artifact removal techniques to increase the signal-to-noise ratio (SNR) and enhance brain-computer interface performance. Recently, our research team has proposed an end-to-end UNet-based EEG artifact removal technique, IC-U-Net, which can reconstruct signals against various artifacts. However, this model suffers from being prone to overfitting with a limited training dataset size and demanding a high computational cost. To address these issues, this study attempted to leverage the architecture of UNet++ to improve the practicability of IC-U-Net by introducing dense skip connections in the encoder-decoder architecture. Results showed that this proposed model obtained superior SNR to the original model with half the number of parameters. Also, this proposed model achieved comparable convergency using a quarter of the training data size.

Abnormal heart rate variability and its application in predicting treatment efficacy in patients with chronic migraine: An exploratory study.

AIM: This study aimed to investigate the extent of autonomic nervous system dysfunction in patients with chronic migraine using heart rate variability analysis. In addition, we explored the potential association between heart rate variability and treatment outcomes in patients receiving preventive treatment. METHODS: In this cross-sectional and prospective study, we compared heart rate variability profiles in 81 preventive-naïve chronic migraine patients and 58 healthy controls. In addition, treatment responses of patients, who received a 12-week treatment with flunarizine, were assessed in relation to baseline heart rate variability. RESULTS: We observed that chronic migraine patients had a reduced heart rate variability, signifying autonomic dysfunction in comparison to healthy controls. Furthermore, patients presenting normal heart rate variability, characterized by a standard deviation exceeding 30 milliseconds in normal-to-normal RR intervals, experienced a superior response to flunarizine treatment. This improvement was exemplified by a significantly larger reduction in monthly headache days for patients with higher heart rate variability compared to those with lower heart rate variability: -9.7 (5.9) vs. -6.2 (6.0) days (p = .026). CONCLUSIONS: Autonomic dysfunction occurs in chronic migraine as evaluated by heart rate variability. A preserved function is associated with a better treatment outcome to flunarizine.Trial registration: Neurologic Signatures of Chronic Pain Disorders, NCT02747940. Registered 22 April 2016, https://clinicaltrials.gov/ct2/show/NCT02747940.

Pseudo-mutual gazing enhances interbrain synchrony during remote joint attention tasking.

INTRODUCTION: Mutual gaze enables people to share attention and increase engagement during social interactions through intentional and implicit messages. Although previous studies have explored gaze behaviors and neural mechanisms underlying in-person eye contact, the growing prevalence of remote communication has raised questions about how to establish mutual gaze remotely and how the brains of interacting individuals synchronize. METHODS: To address these questions, we conducted a study using eye trackers to create a pseudo-mutual gaze channel that mirrors the gazes of each interacting dyad on their respective remote screens. To demonstrate fluctuations in coupling across brains, we incorporated electroencephalographic hyperscanning techniques to simultaneously record the brain activity of interacting dyads engaged in a joint attention task in player-observer, collaborative, and competitive modes. RESULTS: Our results indicated that mutual gaze could improve the efficiency of joint attention activities among remote partners. Moreover, by employing the phase locking value, we could estimate interbrain synchrony (IBS) and observe low-frequency couplings in the frontal and temporal regions that varied based on the interaction mode. While dyadic gender composition significantly affected gaze patterns, it did not impact the IBS. CONCLUSION: These results provide insight into the neurological mechanisms underlying remote interaction through the pseudo-mutual gaze channel and have significant implications for developing effective online communication environments.

Interoceptive awareness: MBSR training alters information processing of salience network.

Mindfulness refers to a mental state of awareness of internal experience without judgment. Studies have suggested that each mindfulness practice may involve a unique mental state, but the underlying neurophysiological mechanisms remain unknown. Here we examined how distinct mindfulness practices after mindfulness-based intervention alter brain functionality. Specifically, we investigated the functional alterations of the salience network (SN) using functional magnetic resonance imaging (fMRI) among the two interoceptive mindfulness practices-breathing and body scan-associated with interoceptive awareness in fixed attention and shifted attention, respectively. Long-distance functional connectivity (FC) and regional homogeneity (ReHo) approaches were applied to measure distant and local neural information processing across various mental states. We hypothesized that mindful breathing and body scan would yield a unique information processing pattern in terms of long-range and local functional connectivity (FC). A total of 18 meditation-naïve participants were enrolled in an 8-week mindfulness-based stress reduction (MBSR) program alongside a waitlist control group (n = 14), with both groups undergoing multiple fMRI sessions during breathing, body scan and resting state for comparison. We demonstrated that two mindfulness practices affect both the long-distance FC SN and the local ReHo, only apparent after the MBSR program. Three functional distinctions between the mindfulness practices and the resting state are noted: (1) distant SN connectivity to occipital regions increased during the breathing practice (fixed attention), whereas the SN increased connection with the frontal/central gyri during the body scan (shifting attention); (2) local ReHo increased only in the parietal lobe during the body scan (shifting attention); (3) distant and local connections turned into a positive correlation only during the mindfulness practices after the MBSR training, indicating a global enhancement of the SN information processing during mindfulness practices. Though with limited sample size, the functional specificity of mindfulness practices offers a potential research direction on neuroimaging of mindfulness, awaiting further studies for verification.

Enhanced electroencephalography effective connectivity in frontal low-gamma band correlates of emotional regulation after mindfulness training.

Practicing mindfulness, focusing attention on the internal and external experiences occurring in the present moment with open and nonjudgement stance, can lead to the development of emotional regulation skills. Yet, the effective connectivity of brain regions during mindfulness has been largely unexplored. Studies have shown that mindfulness practice promotes functional connectivity in practitioners, potentially due to improved emotional regulation abilities and increased connectivity in the lateral prefrontal areas. To examine the changes in effective connectivity due to mindfulness training, we analyzed electroencephalogram (EEG) signals taken before and after mindfulness training, focusing on training-related effective connectivity changes in the frontal area. The mindfulness training group participated in an 8-week mindfulness-based stress reduction (MBSR) program. The control group did not take part. Regardless of the specific mindfulness practice used, low-gamma band effective connectivity increased globally after the mindfulness training. High-beta band effective connectivity increased globally only during Breathing. Moreover, relatively higher outgoing effective connectivity strength was seen during Resting and Breathing and Body-scan. By analyzing the changes in outgoing and incoming connectivity edges, both F7 and F8 exhibited strong parietal connectivity during Resting and Breathing. Multiple regression analysis revealed that the changes in effective connectivity of the right lateral prefrontal area predicted mindfulness and emotional regulation abilities. These results partially support the theory that the lateral prefrontal areas have top-down modulatory control, as these areas have high outflow effective connectivity, implying that mindfulness training cultivates better emotional regulation.

IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal.

Electroencephalography (EEG) signals are often contaminated with artifacts. It is imperative to develop a practical and reliable artifact removal method to prevent the misinterpretation of neural signals and the underperformance of brain-computer interfaces. Based on the U-Net architecture, we developed a new artifact removal model, IC-U-Net, for removing pervasive EEG artifacts and reconstructing brain signals. IC-U-Net was trained using mixtures of brain and non-brain components decomposed by independent component analysis. It uses an ensemble of loss functions to model complex signal fluctuations in EEG recordings. The effectiveness of the proposed method in recovering brain activities and removing various artifacts (e.g., eye blinks/movements, muscle activities, and line/channel noise) was demonstrated in a simulation study and four real-world EEG experiments. IC-U-Net can reconstruct a multi-channel EEG signal and is applicable to most artifact types, offering a promising end-to-end solution for automatically removing artifacts from EEG recordings. It also meets the increasing need to image natural brain dynamics in a mobile setting. The code and pre-trained IC-U-Net model are available at https://github.com/roseDwayane/AIEEG.

Mindfulness Training Associated With Resting-State Electroencephalograms Dynamics in Novice Practitioners via Mindful Breathing and Body-Scan.

Objectives: Mindfulness-based stress reduction has been proven to improve mental health and quality of life. This study examined how mindfulness training and various types of mindfulness practices altered brain activity. Methods: Specifically, the spectral powers of scalp electroencephalography of the mindfulness-based stress reduction (MBSR) group (n=17) who underwent an 8-week MBSR training-including mindful breathing and body-scan-were evaluated and compared with those of the waitlist controls (n=14). Results: Empirical results indicated that the post-intervention effect of MBSR significantly elevated the resting-state beta powers and reduced resting-state delta powers in both practices; such changes were not observed in the waitlist control. Compared with mindful breathing, body-scanning resulted in an overall decline in electroencephalograms (EEG) spectral powers at both delta and low-gamma bands among trained participants. Conclusion: Together with our preliminary data of expert mediators, the aforementioned spectral changes were salient after intervention, but mitigated along with expertise. Additionally, after receiving training, the MBSR group's mindfulness and emotion regulation levels improved significantly, which were correlated with the EEG spectral changes in the theta, alpha, and low-beta bands. The results supported that MBSR might function as a unique internal processing tool that involves increased vigilant capability and induces alterations similar to other cognitive training.

Near-zero phase-lag hyperscanning in a novel wireless EEG system.

Objective. Hyperscanning is an emerging technology that concurrently scans the neural dynamics of multiple individuals to study interpersonal interactions. In particular, hyperscanning with electroencephalography (EEG) is increasingly popular owing to its mobility and its ability to allow studying social interactions in naturalistic settings at the millisecond scale.Approach.To align multiple EEG time series with sophisticated event markers in a single time domain, a precise and unified timestamp is required for stream synchronization. This study proposes a clock-synchronized method that uses a custom-made RJ45 cable to coordinate the sampling between wireless EEG amplifiers to prevent incorrect estimation of interbrain connectivity due to asynchronous sampling. In this method, analog-to-digital converters are driven by the same sampling clock. Additionally, two clock-synchronized amplifiers leverage additional radio frequency channels to keep the counter of their receiving dongles updated, which guarantees that binding event markers received by the dongle with the EEG time series have the correct timestamp.Main results.The results of two simulation experiments and one video gaming experiment reveal that the proposed method ensures synchronous sampling in a system with multiple EEG devices, achieving near-zero phase lag and negligible amplitude difference between the signals.Significance.According to all of the signal-similarity metrics, the suggested method is a promising option for wireless EEG hyperscanning and can be utilized to precisely assess the interbrain couplings underlying social-interaction behaviors.

A Driving Performance Forecasting System Based on Brain Dynamic State Analysis Using 4-D Convolutional Neural Networks.

Vehicle accidents are the primary cause of fatalities worldwide. Most often, experiencing fatigue on the road leads to operator errors and behavioral lapses. Thus, there is a need to predict the cognitive state of drivers, particularly their fatigue level. Electroencephalography (EEG) has been demonstrated to be effective for monitoring changes in the human brain state and behavior. Thirty-seven subjects participated in this driving experiment and performed a perform lane-keeping task in a visual-reality environment. Three domains, namely, frequency, temporal, and 2-D spatial information, of the EEG channel location were comprehensively considered. A 4-D convolutional neural-network (4-D CNN) algorithm was then proposed to associate all information from the EEG signals and the changes in the human state and behavioral performance. A 4-D CNN achieves superior forecasting performance over 2-D CNN, 3-D CNN, and shallow networks. The results showed a 3.82% improvement in the root mean-square error, a 3.45% improvement in the error rate, and a 11.98% improvement in the correlation coefficient with 4-D CNN compared with 3-D CNN. The 4-D CNN algorithm extracts the significant theta and alpha activations in the frontal and posterior cingulate cortices under distinct fatigue levels. This work contributes to enhancing our understanding of deep learning methods in the analysis of EEG signals. We even envision that deep learning might serve as a bridge between translation neuroscience and further real-world applications.

Exploring the Brain Responses to Driving Fatigue Through Simultaneous EEG and fNIRS Measurements.

Fatigue is one problem with driving as it can lead to difficulties with sustaining attention, behavioral lapses, and a tendency to ignore vital information or operations. In this research, we explore multimodal physiological phenomena in response to driving fatigue through simultaneous functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) recordings with the aim of investigating the relationships between hemodynamic and electrical features and driving performance. Sixteen subjects participated in an event-related lane-deviation driving task while measuring their brain dynamics through fNIRS and EEGs. Three performance groups, classified as Optimal, Suboptimal, and Poor, were defined for comparison. From our analysis, we find that tonic variations occur before a deviation, and phasic variations occur afterward. The tonic results show an increased concentration of oxygenated hemoglobin (HbO2) and power changes in the EEG theta, alpha, and beta bands. Both dynamics are significantly correlated with deteriorated driving performance. The phasic EEG results demonstrate event-related desynchronization associated with the onset of steering vehicle in all power bands. The concentration of phasic HbO2 decreased as performance worsened. Further, the negative correlations between tonic EEG delta and alpha power and HbO2 oscillations suggest that activations in HbO2 are related to mental fatigue. In summary, combined hemodynamic and electrodynamic activities can provide complete knowledge of the brain's responses as evidence of state changes during fatigue driving.

The effects of different fatigue levels on brain-behavior relationships in driving.

BACKGROUND: In the past decade, fatigue has been regarded as one of the main factors impairing task performance and increasing behavioral lapses during driving, even leading to fatal car crashes. Although previous studies have explored the impact of acute fatigue through electroencephalography (EEG) signals, it is still unclear how different fatigue levels affect brain-behavior relationships. METHODS: A longitudinal study was performed to investigate the brain dynamics and behavioral changes in individuals under different fatigue levels by a sustained attention task. This study used questionnaires in combination with actigraphy, a noninvasive means of monitoring human physiological activity cycles, to conduct longitudinal assessment and tracking of the objective and subjective fatigue levels of recruited participants. In this study, degrees of effectiveness score (fatigue rating) are divided into three levels (normal, reduced, and high risk) by the SAFTE fatigue model. RESULTS: Results showed that those objective and subjective indicators were negatively correlated to behavioral performance. In addition, increased response times were accompanied by increased alpha and theta power in most brain regions, especially the posterior regions. In particular, the theta and alpha power dramatically increased in the high-fatigue (high-risk) group. Additionally, the alpha power of the occipital regions showed an inverted U-shaped change. CONCLUSION: Our results help to explain the inconsistent findings among existing studies, which considered the effects of only acute fatigue on driving performance while ignoring different levels of resident fatigue, and potentially lead to practical and precise biomathematical models to better predict the performance of human operators.

Neural Comodulation of Independent Brain Processes Related to Multitasking.

Distracted driving is regarded as an integrated task requiring different regions of the brain to receive sensory data, coordinate information, make decisions, and synchronize movements. In this paper, we applied an independent modulator analysis (IMA) method to temporally independent electroencephalography (EEG) components to understand how the human executive control system coordinates different brain regions to simultaneously perform multiple tasks with distractions presented in different modalities. The behavioral results showed that the reaction time (RT) in response to traffic events increased while multitasking. Moreover, the RT was longer when the distractor was presented in an auditory form versus a visual form. The IMA results showed that there were performance-related IMs coordinating different brain regions during distracted driving. The component spectral fluctuations affected by the modulators were distinct between the single- and dual-task conditions. Specifically, more modulatory weight was projected to the occipital region to address the additional distracting stimulus in both visual and auditory modality in the dual-task conditions. A comparison of modulatory weights between auditory and visual distractors showed that more modulatory weight was projected to the frontal region during the processing of the auditory distractor. This paper provides valuable insights into the temporal dynamics of attentional modulation during multitasking as well as an understanding of the underlying brain mechanisms that mediate the synchronization across brain regions and govern the allocation of attention in distracted driving.

Multi-channel EEG recordings during a sustained-attention driving task.

We describe driver behaviour and brain dynamics acquired from a 90-minute sustained-attention task in an immersive driving simulator. The data included 62 sessions of 32-channel electroencephalography (EEG) data for 27 subjects driving on a four-lane highway who were instructed to keep the car cruising in the centre of the lane. Lane-departure events were randomly induced to cause the car to drift from the original cruising lane towards the left or right lane. A complete trial included events with deviation onset, response onset, and response offset. The next trial, in which the subject was instructed to drive back to the original cruising lane, began 5-10 seconds after finishing the previous trial. We believe that this dataset will lead to the development of novel neural processing methodology that can be used to index brain cortical dynamics and detect driving fatigue and drowsiness. This publicly available dataset will be beneficial to the neuroscience and brain-computer interface communities.

Brain Electrodynamic and Hemodynamic Signatures Against Fatigue During Driving.

Fatigue is likely to be gradually cumulated in a prolonged and attention-demanding task that may adversely affect task performance. To address the brain dynamics during a driving task, this study recruited 16 subjects to participate in an event-related lane-departure driving experiment. Each subject was instructed to maintain attention and task performance throughout an hour-long driving experiment. The subjects' brain electrodynamics and hemodynamics were simultaneously recorded via 32-channel electroencephalography (EEG) and 8-source/16-detector functional near-infrared spectroscopy (fNIRS). The behavior performance demonstrated that all subjects were able to promptly respond to lane-deviation events, even if the sign of fatigue arose in the brain, which suggests that the subjects were fighting fatigue during the driving experiment. The EEG event-related analysis showed strengthening alpha suppression in the occipital cortex, a common brain region of fatigue. Furthermore, we noted increasing oxygenated hemoglobin (HbO) of the brain to fight driving fatigue in the frontal cortex, primary motor cortex, parieto-occipital cortex and supplementary motor area. In conclusion, the increasing neural activity and cortical activations were aimed at maintaining driving performance when fatigue emerged. The electrodynamic and hemodynamic signatures of fatigue fighting contribute to our understanding of the brain dynamics of driving fatigue and address driving safety issues through the maintenance of attention and behavioral performance.

Real-Time EEG Signal Enhancement Using Canonical Correlation Analysis and Gaussian Mixture Clustering.

Electroencephalogram (EEG) signals are usually contaminated with various artifacts, such as signal associated with muscle activity, eye movement, and body motion, which have a noncerebral origin. The amplitude of such artifacts is larger than that of the electrical activity of the brain, so they mask the cortical signals of interest, resulting in biased analysis and interpretation. Several blind source separation methods have been developed to remove artifacts from the EEG recordings. However, the iterative process for measuring separation within multichannel recordings is computationally intractable. Moreover, manually excluding the artifact components requires a time-consuming offline process. This work proposes a real-time artifact removal algorithm that is based on canonical correlation analysis (CCA), feature extraction, and the Gaussian mixture model (GMM) to improve the quality of EEG signals. The CCA was used to decompose EEG signals into components followed by feature extraction to extract representative features and GMM to cluster these features into groups to recognize and remove artifacts. The feasibility of the proposed algorithm was demonstrated by effectively removing artifacts caused by blinks, head/body movement, and chewing from EEG recordings while preserving the temporal and spectral characteristics of the signals that are important to cognitive research.

Exploring resting-state EEG complexity before migraine attacks.

Objective Entropy-based approaches to understanding the temporal dynamics of complexity have revealed novel insights into various brain activities. Herein, electroencephalogram complexity before migraine attacks was examined using an inherent fuzzy entropy approach, allowing the development of an electroencephalogram-based classification model to recognize the difference between interictal and preictal phases. Methods Forty patients with migraine without aura and 40 age-matched normal control subjects were recruited, and the resting-state electroencephalogram signals of their prefrontal and occipital areas were prospectively collected. The migraine phases were defined based on the headache diary, and the preictal phase was defined as within 72 hours before a migraine attack. Results The electroencephalogram complexity of patients in the preictal phase, which resembled that of normal control subjects, was significantly higher than that of patients in the interictal phase in the prefrontal area (FDR-adjusted p < 0.05) but not in the occipital area. The measurement of test-retest reliability (n = 8) using the intra-class correlation coefficient was good with r1 = 0.73 ( p = 0.01). Furthermore, the classification model, support vector machine, showed the highest accuracy (76 ± 4%) for classifying interictal and preictal phases using the prefrontal electroencephalogram complexity. Conclusion Entropy-based analytical methods identified enhancement or "normalization" of frontal electroencephalogram complexity during the preictal phase compared with the interictal phase. This classification model, using this complexity feature, may have the potential to provide a preictal alert to migraine without aura patients.

Granger causal connectivity dissociates navigation networks that subserve allocentric and egocentric path integration.

Studies on spatial navigation demonstrate a significant role of the retrosplenial complex (RSC) in the transformation of egocentric and allocentric information into complementary spatial reference frames (SRFs). The tight anatomical connections of the RSC with a wide range of other cortical regions processing spatial information support its vital role within the human navigation network. To better understand how different areas of the navigational network interact, we investigated the dynamic causal interactions of brain regions involved in solving a virtual navigation task. EEG signals were decomposed by independent component analysis (ICA) and subsequently examined for information flow between clusters of independent components (ICs) using direct short-time directed transfer function (sdDTF). The results revealed information flow between the anterior cingulate cortex and the left prefrontal cortex in the theta (4-7 Hz) frequency band and between the prefrontal, motor, parietal, and occipital cortices as well as the RSC in the alpha (8-13 Hz) frequency band. When participants prefered to use distinct reference frames (egocentric vs. allocentric) during navigation was considered, a dominant occipito-parieto-RSC network was identified in allocentric navigators. These results are in line with the assumption that the RSC, parietal, and occipital cortices are involved in transforming egocentric visual-spatial information into an allocentric reference frame. Moreover, the RSC demonstrated the strongest causal flow during changes in orientation, suggesting that this structure directly provides information on heading changes in humans.

Resting-state EEG power and coherence vary between migraine phases.

BACKGROUND: Migraine is characterized by a series of phases (inter-ictal, pre-ictal, ictal, and post-ictal). It is of great interest whether resting-state electroencephalography (EEG) is differentiable between these phases. METHODS: We compared resting-state EEG energy intensity and effective connectivity in different migraine phases using EEG power and coherence analyses in patients with migraine without aura as compared with healthy controls (HCs). EEG power and isolated effective coherence of delta (1-3.5 Hz), theta (4-7.5 Hz), alpha (8-12.5 Hz), and beta (13-30 Hz) bands were calculated in the frontal, central, temporal, parietal, and occipital regions. RESULTS: Fifty patients with episodic migraine (1-5 headache days/month) and 20 HCs completed the study. Patients were classified into inter-ictal, pre-ictal, ictal, and post-ictal phases (n = 22, 12, 8, 8, respectively), using 36-h criteria. Compared to HCs, inter-ictal and ictal patients, but not pre- or post-ictal patients, had lower EEG power and coherence, except for a higher effective connectivity in fronto-occipital network in inter-ictal patients (p < .05). Compared to data obtained from the inter-ictal group, EEG power and coherence were increased in the pre-ictal group, with the exception of a lower effective connectivity in fronto-occipital network (p < .05). Inter-ictal and ictal patients had decreased EEG power and coherence relative to HCs, which were "normalized" in the pre-ictal or post-ictal groups. CONCLUSION: Resting-state EEG power density and effective connectivity differ between migraine phases and provide an insight into the complex neurophysiology of migraine.

An EEG-Based Fatigue Detection and Mitigation System.

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.