EEG Frequency Research Articles

EEG Functional Connectivity Differences Predict Future Conversion to Dementia in Mild Cognitive Impairment With Lewy Body or Alzheimer Disease.

Predicting which individuals may convert to dementia from mild cognitive impairment (MCI) remains difficult in clinical practice. Electroencephalography (EEG) is a widely available investigation but there is limited research exploring EEG connectivity differences in patients with MCI who convert to dementia. Participants with a diagnosis of MCI due to Alzheimer's disease (MCI-AD) or Lewy body disease (MCI-LB) underwent resting state EEG recording. They were followed up annually with a review of the clinical diagnosis (n=66). Participants with a diagnosis of dementia at year 1 or year 2 follow up were classed as converters (n=23) and those with a diagnosis of MCI at year 2 were classed as stable (n=43). We used phase lag index (PLI) to estimate functional connectivity as well as analysing dominant frequency (DF) and relative band power. The Network-based statistic (NBS) toolbox was used to assess differences in network topology. The converting group had reduced DF (U=285.5, p=0.005) and increased relative pre-alpha power (U=702, p=0.005) consistent with previous findings. PLI showed reduced average beta band synchrony in the converting group (U=311, p=0.014) as well as significant differences in alpha and beta network topology. Logistic regression models using regional beta PLI values revealed that right central to right lateral (Sens=56.5%, Spec=86.0%, -2LL=72.48, p=0.017) and left central to right lateral (Sens=47.8%, Spec=81.4%, -2LL=71.37, p=0.012) had the best classification accuracy and fit when adjusted for age and MMSE score. Patients with MCI who convert to dementia have significant differences in EEG frequency, average connectivity and network topology prior to the onset of dementia. The MCI group is clinically heterogeneous and have underlying physiological differences that may be driving the progression of cognitive symptoms. EEG connectivity could be useful to predict which patients with MCI-AD and MCI-LB convert to dementia, regardless of the neurodegenerative aetiology.

Neural mechanisms of cognitive load in Multimedia Learning: a Meta-analysis of EEG frequency Band Modulation

Neural mechanisms of cognitive load in Multimedia Learning: a Meta-analysis of EEG frequency Band Modulation

Stability of infraslow correlation structure in time-shifted intracranial EEG signals.

It is increasingly understood that the epilepsies are characterized by network pathology that can span multiple spatial and temporal scales. Recent work indicates that infraslow (<0.2Hz) envelope correlations may form a basis for distant spatial coupling in the brain. We speculated that infraslow correlation structure may be preserved even with some time lag between signals. To this end, we studied intracranial EEG (icEEG) data collected from 22 medically refractory epilepsy patients. For each patient, we selected hour-long background, awake icEEG epochs before and after antiseizure medication (ASM) taper. For each epoch, we selected 5,000 random electrode contact pairs and estimated magnitude-squared coherence (MSC) below 0.15Hz of band power time-series in the traditional EEG frequency bands. Using these same contact pairs, we shifted one signal of the pair by random durations in 15-s increments between 0 and 300s. We aggregated these data across all patients to determine how infraslow MSC varies with duration of lag. We further examined the effect of ASM taper on infraslow correlation structure. We also used surrogate data to empirically characterize MSC estimator and to set optimal parameters for estimation specifically for the study of infraslow activity. Our empirical analysis of the MSC estimator showed that hour-long segments with MSC computed using 3-min windows with 50% overlap was sufficient to capture infraslow envelope correlations while minimizing estimator bias and variance. The mean MSC decreased monotonically with increasing time lag until 105s of lag, then plateaued between 106 and 300s. Significantly nonzero infraslow envelope MSC was preserved in all frequency bands until about 1min of time lag, both pre- and post-ASM taper. We also saw a slight, but significant increase in infraslow MSC post-ASM taper, consistent with prior work. These results provide evidence for the feasibility of examining infraslow activity via its modulation of higher-frequency activity in the absence of DC-coupled recordings. The use of surrogate data also provides a general methodology for benchmarking measures used in network neuroscience studies. Finally, our study points to the clinical relevance of infraslow activity in assessing seizure risk.

Classifying the Cognitive Performance of Drivers While Talking on Hands-Free Mobile Phone Based on Innovative Sensors and Intelligent Approach

The use of mobile phones while driving is restricted to hands-free mode. But even in the hands-free mode, the use of mobile phones while driving causes cognitive distraction due to the diverted attention of the driver. By employing innovative machine-learning approaches to drivers’ physiological signals, namely electroencephalogram (EEG), heart rate (HR), and blood pressure (BP), the impact of talking on hands-free mobile phones in real time has been investigated in this study. The cognitive impact was measured using EEG, HR, and BP data. The authors developed an intelligent model that classified the cognitive performance of drivers using physiological signals that were measured while drivers were driving and reverse bay parking in real time and talking on hands-free mobile phones, considering all driver ages as a complete cohort. Participants completed two numerical tasks varying in difficulty while driving and reverse bay parking. The results show that when participants did the hard tasks, their theta and lower alpha EEG frequency bands increased and exceeded those when they did the easy tasks. The results also show that the BP and HR under phone condition were higher than the BP and HR under no-phone condition. Participants’ cognitive performance was classified using a feedforward neural network, and 97% accuracy was achieved. According to qualitative results, participants experienced significant cognitive impacts during the task completion.

Non-invasive electroencephalography in awake cats: Feasibility and application to sensory processing in chronic pain

BackgroundFeline osteoarthritis (OA) leads to chronic pain and somatosensory sensitisation. In humans, sensory exposure can modulate chronic pain. Recently, electroencephalography (EEG) revealed a specific brain signature to human OA. However, EEG pain characterisation or its modulation does not exist in OA cats, and all EEG were conducted in sedated cats, using intradermal electrodes, which could alter sensory (pain) perception. New methodCats (n=11) affected by OA were assessed using ten gold-plated surface electrodes. Sensory stimuli were presented in random orders: response to mechanical temporal summation, grapefruit scent and mono-chromatic wavelengths (500 nm-blue, 525 nm-green and 627 nm-red light). The recorded EEG was processed to identify event-related potentials (ERP) and to perform spectral analysis (z-score). ResultsThe procedure was well-tolerated. The ERPs were reported for both mechanical (F3, C3, Cz, P3, Pz) and olfactory stimuli (Cz, Pz). The main limitation was motion artifacts. Spectral analysis revealed a significant interaction between the power of EEG frequency bands and light wavelengths (p<0.001). All wavelengths considered, alpha band proportion was higher than that of delta and gamma bands (p<0.044), while the latter was lower than the beta band (p<0.016). Compared to green and red, exposure to blue light elicited distinct changes in EEG power over time (p<0.001). Comparison with existing methodThis is the first demonstration of EEG feasibility in conscious cats with surface electrodes recording brain activity while exposing them to sensory stimulations. ConclusionThe identification of ERPs and spectral patterns opens new avenues for investigating feline chronic pain and its potential modulation through sensory interventions.

2200 Association between gait speed deterioration and EEG abnormalities

Abstract Introduction Physical and cognitive decline at an older age is preceded by changes that accumulate over time until they become clinically evident difficulties. These changes, frequently overlooked by patients and health professionals, may respond better than fully established conditions to strategies designed to prevent disabilities and dependence in later life. The objective of this study was twofold: to provide further support for the need to screen for early functional changes in older adults and to look for an early association between decline in mobility and cognition. Methods A cross-sectional cohort study was conducted on 95 active functionally independent community-dwelling older adults in Havana, Cuba. We measured their gait speed at the usual pace and their cognitive status using the MMSE. A value of 0.8 m/s was used as the cut-off point to decide whether they presented a decline in gait speed. A quantitative analysis of their EEG at rest was also performed to look for an associated subclinical decline in brain function. Results Results show that 70% of the sample had a gait speed deterioration (i.e. lower than 0.8 m/s), of which 80% also had an abnormal EEG frequency composition for their age. While there was no statistically significant difference in the MMSE score between participants with a gait speed above and below the selected cut-off, individuals with MMSE scores below 25 also had a gait speed&amp;lt;0.8 m/s and an abnormal EEG frequency composition. Conclusions Our results provide further evidence of early decline in older adults – even if still independent and active - and point to the need for clinical pathways that incorporate screening and early intervention targeted at early deterioration to prolong the years of functional life in older age.

Polysomnographic features prior to dream enactment behaviors in isolated rapid eye movement sleep behavior disorder

ObjectiveThis study aimed to identify electroencephalogram correlates of dream enactment behaviors (DEBs) and elucidate their cortical dynamics in patients with isolated/idiopathic rapid eye movement (REM) sleep behavior disorder (iRBD). MethodsThis cross-sectional study included 15 patients with iRBD. Two REM sleep periods in routine polysomnography were compared: the 60 s preceding the DEBs (“pre-representative behavior” [preR]), and the 60 s with the least submental electromyogram activity (“background” [BG]). Six EEG frequency bands and electrooculogram were analyzed; power spectra, coherence and phase-locking values in four 15-s periods were examined to assess trends. These indices were also compared between preR and BG. ResultsCompared with BG, significantly higher delta power in the F3 channel and gamma power in the F4 and O2 channels were observed during preR. For functional connectivity, the widespread beta-band connectivity was significantly increased during preR than BG. ConclusionBefore notable REM sleep behaviors, uneven distributed higher EEG spectral power in both very low and high frequencies, and increased wide-range beta band functional connectivity, were observed over 60 s, suggesting cortical correlates to subsequent DEBs. SignificanceThis study may shed light on the pathological mechanisms underlies RBD through the routine vPSG analysis, leading to detection of DEBs.

The nucleus of solitary tract (NTS) synchronizes sleep-wake-state-dependent cortical activity through the parabrachial nucleus (PB) in rat

BackgroundThe medullary nucleus of solitary tract (NTS) and its afferents of vagus nerve have long been investigated in regulation of cortical activity and sleep promotion. However, the underlying neural circuit by which the NTS regulates electroencephalogram (EEG) and sleep remain unclear. As the NTS has a strong projection to the pontine arousal site, the parabrachial nucleus (PB), we proposed the NTS via the pontine parabrachial nucleus (PB) regulates cortical activity and sleep. MethodsWe bilaterally and directly stimulated the NTS neurons by chemogenetic approach and NTS terminals in the PB by optogenetic approach and examined changes in EEG and sleep in rats. ResultsOpto- and chemo-stimulation of the NTS and NTS-PB pathway altered neither sleep amounts nor patterns; however, both stimulations consistently increased EEG delta (0.5–4.0 Hz) EEG power during non-rapid-eye-movement (NREM) sleep and alpha-beta (10–30 Hz) EEG power during wake and REM sleep. ConclusionOur results indicate that the NTS via its projections to the PB synchronizes low frequency EEG during NREM sleep and high frequency EEG during wake and REM sleep. This pathway may serve the neural foundation for the vagus nerve stimulation (VNS) treating cortical disorders.

Prefrontal Oscillatory Slowing in Early-Course Schizophrenia Is Associated With Worse Cognitive Performance and Negative Symptoms: A Transcranial Magnetic Stimulation-Electroencephalography Study

BackgroundAbnormalities in dorsolateral prefrontal cortex (DLPFC) oscillations are neurophysiological signatures of schizophrenia thought to underlie its cognitive deficits. Transcranial magnetic stimulation with electroencephalography (TMS-EEG) provides a measure of cortical oscillations unaffected by sensory relay functionality and/or patients’ level of engagement, which are important confounding factors in schizophrenia. Previous TMS–EEG work showed reduced fast, gamma-range oscillations and a slowing of the main DLPFC oscillatory frequency, or natural frequency, in chronic schizophrenia. However, it is unclear whether this DLPFC natural frequency slowing is present in early-course schizophrenia (EC-SCZ) and is associated with symptom severity and cognitive dysfunction. MethodsWe applied TMS–EEG to the left DLPFC in 30 individuals with EC-SCZ and 28 healthy control participants. Goal-directed working memory performance was assessed using the AX–Continuous Performance Task. The EEG frequency with the highest cumulative power at the stimulation site, or natural frequency, was extracted. We also calculated the local relative spectral power as the average power in each frequency band divided by the broadband power. ResultsCompared with the healthy control group, the EC-SCZ group had reduced DLPFC natural frequency (p = .0000002, Cohen’s d = −2.32) and higher DLPFC beta-range relative spectral power (p = .0003, Cohen’s d = 0.77). In the EC-SCZ group, the DLPFC natural frequency was inversely associated with negative symptoms. Across all participants, the beta band relative spectral power negatively correlated with AX–Continuous Performance Task performance. ConclusionsDLPFC oscillatory slowing is an early pathophysiological biomarker of schizophrenia that is associated with its symptom severity and cognitive impairments. Future work should assess whether noninvasive neurostimulation, including repetitive TMS, can ameliorate prefrontal oscillatory deficits and related clinical functions in patients with EC-SCZ.

Evidence for a role of synchrony but not common fate in the perception of biological group movements.

Extensive research has shown that observers are able to efficiently extract summary information from groups of people. However, little is known about the cues that determine whether multiple people are represented as a social group or as independent individuals. Initial research on this topic has primarily focused on the role of static cues. Here, we instead investigate the role of dynamic cues. In two experiments with male and female human participants, we use EEG frequency tagging to investigate the influence of two fundamental Gestalt principles - synchrony and common fate - on the grouping of biological movements. In Experiment 1, we find that brain responses coupled to four point-light figures walking together are enhanced when they move in sync vs. out of sync, but only when they are presented upright. In contrast, we found no effect of movement direction (i.e., common fate). In Experiment 2, we rule out that synchrony takes precedence over common fate by replicating the null effect of movement direction while keeping synchrony constant. These results suggest that synchrony plays an important role in the processing of biological group movements. In contrast, the role of common fate is less clear and will require further research.

Automated diagnosis of schizophrenia based on spatial–temporal residual graph convolutional network

BackgroundSchizophrenia (SZ), a psychiatric disorder for which there is no precise diagnosis, has had a serious impact on the quality of human life and social activities for many years. Therefore, an advanced approach for accurate treatment is required.New methodIn this study, we provide a classification approach for SZ patients based on a spatial–temporal residual graph convolutional neural network (STRGCN). The model primarily collects spatial frequency features and temporal frequency features by spatial graph convolution and single-channel temporal convolution, respectively, and blends them both for the classification learning, in contrast to traditional approaches that only evaluate temporal frequency information in EEG and disregard spatial frequency features across brain regions.ResultsWe conducted extensive experiments on the publicly available dataset Zenodo and our own collected dataset. The classification accuracy of the two datasets on our proposed method reached 96.32% and 85.44%, respectively. In the experiment, the dataset using delta has the best classification performance in the sub-bands.Comparison with existing methodsOther methods mainly rely on deep learning models dominated by convolutional neural networks and long and short time memory networks, lacking exploration of the functional connections between channels. In contrast, the present method can treat the EEG signal as a graph and integrate and analyze the temporal frequency and spatial frequency features in the EEG signal.ConclusionWe provide an approach to not only performs better than other classic machine learning and deep learning algorithms on the dataset we used in diagnosing schizophrenia, but also understand the effects of schizophrenia on brain network features.

Chronic Caffeine Consumption, Alone or Combined with Agomelatine or Quetiapine, Reduces the Maximum EEG Peak, As Linked to Cortical Neurodegeneration, Ovarian Estrogen Receptor Alpha, and Melatonin Receptor 2

RationaleEvidence of the effects of chronic caffeine (CAFF)-containing beverages, alone or in combination with agomelatine (AGO) or quetiapine (QUET), on electroencephalography (EEG), which is relevant to cognition, epileptogenesis, and ovarian function, remains lacking. Estrogenic, adenosinergic, and melatonergic signaling is possibly linked to the dynamics of these substances.ObjectivesThe brain and ovarian effects of CAFF were compared with those of AGO + CAFF and QUET + CAFF. The implications of estrogenic, adenosinergic, and melatonergic signaling and the brain-ovarian crosstalk were investigated.MethodsAdult female rats were administered AGO (10 mg/kg), QUET (10 mg/kg), CAFF, AGO + CAFF, or QUET + CAFF, once daily for 8 weeks. EEG, estrous cycle progression, and microstructure of the brain and ovaries were examined. Brain and ovarian 17β-estradiol (E2), antimullerian hormone (AMH), estrogen receptor alpha (E2Rα), adenosine receptor 2A (A2AR), and melatonin receptor 2 (MT2R) were assessed.ResultsCAFF, alone or combined with AGO or QUET, reduced the maximum EEG peak, which was positively linked to ovarian E2Rα, negatively correlated to cortical neurodegeneration and ovarian MT2R, and associated with cystic ovaries. A large corpus luteum emerged with AGO + CAFF and QUET + CAFF, antagonizing the CAFF-mediated increased ovarian A2AR and reduced cortical E2Rα. AGO + CAFF provoked TTP delay and increased ovarian AMH, while QUET + CAFF slowed source EEG frequency to δ range and increased brain E2.ConclusionsCAFF treatment triggered brain and ovarian derangements partially antagonized with concurrent AGO or QUET administration but with no overt affection of estrus cycle progression. Estrogenic, adenosinergic, and melatonergic signaling and brain-ovarian crosstalk may explain these effects.

Overcooling in UAE homes: health issues and implications for learning efficiency

From 1990 to 2016, , air conditioning usage in the UAE increased from 25 to 125 terawatt hours, making up 70% of the country's electricity consumption. Overcooling to 18°C in homes is common, leading to health issues and reduced learning efficiency during the Covid-19 pandemic. This study uses Electroencephalograms (EEG) to examine indoor thermal environments' impact on learning efficiency. An artificial climate chamber set at 24°C or 20.5°C monitored 64 healthy males aged 21–29 during a 70-minute EEG session. Participants took a Visual Continuous Performance test and had their academic performance evaluated. Seven brain areas were analyzed for attention and power frequency. Results showed lower temperatures (20.5°C) increased EEG frequency, indicating better attention than 24°C. Statistical analysis revealed that concentration was achieved faster at lower temperatures. This study highlights the importance of optimizing indoor temperatures for improved learning efficiency and well-being.

Association between gait speed deterioration and EEG abnormalities.

Physical and cognitive decline at an older age is preceded by changes that accumulate over time until they become clinically evident difficulties. These changes, frequently overlooked by patients and health professionals, may respond better than fully established conditions to strategies designed to prevent disabilities and dependence in later life. The objective of this study was twofold; to provide further support for the need to screen for early functional changes in older adults and to look for an early association between decline in mobility and cognition. A cross-sectional cohort study was conducted on 95 active functionally independent community-dwelling older adults in Havana, Cuba. We measured their gait speed at the usual pace and the cognitive status using the MMSE. A value of 0.8 m/s was used as the cut-off point to decide whether they presented a decline in gait speed. A quantitative analysis of their EEG at rest was also performed to look for an associated subclinical decline in brain function. Results show that 70% of the sample had a gait speed deterioration (i.e., lower than 0.8 m/s), of which 80% also had an abnormal EEG frequency composition for their age. While there was no statistically significant difference in the MMSE score between participants with a gait speed above and below the selected cut-off, individuals with MMSE scores below 25 also had a gait speed<0.8 m/s and an abnormal EEG frequency composition. Our results provide further evidence of early decline in older adults-even if still independent and active-and point to the need for clinical pathways that incorporate screening and early intervention targeted at early deterioration to prolong the years of functional life in older age.

Small World derived index to distinguish Alzheimer’s type dementia and healthy subjects

Abstract Background This article introduces a novel index aimed at uncovering specific brain connectivity patterns associated with Alzheimer's disease (AD), defined according to neuropsychological patterns. Methods Electroencephalographic (EEG) recordings of 370 people, including 170 healthy subjects and 200 mild-AD patients, were acquired in different clinical centres using different acquisition equipment by harmonising acquisition settings. The study employed a new derived Small World (SW) index, SWcomb, that serves as a comprehensive metric designed to integrate the seven SW parameters, computed across the typical EEG frequency bands. The objective is to create a unified index that effectively distinguishes individuals with a neuropsychological pattern compatible with AD from healthy ones. Results Results showed that the healthy group exhibited the lowest SWcomb values, while the AD group displayed the highest SWcomb ones. Conclusions These findings suggest that SWcomb index represents an easy-to-perform, low-cost, widely available and non-invasive biomarker for distinguishing between healthy individuals and AD patients.

GABAergic neurons of anterior thalamic reticular nucleus regulate states of consciousness in propofol- and isoflurane-mediated general anesthesia.

The thalamus system plays critical roles in the regulation of reversible unconsciousness induced by general anesthetics, especially the arousal stage of general anesthesia (GA). But the function of thalamus in GA-induced loss of consciousness (LOC) is little known. The thalamic reticular nucleus (TRN) is the only GABAergic neurons-composed nucleus in the thalamus, which is composed of parvalbumin (PV) and somatostatin (SST)-expressing GABAergic neurons. The anterior sector of TRN (aTRN) is indicated to participate in the induction of anesthesia, but the roles remain unclear. This study aimed to reveal the role of the aTRN in propofol and isoflurane anesthesia. We first set up c-Fos straining to monitor the activity variation of aTRNPV and aTRNSST neurons during propofol and isoflurane anesthesia. Subsequently, optogenetic tools were utilized to activate aTRNPV and aTRNSST neurons to elucidate the roles of aTRNPV and aTRNSST neurons in propofol and isoflurane anesthesia. Electroencephalogram (EEG) recordings and behavioral tests were recorded and analyzed. Lastly, chemogenetic activation of the aTRNPV neurons was applied to confirm the function of the aTRN neurons in propofol and isoflurane anesthesia. c-Fos straining showed that both aTRNPV and aTRNSST neurons are activated during the LOC period of propofol and isoflurane anesthesia. Optogenetic activation of aTRNPV and aTRNSST neurons promoted isoflurane induction and delayed the recovery of consciousness (ROC) after propofol and isoflurane anesthesia, meanwhile chemogenetic activation of the aTRNPV neurons displayed the similar effects. Moreover, optogenetic and chemogenetic activation of the aTRN neurons resulted in the accumulated burst suppression ratio (BSR) during propofol and isoflurane GA, although they represented different effects on the power distribution of EEG frequency. Our findings reveal that the aTRN GABAergic neurons play a critical role in promoting the induction of propofol- and isoflurane-mediated GA.

Brain Responses to Real and Imagined Interpretation of Tonal Versus Atonal Music

Professional musicians have been teaching/learning/interpreting Western classical tonal music for longer than atonal music. This may be reflected in their brain plasticity and playing efficiency. To test this idea, EEG connectivity networks (EEG-CNs) of expert cellists at rest and during real and imagined musical interpretation of tonal and atonal excerpts were analyzed. Graphs and connectomes were constructed as models of EEG-CNs, using functional connectivity measurements of EEG phase synchronization in different frequency bands. Tonal and atonal interpretation resulted in a global desynchronization/dysconnectivity versus resting—irrespective of frequency bands—particularly during imagined-interpretation. During the latter, the normalized local information-transfer efficiency (NLE) of graph-EEG-CN’s small-world structure at rest increased significantly during both tonal and atonal interpretation, and more significantly during atonal-interpretation. Regional results from the graphs/connectomes supported previous findings, but only certain EEG frequency bands. During imagined-interpretation, the number of disconnected regions and subnetworks, as well as regions with higher NLE, were greater in atonal-interpretation than in tonal-interpretation for delta/theta/gamma-EEG-CNs. The opposite was true during real-interpretation, specifically limited to alpha-EEG-CN. Our EEG-CN experimental paradigm revealed perceptual differences in musicians’ brains during tonal and atonal interpretations, particularly during imagined-interpretation, potentially due to differences in cognitive roots and brain plasticity for tonal and atonal music, which may affect the musicians’ interpretation.

Seizure detection using nonlinear measures over EEG frequency bands and deep learning classifiers

Epilepsy is a brain disorder that causes patients to suffer from convulsions, which affects their behavior and way of life. Epilepsy can be detected with electroencephalograms (EEGs), which record brain neural activity. Traditional approaches for detecting epileptic seizures from an EEG signal are time-consuming and annoying. To supersede these traditional methods, a myriad of automated seizure detection frameworks based on machine learning techniques have recently been developed. Feature extraction and classification are the two essential phases for seizure detection. The classifier assigns the proper class label after feature extraction lowers the input pattern space while maintaining useful features. This paper proposes a new feature extraction method based on calculating nonlinear features from the most relevant EEG frequency bands. The EEG signal is first decomposed into smaller time segments from which a vector of nonlinear features is computed and supplied to machine learning (ML) and deep learning (DL) classifiers. Experiments on the Bonn dataset reveals an accuracy of 99.7% reached in classifying normal and ictal EEG signals; and an accuracy of 98.8% in the discrimination of ictal and interictal EEG signals. Furthermore, a performance of 100% is achieved on the Hauz Khas dataset. The classification results of the proposed approach were compared to those from published state of the art techniques. Our results are equivalent to or better than some recent studies appeared in the literature.

Residual multimodal Transformer for expression‐EEG fusion continuous emotion recognition

AbstractContinuous emotion recognition is to predict emotion states through affective information and more focus on the continuous variation of emotion. Fusion of electroencephalography (EEG) and facial expressions videos has been used in this field, while there are with some limitations in current researches, such as hand‐engineered features, simple approaches to integration. Hence, a new continuous emotion recognition model is proposed based on the fusion of EEG and facial expressions videos named residual multimodal Transformer (RMMT). Firstly, the Resnet50 and temporal convolutional network (TCN) are utilised to extract spatiotemporal features from videos, and the TCN is also applied to process the computed EEG frequency power to acquire spatiotemporal features of EEG. Then, a multimodal Transformer is used to fuse the spatiotemporal features from the two modalities. Furthermore, a residual connection is introduced to fuse shallow features with deep features which is verified to be effective for continuous emotion recognition through experiments. Inspired by knowledge distillation, the authors incorporate feature‐level loss into the loss function to further enhance the network performance. Experimental results show that the RMMT reaches a superior performance over other methods for the MAHNOB‐HCI dataset. Ablation studies on the residual connection and loss function in the RMMT demonstrate that both of them is functional.

Analyzing EEG patterns in young adults exposed to different acrophobia levels: a VR study.

The primary objective of this research is to examine acrophobia, a widely prevalent and highly severe phobia characterized by an overwhelming dread of heights, which has a substantial impact on a significant proportion of individuals worldwide. The objective of our study was to develop a real-time and precise instrument for evaluating levels of acrophobia by utilizing electroencephalogram (EEG) signals. EEG data was gathered from a sample of 18 individuals diagnosed with acrophobia. Subsequently, a range of classifiers, namely Support Vector Classifier (SVC), K-nearest Neighbors (KNN), Random Forest (RF), Decision Tree (DT), Adaboost, Linear Discriminant Analysis (LDA), Convolutional Neural Network (CNN), and Artificial Neural Network (ANN), were employed in the analysis. These methodologies encompass both machine learning (ML) and deep learning (DL) techniques. The Convolutional Neural Network (CNN) and Artificial Neural Network (ANN) models demonstrated notable efficacy. The Convolutional Neural Network (CNN) model demonstrated a training accuracy of 96% and a testing accuracy of 99%, whereas the Artificial Neural Network (ANN) model attained a training accuracy of 96% and a testing accuracy of 97%. The findings of this study highlight the effectiveness of the proposed methodology in accurately categorizing real-time degrees of acrophobia using EEG data. Further investigation using correlation matrices for each level of acrophobia showed substantial EEG frequency band connections. Beta and Gamma mean values correlated strongly, suggesting cognitive arousal and acrophobic involvement could synchronize activity. Beta and Gamma activity correlated strongly with acrophobia, especially at higher levels. The results underscore the promise of this innovative approach as a dependable and sophisticated method for evaluating acrophobia. This methodology has the potential to make a substantial contribution toward the comprehension and assessment of acrophobia, hence facilitating the development of more individualized and efficacious therapeutic interventions.