Dual-Alpha: a large EEG study for dual-frequency SSVEP brain-computer interface.

BACKGROUND: The domain of brain-computer interface (BCI) technology has experienced significant expansion in recent years. However, the field continues to face a pivotal challenge due to the dearth of high-quality datasets. This lack of robust datasets serves as a bottleneck, constraining the progression of algorithmic innovations and, by extension, the maturation of the BCI field. FINDINGS: This study details the acquisition and compilation of electroencephalogram data across 3 distinct dual-frequency steady-state visual evoked potential (SSVEP) paradigms, encompassing over 100 participants. Each experimental condition featured 40 individual targets with 5 repetitions per target, culminating in a comprehensive dataset consisting of 21,000 trials of dual-frequency SSVEP recordings. We performed an exhaustive validation of the dataset through signal-to-noise ratio analyses and task-related component analysis, thereby substantiating its reliability and effectiveness for classification tasks. CONCLUSIONS: The extensive dataset presented is set to be a catalyst for the accelerated development of BCI technologies. Its significance extends beyond the BCI sphere and holds considerable promise for propelling research in psychology and neuroscience. The dataset is particularly invaluable for discerning the complex dynamics of binocular visual resource distribution.

Pattern-reversal visual evoked potentials in prosthetic vision and simulated visual reduction.

OBJECTIVE: To quantitatively evaluate visual evoked potentials (VEPs) in prosthetic vision and simulated visual reduction. METHODS AND ANALYSIS: Four blind patients implanted with the Argus II retinal prosthesis and seven sighted controls participated. VEPs were recorded with pattern-reversal stimuli (2 cycles of a horizontal square wave grating, 0.1 cycle/degree) at 1.07 reversals per second (rps) for Argus II subjects and 3.37 rps for controls. Argus II patients had both eyes patched, viewing the pattern solely through their implant. Controls viewed the pattern monocularly, either with their best-corrected vision or with simulated visual reduction (field restriction, added blur or reduced display contrast). RESULTS: VEPs recorded in Argus II patients displayed a similar shape to normal VEPs when controls viewed the pattern without simulated visual reduction. In sighted controls, adding blur significantly delayed the P100 peak time by 8.7 ms, 95% CI (0.9, 16.6). Reducing stimulus contrast to 32% and 6% of full display contrast significantly decreased P100 amplitude to 55% (37%, 82%) and 20% (13%, 31%), respectively. Restriction on the field of view had no impact on either the amplitude or the peak latency of P100. CONCLUSION: The early visual cortex in retinal prosthesis users remains responsive to retinal input, showing a similar response profile to that of sighted controls. Pattern-reversal VEP offers valuable insights for objectively evaluating artificial vision therapy systems (AVTSs) when selecting, fitting and training implant users, but the uncertainties in the exact timing and location of electrode stimulation must be considered when interpreting the results.

Genetic mechanisms for impaired synaptic plasticity in schizophrenia revealed by computational modeling.

Schizophrenia phenotypes are suggestive of impaired cortical plasticity in the disease, but the mechanisms of these deficits are unknown. Genomic association studies have implicated a large number of genes that regulate neuromodulation and plasticity, indicating that the plasticity deficits have a genetic origin. Here, we used biochemically detailed computational modeling of postsynaptic plasticity to investigate how schizophrenia-associated genes regulate long-term potentiation (LTP) and depression (LTD). We combined our model with data from postmortem RNA expression studies (CommonMind gene-expression datasets) to assess the consequences of altered expression of plasticity-regulating genes for the amplitude of LTP and LTD. Our results show that the expression alterations observed post mortem, especially those in the anterior cingulate cortex, lead to impaired protein kinase A (PKA)-pathway-mediated LTP in synapses containing GluR1 receptors. We validated these findings using a genotyped electroencephalogram (EEG) dataset where polygenic risk scores for synaptic and ion channel-encoding genes as well as modulation of visual evoked potentials were determined for 286 healthy controls. Our results provide a possible genetic mechanism for plasticity impairments in schizophrenia, which can lead to improved understanding and, ultimately, treatment of the disorder.

Neuro-ophthalmic and Neuro-otologic Evaluation in Individuals with Motion Sickness Susceptibility.

Since the physiological background of motion sickness is not entirely clear, it was aimed to examine the physiological differences in groups consisting of individuals susceptible and non-susceptible to motion sickness. Sixty subjects [motion sickness (MS) group: 33 female, 3 male; 28.8 ± 8.1 years; control group: 19 female, 5 male; 24.5 ± 4.3 years] were included in the study. Near visual acuity test on the treadmill in the presence of visual stimulation, pattern visual-evoked potentials, oculomotor tests, and computerized dynamic posturography were applied. Receiver operating characteristic analysis was performed to determine the parameter that provides the excellent discrimination between the groups. The most effective parameter in differentiating the study groups was determined as dynamic visual acuity with 77.8% sensitivity and 95.8% specificity. Significant differences were found in the vestibular (mean ± standard deviation: 0.63 ± 0.17), visual (0.77 ± 0.18), and composite scores (73.11 ± 11.89) of the patients (P=.000) in posturographic evaluation. In the visual-evoked potential examination, a significant decrease was found in the amplitude values between the P100-N145 waves in the binocular (5.0 ± 2.8, P=.002), right eye (7.6 ± 3.2, P=.009) and left eye (7.9 ± 2.9, P=.016) in the symptomatic patients. In binocular oculomotor evaluation, directional asymmetric findings were obtained. It has been shown that the most effective test parameter that distinguishes the MS susceptible and non-susceptible individuals is the dynamic visual acuity value. Based on the results of neuro-physiological tests, it was suggested that a possible visual-vestibular integration disorder in individuals susceptible to motion sickness may affect visual and vestibular performance.

A MultiModal Vigilance (MMV) dataset during RSVP and SSVEP brain-computer interface tasks.

Vigilance represents an ability to sustain prolonged attention and plays a crucial role in ensuring the reliability and optimal performance of various tasks. In this report, we describe a MultiModal Vigilance (MMV) dataset comprising seven physiological signals acquired during two Brain-Computer Interface (BCI) tasks. The BCI tasks encompass a rapid serial visual presentation (RSVP)-based target image retrieval task and a steady-state visual evoked potential (SSVEP)-based cursor-control task. The MMV dataset includes four sessions of seven physiological signals for 18 subjects, which encompasses electroencephalogram(EEG), electrooculogram (EOG), electrocardiogram (ECG), photoplethysmogram (PPG), electrodermal activity (EDA), electromyogram (EMG), and eye movement. The MMV dataset provides data from four stages: 1) raw data, 2) pre-processed data, 3) trial data, and 4) feature data that can be directly used for vigilance estimation. We believe this dataset will achieve flexible reuse and meet the various needs of researchers. And this dataset will greatly contribute to advancing research on physiological signal-based vigilance research and estimation.

Utility of Visual Evoked Potentials (VEPs) study in the evaluation of visual pathway dysfunction in diabetics without retinopathy: correlations with diabetic peripheral neuropathy and other clinical findings.

Aim and objectives: Visual dysfunction in diabetes mellitus (DM) is multifactorial and can be due to vascular disease, and metabolic abnormalities that can affect the retina, optic nerve, and visual pathways. Visual evoked potential (VEP) is an electrophysiological test that can quantify the functional integrity of the visual pathways from the retina via the optic nerves, and optic tracts to the visual cortices. In this study, we aimed to investigate the visual pathway dysfunction among diabetics without retinopathy compared with healthy controls and to look for any correlation with diabetic neuropathy, duration of diabetes, or HbA1c level. Methods: The study included 75 diabetic patients and 75 age and sex-matched controls. VEPs were recorded using the pattern reversal stimulation method on the Medtronic EMG EP machine, and P100 latency and N75-P100 amplitude were recorded in both diabetic patients and healthy controls. Results: Mean P100 latency was significantly prolonged and N75-P100 amplitude significantly reduced among diabetic cases compared to healthy controls (p < 0.001). Among diabetics with peripheral neuropathy, P100 latency was significantly prolonged and N75-P100 amplitude was significantly reduced compared to diabetics without peripheral neuropathy. A significant positive correlation of VEP P100 latency (p < 0.001) and a negative correlation with N75-P100 amplitude (p < 0.001) with duration of disease were also found. Conclusion: VEP changes are observed in diabetics before the development of retinopathy or peripheral neuropathy indicating optic pathway dysfunction, which precedes the development of these complications. Early preclinical visual pathway dysfunction can warrant taking the necessary measures to reduce diabetic complications. Abbreviations: DM = Diabetes Mellitus, VEP = Visual Evoked Potential, HbA1c = Hemoglobin A1 c, MRI = Magnetic Resonance Imaging, EEG = Electroencephalography, P100 = Positive wave peak at latency 100 ms (millisecond), N75 = Negative wave peak at latency 75 ms (millisecond), N145 = Negative wave peak at latency 145 ms (millisecond), OCT = Optical coherence tomography, PRVEP = Pattern Reversal Visual Evoked Potential, NCS = Nerve Conduction Study, SSR = Sympathetic Skin Response, IL1 = Interleukin-1, LIF = Leukemia inhibitory factor, CNTF = Ciliary neurotrophic factor, TNF alpha = Tumor necrosis factor-alpha, TGF-beta = Transforming growth factor-beta.

Portable multi-focal visual evoked potential diagnostics for multiple sclerosis/optic neuritis patients.

PURPOSE: Multiple sclerosis (MS) is a neuro-inflammatory disease affecting the central nervous system (CNS), where the immune system targets and damages the protective myelin sheath surrounding nerve fibers, inhibiting axonal signal transmission. Demyelinating optic neuritis (ON), a common MS symptom, involves optic nerve damage. We've developed NeuroVEP, a portable, wireless diagnostic system that delivers visual stimuli through a smartphone in a headset and measures evoked potentials at the visual cortex from the scalp using custom electroencephalography electrodes. METHODS: Subject vision is evaluated using a short 2.5-min full-field visual evoked potentials (ffVEP) test, followed by a 12.5-min multifocal VEP (mfVEP) test. The ffVEP evaluates the integrity of the visual pathway by analyzing the P100 component from each eye, while the mfVEP evaluates 36 individual regions of the visual field for abnormalities. Extensive signal processing, feature extraction methods, and machine learning algorithms were explored for analyzing the mfVEPs. Key metrics from patients' ffVEP results were statistically evaluated against data collected from a group of subjects with normal vision. Custom visual stimuli with simulated defects were used to validate the mfVEP results which yielded 91% accuracy of classification. RESULTS: 20 subjects, 10 controls and 10 with MS and/or ON were tested with the NeuroVEP device and a standard-of-care (SOC) VEP testing device which delivers only ffVEP stimuli. In 91% of the cases, the ffVEP results agreed between NeuroVEP and SOC device. Where available, the NeuroVEP mfVEP results were in good agreement with Humphrey Automated Perimetry visual field analysis. The lesion locations deduced from the mfVEP data were consistent with Magnetic Resonance Imaging and Optical Coherence Tomography findings. CONCLUSION: This pilot study indicates that NeuroVEP has the potential to be a reliable, portable, and objective diagnostic device for electrophysiology and visual field analysis for neuro-visual disorders.

Mowat-Wilson syndrome: Case report.

BACKGROUND: Mowat-Wilson syndrome (MWS) is a rare genetic condition resulting in multiple congenital anomalies, including facial dysmorphism, structural anomalies of the internal organs, functional disorders, and, although less commonly, ocular abnormalities. To present a child with MWS and eye abnormalities. METHODS: A 3-year-old boy was born at 37 weeks of pregnancy with dysmorphic features, neurodevelopmental disorders, genetically confirmed MWS, nystagmus, strabismus, and suspicion of congenital glaucoma. Ophthalmic examination was carried out under general anesthesia; eyeball ultrasound and electrophysiological examination (flash visual evoked potentials) were also performed. RESULTS: The examinations revealed nystagmus, a normal response of pupils to light in both eyes, and normal intraocular pressure, that is, 17 and 18 mm Hg in the right and left eye, respectively. Corneal thickness was 606 µm in the right eye and 588 µm in the left eye. Gonioscopy revealed displacement of Schwalbe line anterior to the limbus of the cornea (posterior embryotoxon). Fundus examination revealed a pink optic disk with a cup-to-disc ratio of 0.5, macular pigment regrouping, and normal blood vessels. Flash visual evoked potentials: P2 latency was normal. P2 amplitude from the left hemisphere was reduced to 50%, and P2 amplitude over the right hemisphere was normal. CONCLUSION: Children with genetically determined congenital anomalies need regular ophthalmic checkups to accurately assess the eye and determine the prospects of vision function development.

Effect of nystagmus on VEP-based objective visual acuity estimates.

In order to determine the effect of nystagmus on objective visual acuity (VA) estimates, we compared subjective (VApsych) and objective (VEP, VAVEP) VA estimates in participants with nystagmus. For this purpose, 20 participants with nystagmus (NY) caused by idiopathic infantile nystagmus, albinism, achiasma or acquired nystagmus were recruited in this study. Estimates of BCVA (best corrected visual acuity) were determined psychophysically (VApsych; FrACT, Freiburg visual acuity test) and electrophysiologically (VAVEP; EP2000) according to ISCEV (International Society of Clinical Electrophysiology of Vision) guidelines. For each participant the eye with the stronger fixation instability [Nidek microperimeter (MP-1), Nidek Instruments] was included for further analysis. VApsych vs VAVEP were compared via paired t-tests and the correlation of the difference between VApsych and VAVEP (∆VA) vs the degree of fixation instability was tested with Pearson correlation (r). We found VAVEP to be better than VApsych [by 0.12 Logarithm of the Minimum Angle of Resolution (logMAR); mean ± standard error (SE) of VAVEP vs VApsych: 0.176 ± 0.06 vs. 0.299 ± 0.06, P = 0.017] and ∆VA to be correlated linearly with the degree of fixation instability (r2 = 0.21,p = 0.048). In conclusion, on average we report a small VA overestimation, around 1 line, for VAVEP compared to VApsych in NY. This overestimation depended on the magnitude of the fixation instability. As a rule of thumb, a reduction of the fixation probability in the central 4° from 100 to 50% leads on average to a VAVEP overestimation of around 0.25 logMAR, i.e. 2.5 lines.

Rare incompatible stimuli evoke visual mismatch negativity in a flanker task.

In the flanker task, the behavioral performance for incompatible stimuli is worse in the mostly compatible (rare) condition than in the equiprobable condition. Furthermore, incompatible stimuli evoke visual mismatch negativity (VMMN) when comparing the rare and equiprobable conditions. Compatible and incompatible stimuli differ in terms of their shape and type. This study aimed to examine whether VMMN evoked by rare incompatible stimuli were associated with the shape or type of the stimulus. In a modified version of the flanker task, stimuli were manipulated by two shapes (typical or peculiar) and two types (compatible or incompatible): typical compatible stimuli (< < < < < and > > > > >), typical incompatible stimuli (> > < > > and < < > < <), peculiar compatible stimuli (+ < < < + and + > > > +), and peculiar incompatible stimuli (+ > < > + and + < > < +). In the rare condition, typical incompatible, peculiar compatible, and peculiar incompatible stimuli were presented with a probability of 10%, whereas all the stimuli were presented equally in the equiprobable condition. Right posterior negativity from 200 to 250 ms was significantly more negative in the rare condition than in the equiprobable condition for typical and peculiar incompatible stimuli; however, this difference was not observed for peculiar compatible stimuli. VMMN was significantly more negative for typical and peculiar incompatible stimuli than for peculiar compatible stimuli, and was not significantly different between typical and peculiar incompatible stimuli. These findings suggest that VMMN for incompatible stimuli is associated with the type rather than the shape of the stimulus.

Parsing evoked and induced gamma response differences in Autism: A visual evoked potential study.

OBJECTIVE: Electroencephalography (EEG) measures of visual evoked potentials (VEPs) provide a targeted approach for investigating neural circuit dynamics. This study separately analyses phase-locked (evoked) and non-phase-locked (induced) gamma responses within the VEP to comprehensively investigate circuit differences in autism. METHODS: We analyzed VEP data from 237 autistic and 114 typically developing (TD) children aged 6-11, collected through the Autism Biomarkers Consortium for Clinical Trials (ABC-CT). Evoked and induced gamma (30-90 Hz) responses were separately quantified using a wavelet-based time-frequency analysis, and group differences were evaluated using a permutation-based clustering procedure. RESULTS: Autistic children exhibited reduced evoked gamma power but increased induced gamma power compared to TD peers. Group differences in induced responses showed the most prominent effect size and remained statistically significant after excluding outliers. CONCLUSIONS: Our study corroborates recent research indicating diminished evoked gamma responses in children with autism. Additionally, we observed a pronounced increase in induced power. Building upon existing ABC-CT findings, these results highlight the potential to detect variations in gamma-related neural activity, despite the absence of significant group differences in time-domain VEP components. SIGNIFICANCE: The contrasting patterns of decreased evoked and increased induced gamma activity in autistic children suggest that a combination of different EEG metrics may provide a clearer characterization of autism-related circuitry than individual markers alone.

Stabilizing axin leads to optic nerve hypoplasia in a mouse model of autism.

Autism spectrum disorder (ASD) is a group of neurodevelopment disorders characterized by deficits in social interaction and communication, and repetitive or stereotyped behavior. Autistic children are more likely to have vision problems, and ASD is unusually common among blind people. However, the mechanisms behind the vision disorders in autism are unclear. Stabilizing WNT-targeted scaffold protein Axin2 by XAV939 during embryonic development causes overproduction of cortical neurons and leads to autistic-like behaviors in mice. In this study, we investigated the relationship between vision abnormality and autism using an XAV939-induced mouse model of autism. We found that the mice receiving XAV939 had decreased amplitude of bright light-adaptive ERG. The amplitudes and latency of flash visual evoked potential recorded from XAV939-treated mice were lower and longer, respectively than in the control mice, suggesting that XAV939 inhibits visual signal processing and conductance. Anatomically, the diameters of RGC axons were reduced when Axin2 was stabilized during the development, and the optic fibers had defective myelin sheaths and reduced oligodendrocytes. The results suggest that the WNT signaling pathway is crucial for optic nerve development. This study provides experimental evidence that conditions interfering with brain development may also lead to visual problems, which in turn might exaggerate the autistic features in humans.

It's all in the timing: delayed feedback in autism may weaken predictive mechanisms during contour integration.

Humans rely on predictive and integrative mechanisms during visual processing to efficiently resolve incomplete or ambiguous sensory signals. Although initial low-level sensory data are conveyed by feedforward connections, feedback connections are believed to shape sensory processing through automatic conveyance of statistical probabilities based on prior exposure to stimulus configurations. Individuals with autism spectrum disorder (ASD) show biases in stimulus processing toward parts rather than wholes, suggesting their sensory processing may be less shaped by statistical predictions acquired through prior exposure to global stimulus properties. Investigations of illusory contour (IC) processing in neurotypical (NT) adults have established a well-tested marker of contour integration characterized by a robust modulation of the visually evoked potential (VEP)-the IC-effect-that occurs over lateral occipital scalp during the timeframe of the visual N1 component. Converging evidence strongly supports the notion that this IC-effect indexes a signal with significant feedback contributions. Using high-density VEPs, we compared the IC-effect in 6- to 17-yr-old children with ASD (n = 32) or NT development (n = 53). Both groups of children generated an IC-effect that was equivalent in amplitude. However, the IC-effect notably onset 21 ms later in ASD, even though initial VEP afference was identical across groups. This suggests that feedforward information predominated during perceptual processing for 15% longer in ASD compared with NT children. This delay in the feedback-dependent IC-effect, in the context of known developmental differences between feedforward and feedback fibers, suggests a potential pathophysiological mechanism of visual processing in ASD, whereby ongoing stimulus processing is less shaped by visual feedback.NEW & NOTEWORTHY Children with autism often present with an atypical visual perceptual style that emphasizes parts or details over the whole. Using electroencephalography (EEG), this study identifies delays in the visual feedback from higher-order sensory brain areas to primary sensory regions. Because this type of visual feedback is thought to carry information about prior sensory experiences, individuals with autism may have difficulty efficiently using prior experience or putting together parts into a whole to help make sense of incoming new visual information. This provides empirical neural evidence to support theories of disrupted sensory perception mechanisms in autism.

Processing of visual hapaxes in picture naming task: An event-related potential study.

Object recognition and visual categorization are typically swift and seemingly effortless tasks that involve numerous underlying processes. In our investigation, we utilized a picture naming task to explore the processing of rarely encountered objects (visual hapaxes) in comparison to common objects. Our aim was to determine the stage at which these rare objects are classified as unnamable. Contrary to our expectations and in contrast to some prior research on event-related potentials (ERPs) with novel and atypical objects, no differences between conditions were observed in the late time windows corresponding to the P300 or N400 components. However, distinctive patterns between hapaxes and common objects surfaced in three early time windows, corresponding to the posterior N1 and P2 waves, as well as a widespread N2 wave. According to the ERP data, the differentiation between hapaxes and common objects occurs within the first 380 ms of the processing line, involving only limited and indirect top-down influence.

An automated ensemble approach using Harris Hawk optimization for visually evoked EEG signal classification.

Steady-state visually evoked potential is one of the active explorations in the brain-computer interface research. Electroencephalogram based brain computer interface studies have been widely applied to perceive solutions for real-world problems in the healthcare domain. The classification of externally bestowed visual stimuli of different frequencies on a human was experimented to identify the need of paralytic people. Although many classifiers are at the fingertip of machine learning technology, recent research has proven that ensemble learning is more efficacious than individual classifiers. Despite its efficiency, ensemble learning technology exhibits certain drawbacks like taking more time on selecting the optimal classifier subset. This research article utilizes the Harris Hawk Optimization algorithm to select the best classifier subset from the given set of classifiers. The objective of the research is to develop an efficient multi-classifier model for electroencephalogram signal classification. The proposed model utilizes the Boruta Feature Selection algorithm to select the prominent features for classification. Thus selected prominent features are fed into the multi-classifier subset which has been generated by the Harris Hawk Optimization algorithm. The results of the multi-classifier ensemble model are aggregated using Stacking, Bagging, Boosting, and Voting. The proposed model is evaluated against the acquired dataset and produces a promising accuracy of 96.1%, 98.7%, 91.91%, and 99.01% with the ensemble techniques respectively. The proposed model is also validated with other performance metrics such as sensitivity, specificity, and F1-Score. The experimental results show that the proposed model proves its supremacy in segregating the multi-class classification problem with high accuracy.

Human-centred physical neuromorphics with visual brain-computer interfaces.

Steady-state visual evoked potentials (SSVEPs) are widely used for brain-computer interfaces (BCIs) as they provide a stable and efficient means to connect the computer to the brain with a simple flickering light. Previous studies focused on low-density frequency division multiplexing techniques, i.e. typically employing one or two light-modulation frequencies during a single flickering light stimulation. Here we show that it is possible to encode information in SSVEPs excited by high-density frequency division multiplexing, involving hundreds of frequencies. We then demonstrate the ability to transmit entire images from the computer to the brain/EEG read-out in relatively short times. High-density frequency multiplexing also allows to implement a photonic neural network utilizing SSVEPs, that is applied to simple classification tasks and exhibits promising scalability properties by connecting multiple brains in series. Our findings open up new possibilities for the field of neural interfaces, holding potential for various applications, including assistive technologies and cognitive enhancements, to further improve human-machine interactions.

An Adaptive Hybrid Brain-Computer Interface for Hand Function Rehabilitation of Stroke Patients.

Motor imagery (MI) based brain computer interface (BCI) has been extensively studied to improve motor recovery for stroke patients by inducing neuroplasticity. However, due to the lower spatial resolution and signal-to-noise ratio (SNR) of electroencephalograph (EEG), MI based BCI system that involves decoding hand movements within the same limb remains lower classification accuracy and poorer practicality. To overcome the limitations, an adaptive hybrid BCI system combining MI and steady-state visually evoked potential (SSVEP) is developed to improve decoding accuracy while enhancing neural engagement. On the one hand, the SSVEP evoked by visual stimuli based on action-state flickering coding approach significantly improves the recognition accuracy compared to the pure MI based BCI. On the other hand, to reduce the impact of SSVEP on MI due to the dual-task interference effect, the event-related desynchronization (ERD) based neural engagement is monitored and employed for feedback in real-time to ensure the effective execution of MI tasks. Eight healthy subjects and six post-stroke patients were recruited to verify the effectiveness of the system. The results showed that the four-class gesture recognition accuracies of healthy individuals and patients could be improved to 94.37 ± 4.77 % and 79.38 ± 6.26 %, respectively. Moreover, the designed hybrid BCI could maintain the same degree of neural engagement as observed when subjects solely performed MI tasks. These phenomena demonstrated the interactivity and clinical utility of the developed system for the rehabilitation of hand function in stroke patients.

Benchmarking brain-computer interface algorithms: Riemannian approaches vs convolutional neural networks.

Objective.To date, a comprehensive comparison of Riemannian decoding methods with deep convolutional neural networks for EEG-based brain-computer interfaces remains absent from published work. We address this research gap by using MOABB, The Mother Of All BCI Benchmarks, to compare novel convolutional neural networks to state-of-the-art Riemannian approaches across a broad range of EEG datasets, including motor imagery, P300, and steady-state visual evoked potentials paradigms.Approach.We systematically evaluated the performance of convolutional neural networks, specifically EEGNet, shallow ConvNet, and deep ConvNet, against well-established Riemannian decoding methods using MOABB processing pipelines. This evaluation included within-session, cross-session, and cross-subject methods, to provide a practical analysis of model effectiveness and to find an overall solution that performs well across different experimental settings.Main results.We find no significant differences in decoding performance between convolutional neural networks and Riemannian methods for within-session, cross-session, and cross-subject analyses.Significance.The results show that, when using traditional Brain-Computer Interface paradigms, the choice between CNNs and Riemannian methods may not heavily impact decoding performances in many experimental settings. These findings provide researchers with flexibility in choosing decoding approaches based on factors such as ease of implementation, computational efficiency or individual preferences.

Filter bank temporally local multivariate synchronization index for SSVEP-based BCI.

BACKGROUND: Multivariate synchronization index (MSI) has been successfully applied for frequency detection in steady state visual evoked potential (SSVEP) based brain-computer interface (BCI) systems. However, the standard MSI algorithm and its variants cannot simultaneously take full advantage of the time-local structure and the harmonic components in SSVEP signals, which are both crucial for frequency detection performance. To overcome the limitation, we propose a novel filter bank temporally local MSI (FBTMSI) algorithm to further improve SSVEP frequency detection accuracy. The method explicitly utilizes the temporal information of signal for covariance matrix estimation and employs filter bank decomposition to exploits SSVEP-related harmonic components. RESULTS: We employed the cross-validation strategy on the public Benchmark dataset to optimize the parameters and evaluate the performance of the FBTMSI algorithm. Experimental results show that FBTMSI outperforms the standard MSI, temporally local MSI (TMSI) and filter bank driven MSI (FBMSI) algorithms across multiple experimental settings. In the case of data length of one second, the average accuracy of FBTMSI is 9.85% and 3.15% higher than that of the FBMSI and the TMSI, respectively. CONCLUSIONS: The promising results demonstrate the effectiveness of the FBTMSI algorithm for frequency recognition and show its potential in SSVEP-based BCI applications.