Steady-state Visual Evoked Potential Research Articles

Enhancing SSVEP-BCI Performance Under Fatigue State Using Dynamic Stopping Strategy.

Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have emerged as a prominent technology due to their high information transfer rate, rapid calibration time, and robust signal-to-noise ratio. However, a critical challenge for practical applications is performance degradation caused by user fatigue during prolonged use. This work proposes novel methods to address this challenge by dynamically adjusting data acquisition length and updating detection models based on a fatigue-aware stopping strategy. Two 16-target SSVEP-BCIs were employed, one using low-frequency and the other using high-frequency stimulation. A self-recorded fatigue dataset from 24 subjects was utilized for extensive evaluation. A simulated online experiment demonstrated that the proposed methods outperform the conventional fixed stopping strategy in terms of classification accuracy, information transfer rate, and selection time, irrespective of stimulation frequency. These findings suggest that the proposed approach can significantly improve SSVEP-BCI performance under fatigue conditions, leading to superior performance during extended use.

A Novel Data Augmentation Approach Using Mask Encoding for Deep Learning-Based Asynchronous SSVEP-BCI.

Deep learning (DL)-based methods have been successfully employed as asynchronous classification algorithms in the steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system. However, these methods often suffer from the limited amount of electroencephalography (EEG) data, leading to overfitting. This study proposes an effective data augmentation approach called EEG mask encoding (EEG-ME) to mitigate overfitting. EEG-ME forces models to learn more robust features by masking partial EEG data, leading to enhanced generalization capabilities of models. Three different network architectures, including an architecture integrating convolutional neural networks (CNN) with Transformer (CNN-Former), time domain-based CNN (tCNN), and a lightweight architecture (EEGNet) are utilized to validate the effectiveness of EEG-ME on publicly available benchmark and BETA datasets. The results demonstrate that EEG-ME significantly enhances the average classification accuracy of various DL-based methods with different data lengths of time windows on two public datasets. Specifically, CNN-Former, tCNN, and EEGNet achieve respective improvements of 3.18%, 1.42%, and 3.06% on the benchmark dataset as well as 11.09%, 3.12%, and 2.81% on the BETA dataset, with the 1-second time window as an example. The enhanced performance of SSVEP classification with EEG-ME promotes the implementation of the asynchronous SSVEP-BCI system, leading to improved robustness and flexibility in human-machine interaction.

Improving SSVEP-BCI Performance Through Repetitive Anodal tDCS-Based Neuromodulation: Insights From Fractal EEG and Brain Functional Connectivity.

This study embarks on a comprehensive investigation of the effectiveness of repetitive transcranial direct current stimulation (tDCS)-based neuromodulation in augmenting steady-state visual evoked potential (SSVEP) brain-computer interfaces (BCIs), alongside exploring pertinent electroencephalography (EEG) biomarkers for assessing brain states and evaluating tDCS efficacy. EEG data were garnered across three distinct task modes (eyes open, eyes closed, and SSVEP stimulation) and two neuromodulation patterns (sham-tDCS and anodal-tDCS). Brain arousal and brain functional connectivity were measured by extracting features of fractal EEG and information flow gain, respectively. Anodal-tDCS led to diminished offsets and enhanced information flow gains, indicating improvements in both brain arousal and brain information transmission capacity. Additionally, anodal-tDCS markedly enhanced SSVEP-BCIs performance as evidenced by increased amplitudes and accuracies, whereas sham-tDCS exhibited lesser efficacy. This study proffers invaluable insights into the application of neuromodulation methods for bolstering BCI performance, and concurrently authenticates two potent electrophysiological markers for multifaceted characterization of brain states.

Willed Attentional Selection of Visual Features: An EEG Study.

Visual selective attention studies generally tend to apply cuing paradigms to instructively direct observers' attention to certain locations, features or objects. However, in real situations, attention in humans often flows spontaneously without any specific instructions. Recently, a concept named "willed attention" was raised in visuospatial attention, in which participants are free to make volitional attention decisions. Several ERP components during willed attention were found, along with a perspective that ongoing alpha activity may bias the subsequent attentional choice. However, it remains unclear whether similar neural mechanisms exist in feature- or object-based willed attention. Here, we included choice cues and instruct cues in a feature-based selective attention paradigm, allowing participants to freely choose or to be instructed to attend a color for the subsequent target detection task. Pre-cue ongoing alpha oscillations, cue-evoked potentials and target-related steady-state visual evoked potentials (SSVEPs) were simultaneously measured as markers of attentional processing. As expected, SSVEP responses were similarly modulated by attention between choice and instruct cue trials. Similar to the case of spatial attention, a willed-attention component (Willed Attention Component, WAC) was isolated during the cue-related choice period by comparing choice and instruct cues. However, pre-cue ongoing alpha oscillations did not predict the color choice (yellow vs blue), as indicated by the chance level decoding accuracy (50%). Overall, our results revealed both similarities and differences between spatial and feature-based willed attention, and thus extended the understanding toward the neural mechanisms of volitional attention.

Relationship of SSVEP response between flash frequency conditions.

This study delves into the application of Brain-Computer Interfaces (BCIs), focusing on exploiting Steady-State Visual Evoked Potentials (SSVEPs) as communication tools for individuals facing mobility impairments. SSVEP-BCI systems can swiftly transmit substantial volumes of information, rendering them suitable for diverse applications. However, the efficacy of SSVEP responses can be influenced by variables such as the frequency and color of visual stimuli. Through experiments involving participants equipped with electrodes on the brain's visual cortex, visual stimuli were administered at 4, 17, 25, and 40Hz, using white, red, yellow, green, and blue light sources. The results reveal that white and green stimuli evoke higher SSVEP responses at lower frequencies, with color's impact diminishing at higher frequencies. At low light intensity (1W), white and green stimuli elicit significantly higher SSVEP responses, while at high intensity (3W), responses across colors tend to equalize. Notably, due to seizure risks, red and blue lights should be used cautiously, with white and green lights preferred for SSVEP-BCI systems. This underscores the critical consideration of color and frequency in the design of effective and safe SSVEP-BCI systems, necessitating further research to optimize designs for clinical applications.

Development of an Adaptive Artifact Subspace Reconstruction Based on Hebbian/Anti-Hebbian Learning Networks for Enhancing BCI Performance.

Brain-computer interface (BCI) actively translates the brain signals into executable actions by establishing direct communication between the human brain and external devices. Recording brain activity through electroencephalography (EEG) is generally contaminated with both physiological and nonphysiological artifacts, which significantly hinders the BCI performance. Artifact subspace reconstruction (ASR) is a well-known statistical technique that automatically removes artifact components by determining the rejection threshold based on the initial reference EEG segment in multichannel EEG recordings. In real-world applications, the fixed threshold may limit the efficacy of the artifact correction, especially when the quality of the reference data is poor. This study proposes an adaptive online ASR technique by integrating the Hebbian/anti-Hebbian neural networks into the ASR algorithm, namely, principle subspace projection ASR (PSP-ASR) and principal subspace whitening ASR (PSW-ASR) that segmentwise self-organize the artifact subspace by updating the synaptic weights according to the Hebbian and anti-Hebbian learning rules. The effectiveness of the proposed algorithm is compared to the conventional ASR approaches on benchmark EEG dataset and three BCI frameworks, including steady-state visual evoked potential (SSVEP), rapid serial visual presentation (RSVP), and motor imagery (MI) by evaluating the root-mean-square error (RMSE), the signal-to-noise ratio (SNR), the Pearson correlation, and classification accuracy. The results demonstrated that the PSW-ASR algorithm effectively removed the EEG artifacts and retained the activity-specific brain signals compared to the PSP-ASR, standard ASR (Init-ASR), and moving-window ASR (MW-ASR) methods, thereby enhancing the SSVEP, RSVP, and MI BCI performances. Finally, our empirical results from the PSW-ASR algorithm suggested the choice of an aggressive cutoff range of c = 1-10 for activity-specific BCI applications and a moderate range of for the benchmark dataset and general BCI applications.

EEG-controlled tele-grasping for undefined objects.

This paper presents a teleoperation system of robot grasping for undefined objects based on a real-time EEG (Electroencephalography) measurement and shared autonomy. When grasping an undefined object in an unstructured environment, real-time human decision is necessary since fully autonomous grasping may not handle uncertain situations. The proposed system allows involvement of a wide range of human decisions throughout the entire grasping procedure, including 3D movement of the gripper, selecting proper grasping posture, and adjusting the amount of grip force. These multiple decision-making procedures of the human operator have been implemented with six flickering blocks for steady-state visually evoked potentials (SSVEP) by dividing the grasping task into predefined substeps. Each substep consists of approaching the object, selecting posture and grip force, grasping, transporting to the desired position, and releasing. The graphical user interface (GUI) displays the current substep and simple symbols beside each flickering block for quick understanding. The tele-grasping of various objects by using real-time human decisions of selecting among four possible postures and three levels of grip force has been demonstrated. This system can be adapted to other sequential EEG-controlled teleoperation tasks that require complex human decisions.

Convolutional Neural Network-Based Classification of Steady-State Visually Evoked Potentials with Limited Training Data

One approach employed in brain–computer interfaces (BCIs) involves the use of steady-state visual evoked potentials (SSVEPs). This article examines the capability of artificial intelligence, specifically convolutional neural networks (CNNs), to improve SSVEP detection in BCIs. Implementing CNNs for this task does not require specialized knowledge. The subsequent layers of the CNN extract valuable features and perform classification. Nevertheless, a significant number of training examples are typically required, which can pose challenges in the practical application of BCI. This article examines the possibility of using a CNN in combination with data augmentation to address the issue of a limited training dataset. The data augmentation method that we applied is based on the spectral analysis of the electroencephalographic signals (EEG). Initially, we constructed the spectral representation of the EEG signals. Subsequently, we generated new signals by applying random amplitude and phase variations, along with the addition of noise characterized by specific parameters. The method was tested on a set of real EEG signals containing SSVEPs, which were recorded during stimulation by light-emitting diodes (LEDs) at frequencies of 5, 6, 7, and 8 Hz. We compared the classification accuracy and information transfer rate (ITR) across various machine learning approaches using both real training data and data generated with our augmentation method. Our proposed augmentation method combined with a convolutional neural network achieved a high classification accuracy of 0.72. In contrast, the linear discriminant analysis (LDA) method resulted in an accuracy of 0.59, while the canonical correlation analysis (CCA) method yielded 0.57. Additionally, the proposed approach facilitates the training of CNNs to perform more effectively in the presence of various EEG artifacts.

Optimizing SSVEP-based BCI training through Adversarial Generative Neural Networks

Brain-computer interfaces (BCIs) based on steady-state visually evoked potential (SSVEP) use brain activity to control external devices, with applications ranging from assistive technologies to gaming. Typically, BCI systems are developed using supervised learning techniques that require labelled brain signals. However, acquiring these labelled signals can be tiring and time-consuming, especially for subjects with disabilities. In this study, we evaluated the performance impact of using synthetic brain signals to train and calibrate an SSVEP-based BCI system. Specifically, we used generative adversarial networks (GANs) to synthesize brain signals with SSVEP information, considering cases with two and four visual stimuli. Four scenarios with different proportions of real vs. synthetic brain signals were evaluated: Scenario 1 (baseline) using only real data and Scenarios 2-4 with 10%, 20% and 30% of real data replaced by synthetic data, respectively. Our results reveal that synthetic data can be used to train the BCI without a performance loss across the tested scenarios when two visual stimuli are used and with an average performance reduction compared to baseline of 7% (Scenario 2), 10,3% (Scenario 3) and 9,3% (Scenario 4) for four stimuli. Furthermore, considering each recording has duration of 2 seconds, by replacing 30% of real data with synthetic data, there is an immediate time-saving of 48 s and 96 s in the cases with two and four visual stimuli, respectively. This trade-off between accuracy and efficiency has significant implications for improving the usability and accessibility of SSVEP-based BCI, especially for assistive applications.

Filter bank second-order underdamped stochastic resonance analysis for implementing a short-term high-speed SSVEP detection

ObjectiveThe progression of brain-computer interfaces (BCIs) has been propelled by breakthroughs in neuroscience, signal processing, and machine learning, marking it as a dynamic field of study over the past few decades. Nevertheless, the nonlinear and non-stationary characteristics of steady-state visual evoked potentials (SSVEPs), coupled with the incongruity between frequently employed linear techniques and nonlinear signal attributes, resulted in the subpar performance of mainstream non-training algorithms like canonical correlation analysis (CCA), multivariate synchronization index (MSI), and filter bank CCA (FBCCA) in short-term SSVEP detection. MethodsTo tackle this problem, the novel fusions of common filter bank analysis, CCA dimensionality reduction methods, USSR models, and MSI recognition models are used in SSVEP signal recognition. ResultsUnlike conventional linear techniques such as CCA, MSI, and FBCCA, the filter bank second-order underdamped stochastic resonance (FBUSSR) analysis demonstrates superior efficacy in the detection of short-term high-speed SSVEPs. ConclusionThis research enlists 32 subjects and uses a public dataset to assess the proposed approach, and the experimental outcomes indicate that the non-training method can attain greater recognition precision and stability. Furthermore, under the conditions of the newly proposed fusion method and light stimulation, the USSR model exhibits the most optimal enhancement effect. SignificanceThe findings of this study underscore the expansive potential for the application of BCI systems in the realm of neuroscience and signal processing.

Reduced interocular suppression after inverse patching in anisometropic amblyopia.

Recent investigations observed substantial enhancements in binocular balance, visual acuity, and stereovision among older children and adults with amblyopia by patching the amblyopic eye (i.e., inverse patching) for 2 h daily over 2 months. Despite these promising findings, the precise neural mechanisms underlying inverse patching remain elusive. This study endeavors to delve deeper into the neural alterations induced by inverse patching, focusing on steady-state visual evoked potentials (SSVEPs). We specifically investigate the changes in SSVEPs following monocular deprivation of either the fellow eye or the amblyopic eye in older amblyopic children and adults. Ten participants (17.60 ± 2.03 years old; mean ± SEM), clinically diagnosed with anisometropic amblyopia, were recruited for this study. Each participant underwent a 120 min patching session on their fellow eye on the first day, followed by a similar session on their amblyopic eye on the second day. Baseline steady-state visual evoked potentials (SSVEPs) measurements were collected each day prior to patching, with post-patching SSVEPs measurements obtained immediately after the patching session. The experimental design incorporated a binocular rivalry paradigm, utilizing SSVEPs measurements. The results revealed that inverse patching induced a heightened influence on neural plasticity, manifesting in a reduction of interocular suppression from the fellow eye to the amblyopic eye. In contrast, patching the fellow eye demonstrated negligible effects on the visual cortex. Furthermore, alterations in interocular suppression subsequent to inverse patching exhibited a correlation with the visual acuity of the amblyopic eye. Inverse patching emerges as a promising therapeutic avenue for adolescents and adults grappling with severe anisometropic amblyopia that proves refractory to conventional interventions. This innovative approach exhibits the potential to induce more robust neural plasticity within the visual cortex, thereby modulating neural interactions more effectively than traditional amblyopia treatments.

Time-frequency feature extraction based on multivariable synchronization index for training-free SSVEP-based BCI.

Multivariate synchronization index (MSI), as an effective recognition algorithm for steady-state visual evoked potential (SSVEP) brain-computer interface (BCI), can accurately decode target frequencies without training. To further consider temporal features or extract harmonic components, extended MSI (EMSI), temporally local MSI (TMSI), and filter bank MSI (FBMSI) have been proposed. However, the promotion effects of the above three strategies on MSI have not been compared in detail. In this paper, the performance of EMSI, TMSI, and FBMSI under different time windows was analyzed with the same dataset. The results indicated that the improvement effect of the temporally local method on MSI was better than that of the other two methods under the short time window, and the effect of the filter bank method was better when the time window was greater than 0.8s. Based on the idea of simultaneously extracting time-frequency features, FBEMSI and FBTMSI were proposed by integrating time delay embedding and temporally local method into FBMSI respectively. The two improved methods, which has no significant difference, can improve the recognition effect of FBMSI. But the computing time of FBEMSI was shorter, which can be a potential method for SSVEP-BCI.

SSVEP-based visual acuity threshold estimation: linear extrapolation to noise level baseline with various noise definition criteria.

This study aimed to explore the effect of various noise definition criteria in linear extrapolation technique to noise level baseline on steady-state visual evoked potential (SSVEP)-based visual acuity assessment. Four noise definition criteria on frequency-domain, i.e., the mean amplitude at the two adjacent bins of the target frequency, the mean amplitude of a narrow frequency band on either side of the target frequency, the mean amplitude at a broad frequency band except for the target frequency and its harmonic frequencies, and the mean amplitude at a broad frequency band at resting state, corresponding to noise 1, noise 2, noise 3, and noise 4, were introduced to calculate noise level baselines. Then, two experiments were implemented. In experiment 1, electroencephalography (EEG) signals of resting state were recorded for fourteen subjects. In experiment 2, the visual stimuli of vertical sinusoidal gratings at six spatial frequency steps were used to induce SSVEPs for twelve subjects. Finally, SSVEP visual acuity was obtained via the SSVEP visual acuity threshold estimation of linear extrapolation technique to noise level baseline with various noise definition criteria. The bland-Altman analysis found that the difference between subjective Freiburg Visual Acuity and Contrast Test (FrACT) and objective SSVEP visual acuity was - 0.0892, - 0.1071, - 0.0745, and - 0.0804 logMAR and the 95% limit of agreement was 0.2150, 0.2146, 0.2046, and 0.2189 logMAR for noise 1, noise 2, noise 3, and noise 4, respectively, indicating that visual acuity of noise 3 definition criterion, i.e., the mean amplitude at a broad frequency band except for the target frequency and its harmonic frequencies, showed the best performance. This study recommended noise definition criterion 3 of the mean amplitude at a broad frequency band to calculate the noise level baseline in the linear extrapolation of SSVEP-based visual acuity assessment.

A large database towards user-friendly SSVEP-based BCI

Background: Brain-computer interfaces (BCIs) have gained considerable attention for their potential in assisting individuals who have motor impairments with communication and rehabilitation. Among BCIs, steady-state visual evoked potential (SSVEP)-based systems have demonstrated high efficiency in interactive applications. However, ergonomic design challenges have limited their practical implementation in industrial settings. Issues such as visual and mental fatigue caused by flickering stimuli and the time-consuming preparation process hinder user adoption of such systems. Methods: To evaluate these BCI solutions, we introduced an open database comprising Electroencephalogram (EEG) data collected from 59 healthy volunteers using ergonomically designed semi-dry electrodes and grid stimuli. The database was acquired without electromagnetic shielding, and the preparation time for each participant was <5 min. A 40-target SSVEP speller system with cues was used in the experiment. Results: We validate the database by temporal and spectral analyzing methods. To further investigate the database, filter bank canonical correlation analysis (FBCCA), ensemble task-related component analysis (e-TRCA) and multi-stimulus task-related component analysis (msTRCA) were used for classification. The database can be downloaded from the following link: https://drive.google.com/drive/folders/1TXuxU863nZoniZRgNWZy0PRuL8lhBuP4?usp=sharing . Conclusions: This research contributes to enhancing the use of SSVEP-based BCIs in practical settings by addressing user experience and system design challenges. The proposed user-friendly visual stimuli and ergonomic electrode design improve comfort and usability. The open dataset serves as a valuable resource for future studies, enabling the development of robust and efficient SSVEP- BCI systems suitable for industrial applications.

Brain–Computer Interface Integrated With Augmented Reality for Human–Robot Interaction

Brain-computer interface (BCI) has been gradually used in human-robot interaction systems. Steady-state visual evoked potential (SSVEP) as a paradigm of electroencephalography (EEG) has attracted more attention in the BCI system research due to its stability and efficiency. However, an independent monitor is needed in the traditional SSVEP-BCI system to display stimulus targets, and the stimulus targets map fixedly to some pre-set commands. These limit the development of the SSVEP-BCI application system in complex and changeable scenarios. In this study, the SSVEP-BCI system integrated with augmented reality (AR) is proposed. Furthermore, a stimulation interface is made by merging the visual information of the objects with stimulus targets, which can update the mapping relationship between stimulus targets and objects automatically to adapt to the change of the objects in the workspace. During the online experiment of the AR-based SSVEP-BCI cue-guided task with the robotic arm, the success rate of grasping is 87.50 ± 3.10% with the SSVEP-EEG data recognition time of 0.5 s based on FB-tCNN. The proposed AR-based SSVEP-BCI system enables the users to select intention targets more ecologically and can grasp more kinds of different objects with a limited number of stimulus targets, resulting in the potential to be used in complex and changeable scenarios.

Effect of white matter tract microstructural integrity on gamma entrainment using flickering light stimulation

AbstractBackgroundAlthough gamma entrainment using flickering light stimulation (FLS), which was found to reduce Alzheimer’s disease pathologies in mice model, it failed to reduce cerebral amyloid burden in patients with AD or mild cognitive impairment. We investigated the optimal parameters of the FLS for entraining gamma waves in older adults in their brain may be influenced by white‐matter tract microstructural integrity (WMMSI) in humans.MethodWe enrolled 31 cognitively normal volunteers aged ≥ 65 years and measured resting‐state electroencephalography and the steady‐state visually evoked potential (SSVEP) of gamma rhythms induced by optimal FLS. We analyzed the spectral power change of the electroencephalogram induced by FLS using event‐related synchronization (ERS) and the propagation of gamma rhythms from the visual cortex to other brain regions using spectral Granger causality (sGC). Diffusion tensor images were acquired, and the microstructural integrity of white‐matter tracts of interest was measured. We investigated the relationship between white matter integrity and entrainment and propagation using fractional anisotropy (FA).ResultAfter excluding five participants with SSVEP deficit, 26 participants were included in the final analysis. The lowest quartile group of the FA of the left posterior thalamic radiation exhibited a significantly lower ERS of gamma rhythms in the visual cortex than the second‐to‐highest quartile group (p = 0.045). In the multiple linear regression analyses, the effects of the FA of the middle longitudinal fasciculus and superior longitudinal fasciculus 3 on the sGC of the gamma rhythm connectivity from the occipital to the temporal, central, and frontal regions were statistically significant in both hemispheres (p < 0.05).ConclusionThese findings suggest intact WMMSI may be required for proper gamma entrainment using FLS. Therefore, future clinical trials on gamma entrainment using FLS needs to consider WMMSI for participant selection.

Poster Session I: Noninvasive neuromodulation of subcortical visual pathways with transcranial focused ultrasound.

Transcranial ultrasound stimulation (TUS) is an emerging tool to noninvasively modulate neural activity in deep brain areas. In preparation for our first in-human TUS studies, we targeted TUS to the lateral geniculate nucleus (visual thalamus) in a large mammal (sheep). Full-field light flash stimuli were presented with or without concomitant TUS in randomly interleaved trials. Similar to what has previously observed by Fry et al (Nature 1959) in cats, EEG visual-evoked potentials (VEPs) were reversibly suppressed by TUS to the LGN. No changes in VEPs were observed in sheep who received sham-TUS to a control site in the basal ganglia, ruling out potential transducer auditory-somatosensory confounds. Magnetic resonance acoustic radiation force imaging (MR-ARFI), a technique to measure the ultrasound focus in situ, showed a focal volume of microscopic displacement at the expected target. Excitingly, MR-ARFI predicted the suppressive effect on VEPs in individual subjects, suggesting that MR-ARFI can be used to confirm TUS targeting and estimate neurophysiological impact. We are now translating this paradigm into human, targeting TUS to the LGN while participants perform a contrast detection task with EEG recording of steady-state VEPs. MR-ARFI will be measured to evaluate targeting and estimate TUS dosage in each participant. This work provides the foundation for a dissection of the roles of different subcortical nuclei in different aspects of human vision.

A data expansion technique based on training and testing sample to boost the detection of SSVEPs for brain-computer interfaces

Objective. Currently, steady-state visual evoked potentials (SSVEPs)-based brain-computer interfaces (BCIs) have achieved the highest interaction accuracy and speed among all BCI paradigms. However, its decoding efficacy depends deeply on the number of training samples, and the system performance would have a dramatic drop when the training dataset decreased to a small size. To date, no study has been reported to incorporate the unsupervised learning information from testing trails into the construction of supervised classification model, which is a potential way to mitigate the overfitting effect of limited samples. Approach. This study proposed a novel method for SSVEPs detection, i.e. cyclic shift trials (CSTs), which could combine unsupervised learning information from test trials and supervised learning information from train trials. Furthermore, since SSVEPs are time-locked and phase-locked to the onset of specific flashes, CST could also expand training samples on the basis of its regularity and periodicity. In order to verify the effectiveness of CST, we designed an online SSVEP-BCI system, and tested this system combined CST with two common classification algorithms, i.e. extended canonical correlation analysis and ensemble task-related component analysis. Main results. CST could significantly enhance the signal to noise ratios of SSVEPs and improve the performance of systems especially for the condition of few training samples and short stimulus time. The online information transfer rate could reach up to 236.19 bits min−1 using 36 s calibration time of only one training sample for each category. Significance. The proposed CST method can take full advantages of supervised learning information from training samples and unsupervised learning information of testing samples. Furthermore, it is a data expansion technique, which can enhance the SSVEP characteristics and reduce dependence on sample size. Above all, CST is a promising method to improve the performance of SSVEP-based BCI without any additional experimental burden.

Almost free of calibration for SSVEP-based brain-computer interfaces

Objective. Steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) is a promising technology that can achieve high information transfer rate (ITR) with supervised algorithms such as ensemble task-related component analysis (eTRCA) and task-discriminant component analysis (TDCA). However, training individual models requires a tedious and time-consuming calibration process, which hinders the real-life use of SSVEP-BCIs. A recent data augmentation method, called source aliasing matrix estimation (SAME), can generate new EEG samples from a few calibration trials. But SAME does not exploit the information across stimuli as well as only reduces the number of calibration trials per command, so it still has some limitations. Approach. This study proposes an extended version of SAME, called multi-stimulus SAME (msSAME), which exploits the similarity of the aliasing matrix across frequencies to enhance the performance of SSVEP-BCI with insufficient calibration trials. We also propose a semi-supervised approach based on msSAME that can further reduce the number of SSVEP frequencies needed for calibration. We evaluate our method on two public datasets, Benchmark and BETA, and an online experiment. Main results. The results show that msSAME outperforms SAME for both eTRCA and TDCA on the public datasets. Moreover, the semi-supervised msSAME-based method achieves comparable performance to the fully calibrated methods and outperforms the conventional free-calibrated methods. Remarkably, our method only needs 24 s to calibrate 40 targets in the online experiment and achieves an average ITR of 213.8 bits min−1 with a peak of 242.6 bits min−1. Significance. This study significantly reduces the calibration effort for individual SSVEP-BCIs, which is beneficial for developing practical plug-and-play SSVEP-BCIs.

Enhancing multi-class SSVEP classification performance using regularized covariance estimators, spatiotemporal beamforming, and short-time EEG trials

One of the main challenges in BCI technologies is the problem of poor information transfer rate (ITR) of BCI systems and its effect on reducing the commands users can give. At the state of the art, the Linearly Constrained Minimum Variance (LCMV) beamformer is one of the most effective strategies that can provide satisfactory performance in the analysis of steady-state visual evoked potentials (SSVEP). When only a short-period SSVEP signal is available, a poor estimate of the covariance matrix used in the original LCMV method is obtained. Therefore, the main drawback of the conventional LCMV beamformer and its spatiotemporal form (LCMVst) is that they require a long-period SSVEP signal to achieve a reliable estimate for the beamformer weights. To cope with the mentioned problems, this paper presents two types of regularized estimators to achieve a robust estimate for the covariance matrix when only a short-period SSVEP signal is available. These two types, which are user-independent, include the convex combination (CC) and general linear combination (GLC) methods. In the next step, in order to provide suitable beamformer weights, the CC and GLC covariance estimators are combined with the original LCMVst beamformer. Furthermore, two new subject-based electrode selection algorithms, i.e., sequential forward electrode selection (SFES) algorithm and common spatial pattern (CSP) based technique, are applied to pick out the best collection of electrodes and to maximize the classification accuracy. The introduced methods were assessed using a four-class SSVEP dataset recorded on 20 subjects. Experimental results indicate that the proposed estimators optimally classify SSVEPs by estimating proper beamformer weights. The proposed LCMVst-CC and LCMVst-GLC beamformers improved the average classification accuracy by about 27.75% in comparison to the original LCMV-based beamformer at the 0.25-second segment length. Using SSVEP stimulations, we show that our proposed beamformers offer a better classification performance than the conventional LCMV-based spatiotemporal beamformer for all stimulation times.