No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Spatial filtering techniques for improving individual template-based SSVEP detection
Abstract
In the past decade, the performance of brain-computer interfaces based on steady-state visual evoked potentials (SSVEPs) has been significantly improved due to advances in signal analysis algorithms. For example, efficient target-identification methods based on template matching, in which individual templates are obtained by averaging the training data across trials, have been proposed to improve the performance of SSVEP detection. In template-based methods, spatial filtering plays an important role in improving the performance by enhancing the signal-to-noise ratio of SSVEPs. In conventional studies, several spatial-filtering approaches have been introduced for electroencephalogram analysis. However, the optimal spatial-filtering approach for individual template-based SSVEP detection still remains unknown. This chapter reviews the spatial-filtering approaches for improving the template-based SSVEP detection and evaluates their performance through a direct comparison using a benchmark dataset of SSVEPs.
... The spatial filtering technique combining the multielectrode signals into single-or multichannel signals offers a better method for extracting SSVEP features and eliminating nuisance signals in SSVEP studies (Yan et al., 2018). Since scalp EEG is usually regarded to be a linear mixture of multiple time series from various cortical sources (Onton et al., 2006), the weight coefficients can be applied for multielectrode scalp EEG signals to estimate the cortical source activities (Nakanishi et al., 2018b). On the basis of this idea, several methods of extracting optimal spatial filters to reconstruct source activities from scalp EEG signals have been carried out to enhance the SNR of SSVEPs. ...
... , y i (N t ) T ∈ R N t ×1 contains the SSVEP signal of the ith electrode in one segment of N t samples, and e i ∈ R N t ×1 is the noise vector. The SSVEP reference signals model X f ∈ R N t ×2N h is defined by Nakanishi et al. (2018b): ...
... The CCA-based SSVEP visual acuity achieved a difference of 0.039 logMAR and a limit of agreement of 0.202 logMAR from FrACT visual acuity, and that for MSI-based SSVEP visual acuity were −0.080 logMAR and 0.208 logMAR, which was all lower than them of SSVEP visual acuity for the native combination with a difference and a limit of agreement of −0.095 logMAR and 0.253 logMAR. Since the spatial filtering methods can enhance the SNR of SSVEPs and suppress the non-SSVEP noise (Nakanishi et al., 2018b), this result illustrated that the unrelated noise, e.g., EMG and EOG (Friman et al., 2007;Zhang et al., 2021), was one of the reasons for the difference between SSVEP and behavioral visual acuity (Hamilton et al., 2021b), and the other methods of enhancing the SNR, such as signal preprocessing (Kołodziej et al., 2016), e.g., time-domain filtering and blind source separation (BSS) (Ji et al., 2019), and SSVEP recognition algorithms , e.g., wavelet transform (WT) (Rejer, 2017) and empirical mode decomposition (EMD) (Huang et al., 2013;Tello et al., 2014), may also have the property to improve the agreement between SSVEP and behavioral visual acuity. ...
The purpose of this study was to enhance the performance of steady-state visual evoked potential (SSVEP)-based visual acuity assessment with spatial filtering methods. Using the vertical sinusoidal gratings at six spatial frequency steps as the visual stimuli for 11 subjects, SSVEPs were recorded from six occipital electrodes (O1, Oz, O2, PO3, POz, and PO4). Ten commonly used training-free spatial filtering methods, i.e., native combination (single-electrode), bipolar combination, Laplacian combination, average combination, common average reference (CAR), minimum energy combination (MEC), maximum contrast combination (MCC), canonical correlation analysis (CCA), multivariate synchronization index (MSI), and partial least squares (PLS), were compared for multielectrode signals combination in SSVEP visual acuity assessment by statistical analyses, e.g., Bland–Altman analysis and repeated-measures ANOVA. The SSVEP signal characteristics corresponding to each spatial filtering method were compared, determining the chosen spatial filtering methods of CCA and MSI with a higher performance than the native combination for further signal processing. After the visual acuity threshold estimation criterion, the agreement between the subjective Freiburg Visual Acuity and Contrast Test (FrACT) and SSVEP visual acuity for the native combination (0.253 logMAR), CCA (0.202 logMAR), and MSI (0.208 logMAR) was all good, and the difference between FrACT and SSVEP visual acuity was also all acceptable for the native combination (−0.095 logMAR), CCA (0.039 logMAR), and MSI (−0.080 logMAR), where CCA-based SSVEP visual acuity had the best performance and the native combination had the worst. The study proved that the performance of SSVEP-based visual acuity can be enhanced by spatial filtering methods of CCA and MSI and also recommended CCA as the spatial filtering method for multielectrode signals combination in SSVEP visual acuity assessment.
... In addition, the classification accuracy of the frequency-coded SSVEPs was estimated by the well-established target identification algorithms. In particular, the canonical correlation analysis (CCA)based method [20] and the individual-template-based method incorporated with five spatial filtering techniques [21] were employed as calibration-free and fully-calibrated A c c e p t e d M a n u s c r i p t approaches, respectively. Importantly, this study only employed the aforementioned popularly-used algorithms and spatial filtering techniques for ease in understanding and comparing the results with previous studies. ...
... In fully-calibrated methods, individualized templates χ n ∈ R Nc×Ns obtained by averaging multiple training trials as (χ n ) jk = 1 Nt Nt h=1 (χ n ) jkh are employed to better characterize SSVEPs than the computer-generated models [33,34,35]. It has also been proven that spatial filtering techniques are effective to enhance the performance of the fully-calibrated methods [21]. Assuming the stationarity in EEG signals, spatial filters derived from training data can be applied in the following validation stage. ...
... The correlation-based feature extraction in the fully-calibrated methods can be formulated as r n = Corr X T W ,χ T n W . Since more complicated spatial filters can be derived from training trials in the fully-calibrated methods than in the calibrationfree method, several kinds of algorithms have been proposed in previous studies [21]. The following four promising algorithms were employed in this study. ...
Objective:
The emergence of mobile electroencephalogram (EEG) platforms have expanded the use cases of brain--computer interfaces (BCIs) from laboratory-oriented experiments to our daily life. In challenging situations where humans' natural behaviors such as head movements are unrestrained, various artifacts could deteriorate the performance of BCI applications. This paper explored the effect of muscular artifacts generated by participants' head movements on the signal characteristics and classification performance of steady-state visual evoked potentials (SSVEPs).
Approach:
A moving visual flicker was employed to induce not only SSVEPs but also horizontal and vertical head movements at controlled speeds, leading to acquiring EEG signals with intensity-manipulated muscular artifacts. To properly induce neck muscular activities, a laser light was attached to participants' heads to give visual feedback; the laser light indicates the direction of the head independently from eye movements. The visual stimulus was also modulated by four distinct frequencies (10, 11, 12, and 13 Hz). The amplitude and signal-to-noise ratio (SNR) were estimated to quantify the effects of head movements on the signal characteristics of the elicited SSVEPs. The frequency identification accuracy was also estimated by using well-established decoding algorithms including calibration-free and fully-calibrated approaches.
Main results:
The amplitude and SNR of SSVEPs tended to deteriorate when the participants moved their heads, and this tendency was significantly stronger in the vertical head movements than in the horizontal movements. The frequency identification accuracy also deteriorated in proportion to the speed of head movements. Importantly, the accuracy was significantly higher than its chance-level regardless of the level of artifact contamination and algorithms.
Significance:
The results suggested the feasibility of decoding SSVEPs in humans freely moving their head directions, facilitating the real-world applications of mobile BCIs. The clinical trial registration number is HF2018-858.
... The Power Spectral Density (PSD) method was used to compute the spectral power as this is one of the most common and robust approaches to performing frequency analysis of EEG signals (Wang et al., 2006;Nakanishi et al., 2018). The PSD was computed using the Fieldtrip toolbox (Oostenveld et al., 2010) for each of the trials corresponding to each of the five stimulation frequencies, both for the Stimulation and No-stimulation conditions. ...
... This procedure was chosen because it allows calculating the stimulation frequency over time as new EEG observations are available resembling the case of a realistic online situation. Following previous studies (Chen et al., 2015b;Nakanishi et al., 2018;Liang et al., 2020), in our analysis we used a time window of length 1s (T win = 1s) and steps of 0.05s (T shift = 0.05s). We considered other window lengths and steps and these two values provided better performance in terms of accuracy and detection time. ...
Introduction
Brain-Computer Interfaces (BCI) based on Steady-State Visually Evoked Potentials (SSVEP) have great potential for use in communication applications because of their relatively simple assembly and in some cases the possibility of bypassing the time-consuming training stage. However, among multiple factors, the efficient performance of this technology is highly dependent on the stimulation paradigm applied in combination with the SSVEP detection algorithm employed. This paper proposes the performance assessment of the classification of target events with respect to non-target events by applying four types of visual paradigms, rectangular modulated On-Off (OOR), sinusoidal modulated On-Off (OOS), rectangular modulated Checkerboard (CBR), and sinusoidal modulated Checkerboard (CBS), with three types of SSVEP detection methods, Canonical Correlation Analysis (CCA), Filter-Bank CCA (FBCCA), and Minimum Energy Combination (MEC).
Methods
We set up an experimental protocol in which the four types of visual stimuli were presented randomly to twenty-seven participants and after acquiring their electroencephalographic responses to five stimulation frequencies (8.57, 10.909, 15, 20, and 24 Hz), the three detection methods were applied to the collected data.
Results
The results are conclusive, obtaining the best performance with the combination of either OOR or OOS visual stimulus and the FBCCA as a detection method, however, this finding contrasts with the opinion of almost half of the participants in terms of visual comfort, where the 51.9% of the subjects felt more comfortable and focused with CBR or CBS stimulation.
Discussion
Finally, the EEG recordings correspond to the SSVEP response of 27 subjects to four visual paradigms when selecting five items on a screen, which is useful in BCI navigation applications. The dataset is available to anyone interested in studying and evaluating signal processing and machine-learning algorithms for SSVEP-BCI systems.
... This study employed a template-matching-based classification method, which uses correlation coefficients between individual templates and ongoing EEG signals as features [6], [14], [15], [24]. The filter-bank analysis was also integrated to decompose SSVEPs into sub-band components so that independent information embedded in the harmonic components can be extracted efficiently [18]. ...
... This study employed the ensemble TRCA-based method to analyze the waveform-coded SSVEPs since it has shown the greatest performance in the previous literature of an SSVEPbased BCI [15], [24], [27]. To precisely capture fine-tuned fundamental and harmonic components in SSVEPs, more suitable algorithms than the TRCA-based methods, which might be model-based ones, need to be developed. ...
This study presents a novel waveform-coding method for multi-target steady-state visual evoked potential (SSVEP)-based brain–computer interfaces (BCIs). Three periodic waveforms including square, sawtooth, and sinusoidal waves at various frequencies and initial phases were employed to elicit discriminable SSVEPs. A virtual keyboard was first designed using 36 visual stimuli modulated by the combinations of different frequencies, phases, and waveforms. With the virtual keyboard, 13 healthy participants performed offline and online BCI experiments with a cue-guided spelling task. The task-related component analysis (TRCA)-based algorithm was used to identify a target visual stimulus. The offline results showed that the visual stimuli tagged with different properties could accurately be identified by analyzing the elicited SSVEPs. Moreover, the online spelling task achieved promising performance with an averaged information transfer rate (ITR) of 62.6 ± 32.5 bits/min. This study validated the feasibility of implementing a multi-command SSVEP-based BCI using the hybrid waveform-, frequency- and phase-coding method. The proposed waveform-coding method provides a completely new channel for multi-target stimulus coding, expanding the research fields of an SSVEP-based BCI.
... The template-based approach has been widely used in detecting both SSVEP and c-VEP [7], [8]. In addition, a previous comparison study of various spatial-filtering techniques verified that TRCA-based spatial filtering was the most effective approach in enhancing the signal-to-noise ratio (SNR) of evoked potentials including SSVEPs [25]. ...
Visual stimuli design plays an important role in brain-computer interfaces (BCIs) based on visual evoked potentials (VEPs). Variations in stimulus parameters have been shown to affect both decoding accuracy and subjective perception experience, implying the need for a trade-off in design. In this study, we comprehensively and systematically compared various combinations of amplitude contrast and spectral content parameters in the stimulus design to quantify their impact on decoding performance and subject comfort. Specifically, three parameters were investigated: 1) contrast level, 2) temporal pattern (periodic steady-state or pseudo-random code-modulated), and 3) frequency range. We collected electroencephalogram (EEG) data and subjective perception ratings from ten subjects and evaluated the decoding accuracy and subject comfort rating for different combinations of the stimulus parameters. Our results indicate that while high-frequency steady-state VEP (SSVEP) stimuli were rated the most comfortable, they also had the lowest decoding accuracy. Conversely, low-frequency SSVEP stimuli were rated the least comfortable but had the highest decoding accuracy. Standard and high-frequency M-sequence code-modulated VEPs (c-VEPs) produced intermediates between the two. We observed a consistent trade-off relationship between decoding accuracy and subjective comfort level across all parameters. Based on our findings, we offer c-VEP as a preferable stimulus for achieving reliable decoding accuracy while maintaining a reasonable level of comfortability.
... Many studies have validated the effectiveness of incorporating individual calibration data in classification models to reliably detect SSVEPs [2], [3], [4]. It has also been well-validated that spatial filtering techniques can enhance the signal-to-noise ratio (SNR) of SSVEPs by alleviating the interference from spontaneous electroencephalographic (EEG) activities [5]. ...
This commentary presents a replication study to verify the effectiveness of a sum of squared correlations (SSCOR)-based steady-state visual evoked potentials (SSVEPs) decoding method proposed by Kumar et al.. We implemented the SSCOR-based method in accordance with their descriptions and estimated its classification accuracy using a benchmark SSVEP dataset with cross validation. Our results showed significantly lower classification accuracy compared with the ones reported in Kumar et al.’s study. We further investigated the sources of performance discrepancy by simulating data leakage between training and test datasets. The classification performance of the simulation was remarkable similar to those reported by Kumar et al.. We, therefore, question the validity of evaluation and conclusions drawn in Kumar et al.’s study.
Steady-State Visually Evoked Potentials (SSVEPs) manifest as a sustained rhythmic activity that can be observed in surface electroencephalography (EEG) in response to periodic visual stimuli, commonly referred to as flickers. SSVEPs are widely used in fundamental cognitive neuroscience paradigms and Brain-Computer Interfaces (BCI) due to their robust and rapid onset. However, they have drawbacks related to the intrusive saliency of flickering visual stimuli, which may induce eye strain, cognitive fatigue, and biases in visual exploration. Previous findings highlighted the potential of altering features of flicker stimuli to improve user experience. In this study, we propose to reduce the amplitude modulation depth of flickering stimuli down to the individuals’ perceptual visibility threshold (periliminal) and below (subliminal). The stimulus amplitude modulation depth represents the contrast difference between the two alternating states of a flicker. A simple visual attention task where participants responded to the presentation of spatially cued target stimuli (left and right) was used to assess the validity of such periliminal and subliminal frequency-tagging probes to capture spatial attention. The left and right sides of the screen, where target stimuli were presented, were covered by large flickers (13 and 15 Hz, respectively). The amplitude modulation depth of these flickers was manipulated across three conditions: control, periliminal, and subliminal. The latter two levels of flickers amplitude modulation depth were defined through a perceptual visibility threshold protocol on a single-subject basis. Subjective feedback indicated that the use of periliminal and subliminal flickers substantially improved user experience. The present study demonstrates that periliminal and subliminal flickers evoked SSVEP responses that can be used to derive spatial attention in frequency-tagging paradigms. The single-trial classification of attended space (left versus right) based on SSVEP response reached an average accuracy of 81.1% for the periliminal and 58% for the subliminal conditions. These findings reveal the promises held by the application of inconspicuous flickers to both cognitive neuroscience research and BCI development.
Objective
Compared with the light-flashing paradigm, the ring-shaped motion checkerboard patterns avoid uncomfortable flicker or brightness modulation, improving the practical interactivity of brain-computer interface (BCI) applications. However, due to fewer harmonic responses and more concentrated frequency energy elicited by the ring-shaped checkerboard patterns, the mainstream untrained algorithms such as canonical correlation analysis (CCA) and filter bank canonical correlation analysis (FBCCA) methods have poor recognition performance and low information transmission rate (ITR).
Methods
To address this issue, a novel untrained SSVEP-EEG feature enhancement method using CCA and underdamped second-order stochastic resonance (USSR) is proposed to extract electroencephalogram (EEG) features.
Results
In contrast to typical unsupervised dimensionality reduction methods such as common average reference (CAR), principal component analysis (PCA), multidimensional scaling (MDS), and locally linear embedding (LLE), CCA exhibits higher adaptability for SSVEP rhythm components.
Conclusion
This study recruits 42 subjects to evaluate the proposed method and experimental results show that the untrained method can achieve higher detection accuracy and robustness.
Significance
This untrained method provides the possibility of applying a nonlinear model from one-dimensional signals to multi-dimensional signals.
In this study, the information bottleneck method is proposed as an optimisation method for steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI). The information bottleneck is an information-theoretic optimisation method for solving problems with a trade-off between preserving meaningful information and compression. Its main practical application in machine learning is in representation learning or feature extraction. In this study, we use the information bottleneck to find optimal classification rule for a BCI. This is a novel application for the information bottleneck. This approach is particularly suitable for BCIs since the information bottleneck optimises the amount of information transferred by the BCI. Steady-state visual evoked potential-based BCIs often classify targets using very simple rules like choosing the class corresponding to the largest feature value. We call this classifier the arg max classifier. It is unlikely that this approach is optimal, and in this study, we propose a classification method specifically designed to optimise the performance measure of BCIs. This approach gives an advantage over standard machine learning methods, which aim to optimise different measures. The performance of the proposed algorithm is tested on two publicly available datasets in offline experiments. We use the standard power spectral density analysis (PSDA) and canonical correlation analysis (CCA) feature extraction methods on one dataset and show that the current approach outperforms most of the related studies on this dataset. On the second dataset, we use the task-related component analysis (TRCA) method and demonstrate that the proposed method outperforms the standard argmax classification rule in terms of information transfer rate when using a small number of classes. To our knowledge, this is the first time the information bottleneck is used in the context of SSVEP-based BCIs. The approach is unique in the sense that optimisation is done over the space of classification functions. It potentially improves the performance of BCIs and makes it easier to calibrate the system for different subjects.
Task-related component analysis (TRCA) has been the most effective spatial filtering method in implementing high-speed brain-computer interfaces (BCIs) based on steady-state visual evoked potentials (SSVEPs). TRCA is a data-driven method, in which spatial filters are optimized to maximize inter-trial covariance of time-locked electroencephalographic (EEG) data, formulated as a generalized eigenvalue problem. Although multiple eigenvectors can be obtained by TRCA, the traditional TRCA-based SSVEP detection considered only one that corresponds to the largest eigenvalue to reduce its computational cost. This study proposes using multiple eigen-vectors to classify SSVEPs. Specifically, this study integrates a task consistency test, which statistically identifies whether the component reconstructed by each eigenvector is task-related or not, with the TRCA-based SSVEP detection method. The proposed method was evaluated by using a 12-class SSVEP dataset recorded from 10 subjects. The study results indicated that the task consistency test usually identified and suggested more than one eigenvectors (i.e., spatial filters). Further, the use of additional spatial filters significantly improved the classification accuracy of the TRCA-based SSVEP detection.
ResearchGate has not been able to resolve any references for this publication.