Brain–Computer Interface Speller Based on Steady-State Visual Evoked Potential: A Review Focusing on the Stimulus Paradigm and Performance

Abstract

The steady-state visual evoked potential (SSVEP), measured by the electroencephalograph (EEG), has high rates of information transfer and signal-to-noise ratio, and has been used to construct brain–computer interface (BCI) spellers. In BCI spellers, the targets of alphanumeric characters are assigned different visual stimuli and the fixation of each target generates a unique SSVEP. Matching the SSVEP to the stimulus allows users to select target letters and numbers. Many BCI spellers that harness the SSVEP have been proposed over the past two decades. Various paradigms of visual stimuli, including the procedure of target selection, layout of targets, stimulus encoding, and the combination with other triggering methods are used and considered to influence on the BCI speller performance significantly. This paper reviews these stimulus paradigms and analyzes factors influencing their performance. The fundamentals of BCI spellers are first briefly described. SSVEP-based BCI spellers, where only the SSVEP is used, are classified by stimulus paradigms and described in chronological order. Furthermore, hybrid spellers that involve the use of the SSVEP are presented in parallel. Factors influencing the performance and visual fatigue of BCI spellers are provided. Finally, prevailing challenges and prospective research directions are discussed to promote the development of BCI spellers.

Enhancing Performance of SSVEP-Based Visual Acuity via Spatial Filtering

“…Canonical correlation analysis, a statistical way to measure the underlying correlation between two sets of multidimensional variables, was first used in SSVEP analysis by Lin et al (2007) . Till now, CCA has become the most widely used method in SSVEPs as a result of its effectiveness, robustness, and simple implementation ( Bin et al, 2009 ; Zheng et al, 2020b ; Li et al, 2021 ). Here, CCA finds the weights w y ∈ ℝ N e ×1 and w xf ∈ ℝ 2 N h ×1 to maximize the linear combinations between y = Y wy ∈ ℝ N t ×1 and x = X f w xf ∈ ℝ N t ×1 representing the multichannel SSVEP signals and the SSVEP reference signals.…”

“…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. For instance, the basic spatial filtering methods [e.g., Laplacian combination ( Friman et al, 2007 ) and common average reference (CAR) ( Zheng et al, 2020d )] and the model-based spatial filtering methods [e.g., minimum energy combination (MEC) ( Friman et al, 2007 ), canonical correlation analysis (CCA) ( Bin et al, 2009 ; Zheng et al, 2020b ; Li et al, 2021 ), and multivariate synchronization index (MSI) ( Zhang et al, 2014a )] have been applied to improve the performance of SSVEPs. However, to date, little is known about whether there is an enhancement of the spatial filtering technique from multielectrode signals on SSVEP visual acuity.…”

Steady-State Visual Evoked Potential Classification Using Complex Valued Convolutional Neural Networks

“…The response EEG has peak frequencies that are the fundamental and harmonic frequencies of the flicker stimulation. An SSVEP-based BCI is realized by assigning commands or alphabets to flickers having different frequencies [ 16 , 17 ]. BCIs can determine the intended commands of users by detecting the peak frequency from observed EEGs.…”

“…BCIs can determine the intended commands of users by detecting the peak frequency from observed EEGs. SSVEP-based BCIs achieve the highest information transfer rate (ITR) among state-of-the-art BCI implementations [ 16 , 17 , 18 ]. There are many extensions and hybrid BCIs for SSVEP-based BCIs.…”

Solving the SSVEP Paradigm Using the Nonlinear Canonical Correlation Analysis Approach

“…The response generally occurs in the occipital and parietal lobes of the brain, where it is possible to collect multiple trials quickly. These stimuli produce steady-stable and small-amplitude visual evoked potentials if the eyes face the same exogenous input [ 11 , 12 ] and its frequency is greater than 2 Hz; otherwise, it produces a transient VEP. However, the stimulus achieves a periodic response called SSVEP when the frequency is higher (>6 Hz) [ 13 ].…”