Enhancing Performance of SSVEP-Based Visual Acuity via Spatial Filtering

Abstract

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.

Enhancing Performance of Single-Channel SSVEP-Based Visual Acuity Assessment via Mode Decomposition

“…In this study, we used the SSVEP dataset in our previous work [9]. Eleven healthy subjects (four females, ages 22-27 years) were recruited.…”

“…Previous studies have proposed and compared the classic linear extrapolation methods and then improved these methods from some different aspects [7], e.g., machine learning [8], spatial filtering [9], and curvilinear form [10,11]. Here, most studies use EEG signals from only a single channel in visual acuity assessment for its convenience, especially for children and infants, and then apply the Fourier transform to extract the frequency-domain amplitude feature [6].…”

“…Therefore, this study aimed to explore the effect of mode decomposition methods on the single-channel SSVEP visual acuity assessment. First, the SSVEP dataset corresponding to six spatial frequencies and six electrode channels from 11 subjects was obtained from our previous study [9]. Then, EMD, EEMD, ICEEMDAN, and VMD were applied to the single-channel SSVEP signal of the Oz electrode, and the mode decomposition methods with good performance for further signal processing were chosen.…”

A Methodology for Enhancing SSVEP Features Using Adaptive Filtering Based on the Spatial Distribution of EEG Signals

“…A high-quality EEG requires more EEG channels and proper electrode placement, which is difficult to achieve in practical application environments [ 29 , 30 ]. The existing classical CCA algorithm has the problem of low accuracy when there is a lack of stimulation time or EEG leads [ 31 , 32 , 33 , 34 ]. To solve this problem, we tried to reduce the number of electrode channels required for EEG recording, while ensuring a certain accuracy, so that the SSVEP BCI system is more applicable to a wearable environment.…”

“…A high-quality EEG requires more EEG channels and proper electrode placement, which is difficult to achieve in practical application environments [29,30]. The existing classical CCA algorithm has the problem of low accuracy when there is a lack of stimulation time or EEG leads [31][32][33][34].…”