Effect of background luminance of visual stimulus on elicited steady-state visual evoked potentials

Steady-state visual evoked potential(SSVEP)-based brain-computer interfaces(BCIs)have been widely studied.Considerable progress has been made in the aspects of stimulus coding,electroencephalogram processing,and recognition algorithms to enhance system performance.The properties of SSVEP have been demonstrated to be highly sensitive to stimulus luminance.However,thus far,there have been very few reports on the impact of background luminance on the system performance of SSVEP-based BCIs.This study investigated the impact of stimulus background luminance on SSVEPs.Specifically,this study compared two types of background luminance,i.e.,(1)black luminance[red,green,blue(rgb):(0,0,0)]and(2)gray luminance[rgb:(128,128,128)],and determined their effect on the classification performance of SSVEPs at the stimulus frequencies of 9,11,13,and 15 Hz.The offline results from nine healthy subjects showed that compared with the gray background luminance,the black background luminance induced larger SSVEP amplitude and larger signal-to-noise ratio,resulting in a better classification accuracy.These results suggest that the background luminance of visual stimulus has a considerable effect on the SSVEP and therefore has a potential to improve the BCI performance.

Gaussian Process for a Single-channel EEG Decoder with Inconspicuous Stimuli and Eyeblinks

A single-channel electroencephalography(EEG)device,despite being widely accepted due to convenience,ease of deployment and suitability for use in complex environments,typically poses a great challenge for reactive brain-computer interface(BCI)applications particularly when a continuous command from users is desired to run a motorized actuator with different speed profiles.In this study,a combination of an inconspicuous visual stimulus and voluntary eyeblinks along with a machine learning-based decoder is considered as a new reactive BCI paradigm to increase the degree of freedom and minimize mismatches between the intended dynamic command and transmitted control signal.The proposed decoder is constructed based on Gaussian Process model(GPM)which is a nonparametric Bayesian approach that has the advantages of being able to operate on small datasets and providing measurements of uncertainty on predictions.To evaluate the effectiveness of the proposed method,the GPM is compared against other competitive techniques which include k-Nearest Neighbors,linear discriminant analysis,support vector machine,ensemble learning and neural network.Results demonstrate that a significant improvement can be achieved via the GPM approach with average accuracy reaching over 96%and mean absolute error of no greater than 0.8 cm/s.In addition,the analysis reveals that while the performances of other existing methods deteriorate with a certain type of stimulus due to signal drifts resulting from the voluntary eyeblinks,the proposed GPM exhibits consistent performance across all stimuli considered,thereby manifesting its generalization capability and making it a more suitable option for dynamic commands with a single-channel EEG-controlled actuator.