Simultaneous Decoding of Eccentricity and Direction Information for a Single-Flicker SSVEP BCI

Jingjing Chen,Yijun Wang,Alexander Maye,Xiaorong Gao,Dan Zhang,Andreas K Engel

doi:10.3390/electronics8121554

Abstract

The feasibility of a steady-state visual evoked potential (SSVEP) brain–computer interface (BCI) with a single-flicker stimulus for multiple-target decoding has been demonstrated in a number of recent studies. The single-flicker BCIs have mainly employed the direction information for encoding the targets, i.e., different targets are placed at different spatial directions relative to the flicker stimulus. The present study explored whether visual eccentricity information can also be used to encode targets for the purpose of increasing the number of targets in the single-flicker BCIs. A total number of 16 targets were encoded, placed at eight spatial directions, and two eccentricities (2.5° and 5°) relative to a 12 Hz flicker stimulus. Whereas distinct SSVEP topographies were elicited when participants gazed at targets of different directions, targets of different eccentricities were mainly represented by different signal-to-noise ratios (SNRs). Using a canonical correlation analysis-based classification algorithm, simultaneous decoding of both direction and eccentricity information was achieved, with an offline 16-class accuracy of 66.8 ± 16.4% averaged over 12 participants and a best individual accuracy of 90.0%. Our results demonstrate a single-flicker BCI with a substantially increased target number towards practical applications.

Highlights

Steady-state visual evoked potential (SSVEP), as one of the most widely used responses in electroencephalogram (EEG) -based brain–computer interfaces (BCIs), has received sustained attention [1,2,3,4,5,6,7]
By encoding targets with visual direction and eccentricity information simultaneously, By encoding targets with visual direction and eccentricity information simultaneously, a singlea single-stimulus 16-target SSVEP BCI was proposed in the present study
When participants stimulus 16-target SSVEP BCI was proposed in the present study

Summary

Introduction

Steady-state visual evoked potential (SSVEP), as one of the most widely used responses in electroencephalogram (EEG) -based brain–computer interfaces (BCIs), has received sustained attention [1,2,3,4,5,6,7]. When participants attend a periodic visual stimulus, SSVEPs are elicited at the stimulation frequency and its harmonics [8]. By encoding different targets with distinct frequencies, BCI systems can be realized via real-time frequency recognition of the recorded. The frequency-coding SSVEP BCIs have achieved significant progress, featured by the relatively large number of simultaneously decodable targets and the high communication speed [5,6], thereby potential for real-life applications such as letter typing. SSVEP responses would be elicited [10].

Methods

Results

Conclusion