Design and Implementation of an Asynchronous BCI System With Alpha Rhythm and SSVEP

Lei Zhang,Jingfeng Liu,Xiaojing Guo,Bangyan Zhou,Xiaopei Wu

doi:10.1109/access.2019.2946301

Abstract

Objective : The aim of this work was to build an asynchronous brain-computer interface (BCI) system based on steady-state visual evoked potentials (SSVEPs) that outputs continuous, stable and smooth control commands in the up, down, left and right directions. Real-time feedback is presented on the computer screen to enhance collaborative participation in the human-computer interaction. Methods : Four stimulus sources flickering at different frequencies were sequentially fixed around the computer monitor to allow for subjects to complete control tasks by gazing at different stimulus sources. The subjects autonomously switched between the idle and working states by controlling the alpha amplitude. A sliding window voting discrimination (SWVD) strategy was incorporated into the canonical correlation analysis (CCA) algorithm for asynchronous classification. Results : Experiments were performed with 18 subjects using both the synchronous and asynchronous paradigms. The average accuracy was 95.42±3.35% with a data length of 3 s for synchronous operation; in addition, most subjects were able to successfully control a target to move precisely and smoothly with a 1 s sliding window during asynchronous operation. Conclusion : The proposed design scheme is feasible for our online asynchronous BCI system. Significance : By applying the SWVD strategy and optimizing the experimental paradigm, the classical CCA algorithm was successfully applied for continuous control in an asynchronous BCI system. With the developed system, obvious improvements in the information transmission rate (ITR) and sensitivity were achieved, which will be beneficial for the development of practical BCI systems.

Highlights

A brain-computer interface (BCI) is a specialized type of technology for human-computer interaction characterized by the use of electroencephalography (EEG) signals as information carriers to allow the human brain to exert direct control over external equipment [1]
During asynchronous operation of the BCI system, two main types of EEG measurements are collected: spontaneous EEG alpha waves, which are used to control the switching of the operation state of the system, and state visual evoked potentials (SSVEPs) signals, which are used to realize multitarget control commands
We fixed 4 external stimulus sources flashing at different frequencies in 4 positions around a computer monitor, which were used to induce EEG signal conversion into continuous direction control commands

Summary

Introduction

A brain-computer interface (BCI) is a specialized type of technology for human-computer interaction characterized by the use of electroencephalography (EEG) signals as information carriers to allow the human brain to exert direct control over external equipment [1]. There are four main types of EEG-based BCI systems: systems using steady-state visual evoked potentials (SSVEPs) based on visual stimuli; systems using mu and beta rhythm event-related desynchronization/ synchronization (ERD/ERS) caused by mental tasks such as motor imagery; systems using the P300 ERP component; and systems using slow cortical potentials (SCPs) [4]. SSVEPbased BCI systems have many advantages, including the ability to support many control commands, a high information transmission rate (ITR), a short training time, small differences among individual users and strong versatility. Their disadvantage is that long-term stimulation can lead to visual fatigue [5]–[7]. Motor imagery-based BCI systems do not require external

Methods

Results

Discussion

Conclusion