Abstract
A challenging task for an electroencephalography (EEG)-based asynchronous brain-computer interface (BCI) is to effectively distinguish between the idle state and the control state while maintaining a short response time and a high accuracy when commands are issued in the control state. This study proposes a novel hybrid asynchronous BCI system based on a combination of steady-state visual evoked potentials (SSVEPs) in the EEG signal and blink-related electrooculography (EOG) signals. Twelve buttons corresponding to 12 characters are included in the graphical user interface (GUI). These buttons flicker at different fixed frequencies and phases to evoke SSVEPs and are simultaneously highlighted by changing their sizes. The user can select a character by focusing on its frequency-phase stimulus and simultaneously blinking his/her eyes in accordance with its highlighting as his/her EEG and EOG signals are recorded. A multifrequency band-based canonical correlation analysis (CCA) method is applied to the EEG data to detect the evoked SSVEPs, whereas the EOG data are analyzed to identify the user's blinks. Finally, the target character is identified based on the SSVEP and blink detection results. Ten healthy subjects participated in our experiments and achieved an average information transfer rate (ITR) of 105.52 bits/min, an average accuracy of 95.42%, an average response time of 1.34s and an average false-positive rate (FPR) of 0.8%. The proposed BCI generates multiple commands with a high ITR and low FPR. The hybrid asynchronous BCI has great potential for practical applications in communication and control.
Highlights
I N RECENT years, research on brain-computer interfaces (BCIs), which enable the translation of neural activities into control commands for external devices without the participation of peripheral nerves and muscles [1], has witnessed tremendous development
Satisfactory performance was achieved by all subjects, with a high accuracy (95.42% ± 2.15%), a relatively high information transfer rate (ITR) (105.53 bits/min ± 11.06 bits/min), and a short response time (1.34 s ± 0.16 s) in the control state and a low falsepositive rate (FPR)
The left panel shows that no apparent EOG waveforms similar to the waveforms depicted in the top panel of Fig. 4 were observed under the condition of eye blinking, while the middle and right panels revealed comparable responses at the fundamental frequency (8.5 Hz) under both conditions
Summary
I N RECENT years, research on brain-computer interfaces (BCIs), which enable the translation of neural activities into control commands for external devices without the participation of peripheral nerves and muscles [1], has witnessed tremendous development. An ideal asynchronous BCI must effectively distinguish between the idle and control states, which requires a low falsepositive rate (FPR) in the idle state and a low false-negative rate (FNR) in the control state. A strict threshold criterion is generally used to decrease the FPR in the idle state Imposing this criterion will increase the response time when a control command is issued and the FNR in the control state. A lax threshold condition potentially reduces the response time; it will lead to a high FPR in the idle state, and many control commands might be incorrectly generated in the idle state. A challenging task is to establish an asynchronous BCI system with high performance in effectively distinguishing between idle and control states
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
