Evaluation of Real-Time Endogenous Brain-Computer Interface Developed Using Ear-Electroencephalography

Soo-In Choi; Ji-Yoon Lee; Ki Moo Lim; Han-Jeong Hwang

doi:10.3389/fnins.2022.842635

Evaluation of Real-Time Endogenous Brain-Computer Interface Developed Using Ear-Electroencephalography

Front Neurosci. 2022 Mar 24:16:842635. doi: 10.3389/fnins.2022.842635. eCollection 2022.

Authors

Soo-In Choi¹, Ji-Yoon Lee^{2

3}, Ki Moo Lim^{1

4}, Han-Jeong Hwang^{2

3}

Affiliations

¹ Department of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi-si, South Korea.
² Department of Electronics and Information Engineering, Korea University, Sejong City, South Korea.
³ Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology, Korea University, Sejong City, South Korea.
⁴ Department of IT Convergence Engineering, Kumoh National Institute of Technology, Gumi-si, South Korea.

Abstract

While previous studies have demonstrated the feasibility of using ear-electroencephalography (ear-EEG) for the development of brain-computer interfaces (BCIs), most of them have been performed using exogenous paradigms in offline environments. To verify the reliable feasibility of constructing ear-EEG-based BCIs, the feasibility of using ear-EEG should be further demonstrated using another BCI paradigm, namely the endogenous paradigm, in real-time online environments. Exogenous and endogenous BCIs are to use the EEG evoked by external stimuli and induced by self-modulation, respectively. In this study, we investigated whether an endogenous ear-EEG-based BCI with reasonable performance can be implemented in online environments that mimic real-world scenarios. To this end, we used three different mental tasks, i.e., mental arithmetic, word association, and mental singing, and performed BCI experiments with fourteen subjects on three different days to investigate not only the reliability of a real-time endogenous ear-EEG-based BCI, but also its test-retest reliability. The mean online classification accuracy was almost 70%, which was equivalent to a marginal accuracy for a practical two-class BCI (70%), demonstrating the feasibility of using ear-EEG for the development of real-time endogenous BCIs, but further studies should follow to improve its performance enough to be used for practical ear-EEG-based BCI applications.

Keywords: brain-computer interface (BCI); ear-EEG; electroencephalography (EEG); endogenous BCI; test-retest reliability.