Analysis of Prefrontal Single-Channel EEG Data for Portable Auditory ERP-Based Brain-Computer Interfaces

Abstract

An electroencephalogram (EEG)-based brain-computer interface (BCI) is a tool to non-invasively control computers by translating the electrical activity of the brain. This technology has the potential to provide patients who have severe generalized myopathy, such as those suffering from amyotrophic lateral sclerosis (ALS), with the ability to communicate. Recently, auditory oddball paradigms have been developed to implement more practical event-related potential (ERP)-based BCIs because they can operate without ocular activities. These paradigms generally make use of clinical (over 16-channel) EEG devices and natural sound stimuli to maintain the user's motivation during the BCI operation; however, most ALS patients who have taken part in auditory ERP-based BCIs tend to complain about the following factors: (i) total device cost and (ii) setup time. The development of a portable auditory ERP-based BCI could overcome considerable obstacles that prevent the use of this technology in communication in everyday life. To address this issue, we analyzed prefrontal single-channel EEG data acquired from a consumer-grade single-channel EEG device using a natural sound-based auditory oddball paradigm. In our experiments, EEG data was gathered from nine healthy subjects and one ALS patient. The performance of auditory ERP-based BCI was quantified under an offline condition and two online conditions. The offline analysis indicated that our paradigm maintained a high level of detection accuracy (%) and ITR (bits/min) across all subjects through a cross-validation procedure (for five commands: 70.0 ± 16.1 and 1.29 ± 0.93, for four commands: 73.8 ± 14.2 and 1.16 ± 0.78, for three commands: 78.7 ± 11.8 and 0.95 ± 0.61, and for two commands: 85.7 ± 8.6 and 0.63 ± 0.38). Furthermore, the first online analysis demonstrated that our paradigm also achieved high performance for new data in an online data acquisition stream (for three commands: 80.0 ± 19.4 and 1.16 ± 0.83). The second online analysis measured online performances on the different day of offline and first online analyses on a different day (for three commands: 62.5 ± 14.3 and 0.43 ± 0.36). These results indicate that prefrontal single-channel EEGs have the potential to contribute to the development of a user-friendly portable auditory ERP-based BCI.

Keywords: auditory event-related potential; brain–computer interface; electroencephalogram; portable measurement device; single-channel data.

Figure 1

Spectrograms and directions of the five natural sounds (0°: duck, 45°: singing bird, 90°: frog, 135°: seagull, and 180°: dove) presented in our experiments.

Figure 2

Experimental protocols for one participant in (A) offline analysis and (B) online analyses. Two runs with online data were performed on the same day as the offline analysis (online experiment 1). The other eight runs were conducted 6 months later (online experiment 2). Five natural sounds were randomly presented, and the participants mentally counted the presence of the target sound during EEG recordings.

Figure 3

ERP and non-ERP waveforms of each subject in the offline analysis (purple line: ERP, blue line: non-ERP). The filled fields along the plots denote the standard error (SE) of amplitudes for each time point. The time interval for N200 is filled with light-gray color at 200–350 ms. In addition, the time intervals between 350–600 and 700–1,000 ms were filled with dark-gray color for finding the positive peaks of ERP responses.

Figure 4

ERP and non-ERP waveforms of each subject in the online analysis 1 (purple line: ERP, blue line: non-ERP). The filled fields along the plots denote the standard error (SE) of amplitudes for each time point. The time interval for N200 is filled with light-gray color at 200–350 ms. In addition, the time intervals between 350–600 and 700–1,000 ms were filled with dark-gray color for finding the positive peaks of ERP responses.

Figure 5

ERP and non-ERP waveforms of each subject in the online analysis 2 (purple line: ERP, blue line: non-ERP). The filled fields along the plots denote the standard error (SE) of amplitudes for each time point. The time interval for N200 is filled with light-gray color at 200—350 ms. In addition, the time intervals between 350–600 and 700–1,000 ms were filled with dark-gray color for finding the positive peaks of ERP responses.

Figure 6

Average detection accuracies based on LOTOCV for increasing the number of learning trials with two, three, four, and five commands.