A high frequency steady-state visually evoked potential based brain computer interface using consumer-grade EEG headset

Abstract

This work evaluates a possibility of creating a high-frequency, SSVEP-based brain computer interface using a low cost EEG recording hardware - an Emotiv EEG Neuro-headset. Both above aspects are crucial to enable deploying the BCI technology in the consumer market. High frequencies can be used to create a non-tiring and more pleasant interface. Commercial EEG systems, as the Emotiv EEG, although demonstrating large underperformance, are much more affordable than standard, clinical-grade EEG amplifiers. A system classifying between two stimuli and rest is designed and tested in two experiments: on five and ten subject respectively. First, the accuracy of the system is compared for frequencies in lower range (17Hz, 19Hz, 23Hz, 25Hz) and higher range (31Hz, 33Hz, 37Hz, 40Hz). The mean online accuracy is 80%±15% for the former and 67%±12% for the latter. Second, a more thorough investigation is done by evaluating the system for frequencies within a set of 35Hz-40Hz. Although the mean accuracy, 64% ± 22%, is relatively low, most of the users were able to achieve satisfying accuracy, with the mean reaching 82%±5%, which would allow for an efficient, and yet pleasant, usage of the BCI system. In each case a user dependent approach is applied, with a calibration session lasting about five minutes. EEG feature extraction is done using common spatial pattern (CSP) filtering, canonical correlation analysis (CCA), and linear discrimination analysis (LDA).

Comparison of Medical and Consumer Wireless EEG Systems for Use in Clinical Trials

“…Among the popular applications of consumer EEG systems are meditation and relaxation training as well as coping with anxiety or pain. Recent investigations have been exploring their utility beyond gaming: NeuroSky was shown to be able to detect onset of stage 1 sleep (Van Hal et al, 2014 ) and there has also been interest in assessing consumer EEG within brain computer-interfaces (Bialas and Milanowski, 2014 ; Kim et al, 2015 ; Taherian et al, 2017 ). The application of simpler EEG systems (6-channels, for example) is also being explored for emergency settings (Jakab et al, 2014 ).…”

EEG-Based Emotion Recognition: A State-of-the-Art Review of Current Trends and Opportunities

“…As seen from Figure 6 , the ease of setup while wearing a low-cost, consumer-grade wearable EEG headset provides comfort and reduces the complexity of setting up the device on the user's scalp, which is important for both researchers and users [ 63 ]. Even with the lower performance of wearable low-cost EEG devices, it is much more affordable compared to the standard clinical-grade EEG amplifiers [ 64 ]. Interestingly, the supposedly lower performance EEG headset could outperform a medical-grade EEG system with a lesser number of electrodes [ 65 ].…”

Cross-Platform Implementation of an SSVEP-Based BCI for the Control of a 6-DOF Robotic Arm

“…A common spatial patterns (CSP) filter selects the best characteristics from the EEG signal. The CSP algorithm produces spatial filters that maximize the variance of bandpass-filtered EEG signals from one class while minimizing their variance for the other class [122][123][124][125][126].…”

“…A common spatial patterns (CSP) filter selects the best characteristics from the EEG signal. The CSP algorithm produces spatial filters that maximize the variance of bandpass-filtered EEG signals from one class while minimizing their variance for the other class [122][123][124][125][126]. Considering that the cognitive activity of interest in this study is in the range of 0.2-40 Hz, a fourth-order Butterworth band-pass filter between 6-40 Hz was applied to the EEG signal.…”