Performance Assessment of a Custom, Portable, and Low-Cost Brain-Computer Interface Platform

Performance Assessment of a Custom, Portable, and Low-Cost Brain-Computer Interface Platform

Performance Assessment of a Custom, Portable, and Low-Cost Brain-Computer Interface Platform 170 177 IEEE Transactions on Biomedical Engineering (TBME)

Performance Assessment of a Custom, Portable, and Low-Cost Brain-Computer Interface Platform

Conventional brain-computer interfaces (BCIs) are often expensive, complex to operate, and lack portability, which confines their use to laboratory settings. Portable, inexpensive BCIs can mitigate these problems, but it remains unclear whether their low-cost design compromises their performance. Therefore, we developed a portable, low-cost (~$310) BCI and compared its performance to that of a conventional BCI. The BCI was assembled by integrating a custom electroencephalogram (EEG) amplifier with an open-source microcontroller and a touchscreen. The function of the amplifier was first validated against a commercial bioamplifier by simultaneously acquiring EEG data with both systems. The resulting data were visually similar and highly correlated (ρ=0.79). Next, a head-to-head comparison between the custom BCI (using 4 EEG channels) and a conventional 32-channel BCI was performed. Specifically, 5 able-bodied subjects were cued to alternate between hand opening/closing and remaining motionless while the BCI decoded the EEG underlying their movement state in real-time and provided visual feedback through a light emitting diode. Subjects repeated the above task for a total of 10 trials (5 trials per system), and were blinded to which system was being used. The performance in each trial was defined as the temporal correlation between instructional cues and the decoded states. Overall, subject performance with the custom and conventional system were not significantly different (average performance of 0.70±0.12 and 0.68±0.10, respectively). This study demonstrates that the performance of our custom BCI is comparable to that of conventional BCIs, and thus simple, portable, low-cost platforms, such as the one developed here, are suitable for BCI applications outside of a laboratory.