Skip to Main Content
Brain-Computer Interface is an alternative communication system between human and outside world which enables paralyzed and locked-in patients (like Amyotrophic lateral sclerosis - ALS) to communicate with their environment or control some electronic devices like computer using only their brain activity. Over the last two decades, numerous studies have been performed on this title and researchers proposed various applications and methodologies related to BCI research. In this study, a design and implementation of a P300 based BCI is realized. The hardware of the system consists of a 10 channel Electroencephalography (EEG) device which has been developed in our laboratory for BCI research. As the first application of this system, the so called “P300 Speller” of Farwell and Donchin has been chosen. Several statistical signal processing techniques and operational optimizations have been applied to improve the speed-accuracy performance of this spelling application. According to the online experiment results performed to test the practicality of this system, two out of five healthy participants were able to operate the system using only two trial repetitions for the perfect prediction of the target characters (6 seconds). The average and maximum bit rates of the system were measured to be 10.4bits/min and 31.14bits/min respectively. Regarding these results, the developed system has superior performance as compared to most of the P300 based BCI systems in the literature.