Improved BCI performance with sequential hypothesis testing

Abstract

One of the primary challenges in noninvasive brain-computer interface (BCI) control is low information transfer rate (ITR). An approach that employs a power-based sequential hypothesis testing (SHT) technique is presented for real-time detection of motor commands. Electroencephalogram (EEG) recordings obtained during a BCI task were first analyzed with a hypothesis testing (HT) method. Using serial analysis we minimized the time to determine a cued motor imagery cursor control decision. Experimental results show that the accuracy of the SHT method was above 80% for all the subjects (n = 3). The average decision time was 3.4 s, as compared with 6.0 s for the HT method. Moreover, the proposed SHT method has three times the information transfer rate (ITR) compared with the HT method.