Spelling with Steady-State Visual Evoked Potentials

In this work, the real-time performance of a novel method for detecting steady-state visual evoked potentials (SSVEP) is evaluated in a brain-computer interface (BCI) spelling task. At the core of this method is a spatial filtering algorithm for extracting SSVEP responses, which in previous off-line studies has shown significantly improved classification performance. The on-line performance is investigated by letting a group of 11 healthy subjects spell the word `BRAINCOMPUTERINTERFACE'. An average information transfer rate of 27 bits/minute was obtained in this task and the probability of correctly classifying the user's intention was estimated to 97.5%. In addition, two different letter layouts and selection schemes tailored for SSVEP BCI's are compared.