Using a P3-based Brain-Computer Interface
in Virtual and Real Worlds

Jessica D. Bayliss
Department of Computer Science
Rochester Institute of Technology


Recent advances in signal processing techniques have made brain-computer interfaces feasible for use by the handicapped. One type of EEG signal that may be used is the P3. The P3 component of the evoked potential is a response that occurs 300-450ms after a task-relevant stimulus. Since the P3 component is an inherent response, it requires little training for a subject to use a brain-computer interface (BCI) with this component as the control signal. The P3 component has been shown to be robust over different environments including immersive virtual reality and while sitting in a room watching a computer monitor. We present an environmental control application in a virtual apartment that enables a subject to turn on/off a light, television set, and radio. The BCI also enables a subject to say Hi/Bye to a virtual person.

The main drawback of P3-based BCI's is their slowness. Single trial analysis may speed up recognition, but often at the cost of accuracy. We discuss results from single trial analysis within the virtual apartment, how various movement artifacts can affect recognition, and conclude with possible ways for improving the system.

Colloquia Series page.