Brain Computer Interface with Genetic Algorithm

Brain Computer Interfaces (BCIs) measure brain signals of brain activity intentionally and unintentionally induced by the user, and thus provide a promising communication channel that does not depend on the brain’s normal output pathway consisting of peripheral nerves and muscles. Present-day Brain Computer Interfaces determine the intent of the user from a variety of different electrophysiological signals. They translate these signals in real-time commands that operate a computer display or other device. Successful operation requires that the user encode commands in these signals and that the BCI derive the commands from the signals. Thus, the user and the BCI system need to adapt to each other both initially and continually so as to ensure stable performance. Current BCIs have low information transfer rates (e.g. up to 10–25 bits/min). This is limited capacity for many possible applications of BCI technology, such as neuroprosthesis control, this device require higher information transfer rates. In non-invasive BCI, Signals from the brain are acquired by channels (i.e. electrodes) on the scalp. In new BCI systems for increase accuracy, increased number of electrodes. In this case the increased number of electrodes causes a non-linear increase in computational complexity (i.e. decrease transfer rate). This article used Genetic Algorithm for select the effective number of electrodes and Redundancy Reduction.