Improving the performance of the LF-ASD brain computer interface by means of genetic algorithm

The low frequency-asynchronous switch design (the LF-ASD) was introduced as a direct asynchronous brain computer interface (BCI) system. An asynchronous BCI system is activated only when a user intends control and maintains an inactive state output when a user is not meaning to control the device. Results from the LF-ASD evaluations have shown promise, although the reported error rates are still high for most practical applications. One reason is that, so far, no user customization has been done on the LF-ASD. In this paper genetic algorithms are applied to automatically customize the length of the energy normalization transform (ENT) in the LF-ASD. In a previous design, it has been shown that the ENT is probably the greatest source of improvement, so tuning it would probably yield the best short term results. Results for three subjects show encouraging results for the proposed algorithm with respect to the previous designs.