User customization of the feature generator of an asynchronous brain interface

A study that customizes the feature generator parameters of an asynchronous Brain Interface (BI) is discussed. The goal is to detect the presence of a certain pattern, in the ongoing EEG, associated with a specific movement and to improve the system's performance. Results of this study show that customization mostly benefits able-bodied subjects with performance improvements of up to 6.8%. We evaluate the performance of our BI using stratified cross-validation scheme. This scheme repeats the analysis on the different cross-validation sets. It is shown that the performances of the system across the different sets are very similar. Thus, we conclude that a robust performance measure of the system can be obtained by using only one of these performance results.