Exploitation of a compact, cost-effective EEG module for plug-and-play, SSVEP-based BCI

The possibility to develop compact, cost effective Brain-Computer Interface (BCI) solutions could take another step into transferring and spreading such technologies outside the labs. We present here our compact EEG hardware unit, and compare its performance against a commercial device. Then, we will demonstrate its use in a SSVEP-based BCI. The signal processing chain is briefly discussed. We also present a strategy for improving classification accuracy and false positives immunity by introducing an indicator related to the prediction confidence. A method for adaptively changing the length of the observed EEG window is also discussed. All these ideas are tested in an online, self-paced 4 class SSVEP-based BCI Moreover, tests are performed on the subject population as a whole, in an effort to produce subject-independent methods. Good performance is achieved, both in terms of true positive rate (>94%), as well as low false positive rate (0.26 min^-1).