Brain-Computer Interface (BCI) approaches exhibit remarkable potential in neuro prosthetic applications. Good BCI system must be compact, decreasingly intrusive, have superior accuracy in classification accuracy as well as effective one. In the form of two popularly employed non-intrusive brain imaging techniques, namely, functional nearinfrared spectroscopy (fNIRS) and Electroencephalography (EEG), BCI system is included frequently into hybrid BCI system design, based on their complementing characteristics. In this work, the objective is to examine if early temporal information obtained from channels of fNIRS and singular EEG on every hemisphere is utilized for improving hybrid EEG-fNIRS BCI system’s efficacy and accuracy. With the expectation of noteworthy BCI performances on an overall, the abilities of integrating EEG and fNIRS recordings with benchmarked Deep Learning processes have been investigated.

Functional Near-Infrared Spectroscopy, Electroencephalography, Linear Component Analysis, Support Vector Machine, Brain-Computer Interface, Deep Neural Network, Genetic Algorithm.