A back-propagation through time based recurrent neural network approach for classification of cognitive EEG states

Decision making plays a very vital role in a person´s life and hence any impairment of this ability is of great concern. Thus our study aims at designing such an experiment that will involve the task of decision making and assist in developing cognitive rehabilitation system in near future with the help of Brain Computer Interface. The brain signals are acquired using EEG (electroencephalography) and the two vital tools of BCI system, feature extraction and classification are implemented on these signals. The feature extraction is done using the time varying adaptive autoregressive algorithm. But the prime focus of this paper is the implementation of back propagation through time recurrent neural network algorithm as mental state classifier.