Development of a decision system by a brain computer interface based on P300

A brain-computer interface (BCI) is a system that allows a user to communicate with the environment only through cerebral activity. To establish a direct link between the brain and a computer, the cerebral activity is measured and then analyzed with the help of signal processing and machine learning algorithms. P300 signal, which is used widely in BCI applications, is produced as a response to a stimuli and can be measured in the parietal lobe of the brain. The presence, magnitude and timing of this signal are often used as metrics of cognitive function in decision making. In this thesis, a system that is based on the P300 evoked potential is designed. The proposed hybrid structure uses Artificial Bee Colony (ABC) algorithm to optimize the weights of a Multilayer Perceptron (MLP). The hybrid system is compared with the widely used algorithms such as Support Vector Machines (SVM), K-Nearest Neighbour (KNN) and Linear Discriminant Analysis (LDA) and it is shown that the proposed system has a higher accuracy.