EEG Signal processing and identification of P300 signals using deep learning

An Electroencephalography (EEG)-based brain-computer interface (BCI) is a system that helps in the process of direct communication between humans and computers using brain activity or biosignals. With the help of BCI, it is possible to notice events related to cognitive, motor, and sensory activities particular to that event, and this response is seen as a P300 peak in EEG signals. This event-related potential of the EEG signals is usually used to build speller systems. The input of commands or texts to a computer by thought can be done with the help of a communication tool P300 Speller. Therefore, to build a faster speller system, fundamentally a correct identification and classification of P300 responses are required. The main objective of this paper is to explore the use of the deep learning models and to identify the P300 waves which help in visualizing the P300 signals from the given input EEG signals.