Classification Of EEG Imagery Motor Function Using 3D Convolutional Neural Network

A brain-computer interface (BCI) is a computer-based system that
acquires brain signals, analyzes them, and translates them into commands. One of the
main uses for BCI is motor imagery, which has countless potential ranging from control
over prosthetic limbs to cybertronics. This project consists of research done towards braincomputer interfacing mainly using the outputs generated from EEG signals of left/right
imagined arm movements. This EEG output signal will then be classified using deep
learning technique known as 3D convolutional neural network to create a classification
algorithm. 3D ConvNet is well-suited for spatiotemporal feature learning, where
convolution and pooling operations are performed spatio-temporally. Compared to 2D
ConvNet, 3D ConvNet has the ability to model temporal information better owing to 3D
convolution and 3D pooling operations.