Exploring The Temporal And Spatial Features of EEG Signals In Motor Imagery Task Using Deep Learning

摘要

Recently deep learning has outperformed classical method in many tasks. Since extracting useful features is the key point in BCI research, it is reasonable to assume that deep neuron networks can extract useful features from raw data. We will focus on how to use CNN and RNN to extract spatial and temporal features and gain better result on open dataset. We did our experiment on open dataset and mainly focus on motor imagery task.