Motor Imagery EEG Data Augmentation with cWGAN-GP for Brain-Computer Interfaces

Abstract

Motor imagery is a paradigm in Brain-Computer Interface (BCI) systems based on EEG data. Recently, Deep Neural Networks (DNNs), such as EEGNet, have become a vital component for those systems, overcoming previous state-of-the-art techniques for classifying these data. However, most motor imagery EEG datasets are relatively small, hindering DNNs from achieving better results. In this sense, we propose using Generative Adversarial Networks to augment dataset 1 from the BCI Competition IV for classification efficiency improvement. In addition, we explore augmentation with Gaussian noise for comparison purposes. The experiments were analyzed considering the intrasubject and cross-subject perspectives.