Generative Adversarial Networks for Augmenting EEG Data in P300-based Applications: A Comparative Study

Abstract

The performance of P300-based Brain-Computer Interface (BCI) applications is highly dependent on both the quality and quantity of the recorded Electroencephalography (EEG) signals. As recording extended datasets from users for calibration is often a difficult and tedious task, data augmentation can be used to help supplement the training data for machine learning classifiers that are typically used in P300-based BCI applications. In this paper, we analyze and compare the performance of three different generative adversarial networks (GANs) as data augmentation techniques; namely, deep convolutional GAN (DCGAN), conditional GAN (cGAN), and the auxiliary classifier GAN (ACGAN). We first investigated the effect of increasing the training data size using each of these GANs on the performance of P300 classification. Our results revealed that the cGAN increased the classification accuracy by up to 18% relative to the baseline data under the best conditions. We also investigated the effect of decreasing the training data size and compensating for the reduced data size using data generated from the GANs. Our analysis indicated that the training data size could be reduced by ~30% while maintaining the accuracy on par with the baseline accuracy. These results demonstrate the utility of GANs in addressing the challenges associated with the limited data typically available for BCI applications.