Modeling EEG Data Distribution With a Wasserstein Generative Adversarial Network to Predict RSVP Events

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 28; no. 8; pp. 1720 - 1730
• Main Authors: Panwar, Sharaj, Rad, Paul, Jung, Tzyy-Ping, Huang, Yufei
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Brain modeling; Classification; Computer simulation; convolutional neural network; data augmentation; Deconvolution; EEG; Electroencephalography; Gallium nitride; Gaussian mixture models; Generative adversarial networks; Generators; Machine learning; Modelling; Training; Visual signals; Wasserstein generative adversarial network
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2020.3006180

Electroencephalography (EEG) data are difficult to obtain due to complex experimental setups and reduced comfort with prolonged wearing. This poses challenges to train powerful deep learning model with the limited EEG data. Being able to generate EEG data computationally could address this limitation. We propose a novel Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) to synthesize EEG data. This network addresses several modeling challenges of simulating time-series EEG data including frequency artifacts and training instability. We further extended this network to a class-conditioned variant that also includes a classification branch to perform event-related classification. We trained the proposed networks to generate one and 64-channel data resembling EEG signals routinely seen in a rapid serial visual presentation (RSVP) experiment and demonstrated the validity of the generated samples. We also tested intra-subject cross-session classification performance for classifying the RSVP target events and showed that class-conditioned WGAN-GP can achieve improved event-classification performance over EEGNet.