Modeling EEG data distribution with a Wasserstein Generative Adversarial Network to predict RSVP Events
This work addresses data scarcity in EEG-based applications, such as rapid serial visual presentation experiments, by generating synthetic data to enhance model training, though it is incremental as it builds on existing WGAN-GP methods.
The authors tackled the problem of limited EEG data for training deep learning models by proposing a Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) to synthesize EEG data, demonstrating its validity for generating one and 64-channel data and showing that a class-conditioned variant improves event-classification performance over EEGNet.
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.