EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals
This work addresses the need for synthetic EEG data in neuroscientific and neurological applications, such as data augmentation for brain-computer interfaces, but it is incremental as it adapts existing GAN methods to time series data.
The authors tackled the problem of generating realistic electroencephalographic (EEG) brain signals by developing EEG-GAN, a framework based on generative adversarial networks, which produced naturalistic EEG examples as validated by metrics like Inception score and Frechet inception distance.
Generative adversarial networks (GANs) are recently highly successful in generative applications involving images and start being applied to time series data. Here we describe EEG-GAN as a framework to generate electroencephalographic (EEG) brain signals. We introduce a modification to the improved training of Wasserstein GANs to stabilize training and investigate a range of architectural choices critical for time series generation (most notably up- and down-sampling). For evaluation we consider and compare different metrics such as Inception score, Frechet inception distance and sliced Wasserstein distance, together showing that our EEG-GAN framework generated naturalistic EEG examples. It thus opens up a range of new generative application scenarios in the neuroscientific and neurological context, such as data augmentation in brain-computer interfacing tasks, EEG super-sampling, or restoration of corrupted data segments. The possibility to generate signals of a certain class and/or with specific properties may also open a new avenue for research into the underlying structure of brain signals.