Denoising EEG Signals for Real-World BCI Applications Using GANs

Abstract

As a measure of the brain's electrical activity, electroencephalography (EEG) is the primary signal of interest for brain-computer-interfaces (BCI). BCIs offer a communication pathway between a brain and an external device, translating thought into action with suitable processing. EEG data is the most common signal source for such technologies. However, artefacts induced in BCIs in the real-world context can severely degrade their performance relative to their in-laboratory performance. In most cases, the recorded signals are so heavily corrupted by noise that they are unusable and restrict BCI's broader applicability. To realise the use of portable BCIs capable of high-quality performance in a real-world setting, we use Generative Adversarial Networks (GANs) that can adopt both supervised and unsupervised learning approaches. Although our approach is supervised, the same model can be used for unsupervised tasks such as data augmentation/imputation in the low resource setting. Exploiting recent advancements in Generative Adversarial Networks (GAN), we construct a pipeline capable of denoising artefacts from EEG time series data. In the case of denoising data, it maps noisy EEG signals to clean EEG signals, given the nature of the respective artefact. We demonstrate the capability of our network on a toy dataset and a benchmark EEG dataset developed explicitly for deep learning denoising techniques. Our datasets consist of an artificially added mains noise (50/60 Hz) artefact dataset and an open-source EEG benchmark dataset with two artificially added artefacts. Artificially inducing myogenic and ocular artefacts for the benchmark dataset allows us to present qualitative and quantitative evidence of the GANs denoising capabilities and rank it among the current gold standard deep learning EEG denoising techniques. We show the power spectral density (PSD), signal-to-noise ratio (SNR), and other classical time series similarity measures for quantitative metrics and compare our model to those previously used in the literature. To our knowledge, this framework is the first example of a GAN capable of EEG artefact removal and generalisable to more than one artefact type. Our model has provided a competitive performance in advancing the state-of-the-art deep learning EEG denoising techniques. Furthermore, given the integration of AI into wearable technology, our method would allow for portable EEG devices with less noisy and more stable brain signals.

The Influence of Smoothing Filtering Methods on the Performance of an EEG-Based Brain–Computer Interface

“…However, the use of EEG as an input to the system has limited the potential to design practical and useful BCI systems because of its low spatial resolution and SNRs. A number of denoising techniques have been developed for preventing noise in EEG and hence increasing SNRs [31], [32], [33]. Some of these techniques include signal averaging, filtering, principal component analysis, independent component analysis, and parallel factor analysis [36].…”

Self-supervised deep learning and EEG categorization

“…Luo et al (2020) use GANs to increase the sampling frequency of EEG. Different GAN-strategies are also used for artifact reduction Brophy et al, 2022;Sawangjai et al, 2022). Hu et al (2022) use GANs to transform scalp EEG to stereo-EEG.…”

Deep Autoencoder for Real-Time Single-Channel EEG Cleaning and Its Smartphone Implementation Using TensorFlow Lite With Hardware/Software Acceleration

“…We use multiple metrics to show the performance of our approach, with the metrics previously used in EEG artifact removal validation research [24], [30]- [32]. The metrics are calculated on each EEG segment in the test dataset and the mean and standard deviation calculated for each different artifact type.…”