Skip to content

Improving BCIs with generative models synthesizing realistic EEG signals. Co-authored research paper: https://arxiv.org/abs/2402.09453

License

Notifications You must be signed in to change notification settings

UBCMint/eeg-wgan

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

42 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Improving EEG Signal Availability using Deep Learning and Generative Adversarial Networks

License: MIT

Project Description

This repository contains the implementation of the Wasserstein GAN (WGAN) model with gradient penalty developed in our research paper. The focus of our research was to generate synthetic 1D time-series Electroencephalogram (EEG) signals that mimic real EEG data.

Abstract

Electroencephalography (EEG) plays a vital role in recording brain activities and is integral to the development of brain-computer interface (BCI) technologies. However, the limited availability and high variability of EEG signals present substantial challenges in creating reliable BCIs. To address this challenge, we propose a practical solution drawing on the latest developments in deep learning and Wasserstein Generative Adversarial Network (WGAN). The WGAN was trained on the BCI2000 dataset, consisting of around 1500 EEG recordings and 64 channels from 45 individuals. The generated EEG signals were evaluated via three classifiers yielding improved average accuracies. The quality of generated signals measured using Frechet Inception Distance (FID) yielded scores of 1.345 and 11.565 for eyes open and closed respectively. Even without a spectral or spatial loss term, our WGAN model was able to emulate the spectral and spatial properties of the EEG training data. The WGAN generated data mirrored the dominant alpha activity during closed-eye resting and high delta waves in the training data in its topographic map and power spectral density (PSD) plot. Our research testifies to the potential of WGANs in addressing the limited EEG data issue for BCI development by enhancing a small dataset to improve classifier generalizability.

Model architecture:

Results

Detailed results and comparisons are available in our paper.

Quick Start

To train the model and reproduce the results from our paper, simply run wgan-gp.ipynb file in a notebook environment such as Jupyter notebook

Citation

If you find our work useful, please cite our paper: Improving EEG Signal Availability using Deep Learning and Generative Adversarial Networks:

Contact

Feel free to contact joshparksj(at)gmail(dot)com for any question or suggestion.

About

Improving BCIs with generative models synthesizing realistic EEG signals. Co-authored research paper: https://arxiv.org/abs/2402.09453

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%