EUVIMEDEUVIMED entdecken
Crossref

EEG-GANet: Simulating Electroencephalogram Data to Address Sample Imbalance in P300 Speller

Xicheng Lou, Xinwei Li, Hongying Meng, Peiyang Li, Lisha Zhong, Zhangyong Li

Tsinghua Science and Technology · 2026-06 · 31 (6) · 2877-2891

DOI: 10.26599/tst.2025.9010083 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tsinghua Science and Technology, 2026-06. Verfasst von Xicheng Lou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The P300 speller is a brain−computer interface (BCI) system that enables character selection using event-related potentials (ERPs). However, the inherent imbalance between target and non-target stimuli biases deep learning models. Reducing non-target samples to mitigate this issue risks underutilizing valuable data. We propose EEG-GANet, a generative adversarial network leveraging domain transformation to augment target samples and mitigate class imbalance in P300 speller datasets. Additionally, we develop EEG-DBNet-V2, a compact dual-branch network that efficiently extracts temporal and spectral features from electroencephalography (EEG) signals, serving both as a classification model and as the discriminator within EEG-GANet. Extensive experiments with ten-fold cross-validation on three public datasets demonstrated EEG-DBNet-V2’s superior classification accuracy compared to state-of-the-art models, achieving this with significantly fewer parameters. Integrating EEG-GANet’s augmented data via fine-tuning further improved classification performance. EEG-GANet effectively addresses sample imbalance by generating physiologically accurate augmented data, substantially enhancing EEG-DBNet-V2’s classification capability. Our study introduces a targeted generative adversarial network (GAN)-based EEG data augmentation framework, enabling balanced model training without discarding valuable non-target samples. The integration of EEG-GANet and EEG-DBNet-V2 offers a lightweight yet robust solution, advancing the practical deployment of EEG-based BCIs under data-constrained conditions. The source code is publicly available at https://github.com/xicheng105/EEG-GANet.

Zitieren

APA

Lou, X., Li, X., Meng, H., Li, P., Zhong, L., & Li, Z. (2026). EEG-GANet: Simulating Electroencephalogram Data to Address Sample Imbalance in P300 Speller. Tsinghua Science and Technology, 31(6), 2877-2891. https://doi.org/10.26599/tst.2025.9010083

Vancouver

Lou X, Li X, Meng H, Li P, Zhong L, Li Z. EEG-GANet: Simulating Electroencephalogram Data to Address Sample Imbalance in P300 Speller. Tsinghua Science and Technology. 2026;31(6):2877-2891. doi:10.26599/tst.2025.9010083

BibTeX
@article{Lou2026,
  author = {Lou, Xicheng and Li, Xinwei and Meng, Hongying and Li, Peiyang and Zhong, Lisha and Li, Zhangyong},
  title = {EEG-GANet: Simulating Electroencephalogram Data to Address Sample Imbalance in P300 Speller},
  journal = {Tsinghua Science and Technology},
  year = {2026},
  volume = {31},
  number = {6},
  pages = {2877--2891},
  doi = {10.26599/tst.2025.9010083}
}
Kostenlos starten →