Adversarial denoising of EEG signals: a comparative analysis of standard GAN and WGAN-GP approaches
By systematically comparing standard GAN and WGAN-GP architectures, this study highlights a practical trade-off between aggressive noise suppression and high-fidelity signal reconstruction. The demonstrated improvements in signal quality underscore the promise of adversarially trained models for applications ranging from basic neuroscience research to real-time brain-computer interfaces (BCIs) in clinical or consumer-grade settings. The results further suggest that GAN-based frameworks can be easily scaled to next-generation wireless networks and complex electrophysiological datasets, offering robust and dynamic solutions to long-standing challenges in EEG denoising.
Authors
- Samuele Russo (ORCID: https://orcid.org/0000-0002-1846-9996)
- Christian Napoli (ORCID: https://orcid.org/0000-0002-3336-5853)
- Abdelaziz Rabehi (ORCID: https://orcid.org/0000-0001-8684-4754)
- Imad Eddine Tibermacine (ORCID: https://orcid.org/0009-0004-4729-7128)
- Giuseppe Mancini (ORCID: https://orcid.org/0000-0003-1286-2380)
- El‐Sayed M. El‐kenawy (ORCID: https://orcid.org/0000-0002-9221-7658)
- Amal H. Alharbi (ORCID: https://orcid.org/0000-0001-9327-7284)
- Francesco Citeroni
Institutions
- Princess Nourah bint Abdulrahman University (SA)
- Częstochowa University of Technology (PL)
- Applied Science Private University (JO)
- Ziane Achour University of Djelfa (DZ)
- National Research Council (IT)
- Istituto di Analisi dei Sistemi ed Informatica Antonio Ruberti (IT)
- Bahrain Polytechnic (BH)
- Sapienza University of Rome (IT)
Publication Details
- Journal
- Frontiers in Human Neuroscience
- Published
- 2025-05-06
- DOI
- https://doi.org/10.3389/fnhum.2025.1583342
- Citations
- 15
- Primary Topic
- Image and Signal Denoising Methods
- Type
- article
- Field-Weighted Citation Impact
- 19.14
Funders
- Princess Nourah Bint Abdulrahman University