ArtifactGen: Benchmarking WGAN-GP vs Diffusion for Label-Aware EEG Artifact Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908529805230080 |
|---|---|
| author | Arasu, Hritik Jahangiri, Faisal R |
| author_facet | Arasu, Hritik Jahangiri, Faisal R |
| contents | Artifacts in electroencephalography (EEG) -- muscle, eye movement, electrode, chewing, and shiver -- confound automated analysis yet are costly to label at scale. We study whether modern generative models can synthesize realistic, label-aware artifact segments suitable for augmentation and stress-testing. Using the TUH EEG Artifact (TUAR) corpus, we curate subject-wise splits and fixed-length multi-channel windows (e.g., 250 samples) with preprocessing tailored to each model (per-window min-max for adversarial training; per-recording/channel $z$-score for diffusion). We compare a conditional WGAN-GP with a projection discriminator to a 1D denoising diffusion model with classifier-free guidance, and evaluate along three axes: (i) fidelity via Welch band-power deltas ($Δδ,\ Δθ,\ Δα,\ Δβ$), channel-covariance Frobenius distance, autocorrelation $L_2$, and distributional metrics (MMD/PRD); (ii) specificity via class-conditional recovery with lightweight $k$NN/classifiers; and (iii) utility via augmentation effects on artifact recognition. In our setting, WGAN-GP achieves closer spectral alignment and lower MMD to real data, while both models exhibit weak class-conditional recovery, limiting immediate augmentation gains and revealing opportunities for stronger conditioning and coverage. We release a reproducible pipeline -- data manifests, training configurations, and evaluation scripts -- to establish a baseline for EEG artifact synthesis and to surface actionable failure modes for future work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08188 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ArtifactGen: Benchmarking WGAN-GP vs Diffusion for Label-Aware EEG Artifact Synthesis Arasu, Hritik Jahangiri, Faisal R Machine Learning Neural and Evolutionary Computing Neurons and Cognition Artifacts in electroencephalography (EEG) -- muscle, eye movement, electrode, chewing, and shiver -- confound automated analysis yet are costly to label at scale. We study whether modern generative models can synthesize realistic, label-aware artifact segments suitable for augmentation and stress-testing. Using the TUH EEG Artifact (TUAR) corpus, we curate subject-wise splits and fixed-length multi-channel windows (e.g., 250 samples) with preprocessing tailored to each model (per-window min-max for adversarial training; per-recording/channel $z$-score for diffusion). We compare a conditional WGAN-GP with a projection discriminator to a 1D denoising diffusion model with classifier-free guidance, and evaluate along three axes: (i) fidelity via Welch band-power deltas ($Δδ,\ Δθ,\ Δα,\ Δβ$), channel-covariance Frobenius distance, autocorrelation $L_2$, and distributional metrics (MMD/PRD); (ii) specificity via class-conditional recovery with lightweight $k$NN/classifiers; and (iii) utility via augmentation effects on artifact recognition. In our setting, WGAN-GP achieves closer spectral alignment and lower MMD to real data, while both models exhibit weak class-conditional recovery, limiting immediate augmentation gains and revealing opportunities for stronger conditioning and coverage. We release a reproducible pipeline -- data manifests, training configurations, and evaluation scripts -- to establish a baseline for EEG artifact synthesis and to surface actionable failure modes for future work. |
| title | ArtifactGen: Benchmarking WGAN-GP vs Diffusion for Label-Aware EEG Artifact Synthesis |
| topic | Machine Learning Neural and Evolutionary Computing Neurons and Cognition |
| url | https://arxiv.org/abs/2509.08188 |