Evaluating the impact of input noise and ERP-based penalties on the physiological plausibility of EEG generation using WGAN-GP

Résumé fourni par la source

It is possible to generate artificial EEG signals using generative adversarial networks (GANs), but the physiological plausibility of these signals is not always considered, even though plausibility is important for the trustworthiness of generated EEG. Here, for the first time, we investigate how two key factors, input noise type (white vs. 1/f) and event-related potential (ERP)-based penalties, affect the plausibility of EEG trials generation, using a Wasserstein GAN with gradient penalty (WGAN-GP). ERP penalties were introduced as loss terms to penalize excessive high-frequency oscillations, thereby suppressing them during training. We evaluated physiological plausibility through visual inspection of ERP waveforms and power spectra (PS), statistical comparisons of EEG features (bandpower, entropy, P3 amplitude and latency, Petrosian fractal dimension, and Hjorth complexity), dimensional similarity by principal component analysis, t-distributed stochastic neighbor embedding, kernel density estimation, and decomposition of periodic and aperiodic components. Results show that WGAN-GP models using 1/f noise input preserved spectral characteristics better than white noise models, which introduced high-frequency oscillations. ERP-based penalties reduced these oscillations in white noise models, especially the 0.5-5 Hz bandpass-filtered ERP penalty, improving ERP waveforms and PS. However, ERP penalties with 1/f noise models sometimes disrupted the PS. In summary, using white noise and a 0.5-5 Hz passband penalty best reproduced ERP waveforms and PS, while using 1/f noise and a 0.5-3 Hz passband penalty achieved the most physiologically plausible feature distributions. There is a trade-off between learning time and frequency domain features. Input noise and ERP penalties must be aligned with the intended application.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.