Trans-cVAE-GAN: Transformer-Based cVAE-GAN for High-Fidelity EEG Signal Generation

Electroencephalography signal generation remains a challenging task due to its non-stationarity, multi-scale oscillations, and strong spatiotemporal coupling. Conventional generative models, including VAEs and GAN variants such as DCGAN, WGAN, and WGAN-GP, often yield blurred waveforms, unstable spe...

Full description

Saved in:
Bibliographic Details
Published in:Bioengineering (Basel) Vol. 12; no. 10; p. 1028
Main Authors: Yao, Yiduo, Wang, Xiao, Hao, Xudong, Sun, Hongyu, Dong, Ruixin, Li, Yansheng
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 26.09.2025
Subjects:
Ablation
Affective computing
Biochips
Brain
Comparative analysis
Computer applications
conditional variational autoencoder
Conditioning
Control stability
Controllability
Design
EEG
Electric transformers
Electroencephalography
Emotion recognition
Emotions
Fourier transforms
generative adversarial network
Generative adversarial networks
generative modeling
Human-computer interface
Implants
Labels
Liquors
Machine learning
Measurement techniques
Neural networks
Neurophysiology
Oscillations
Realism
Semantics
Signal generation
Time series
transformer
Waveforms
Wavelet transforms
generative adversarial network
conditional variational autoencoder
transformer
generative modeling
ISSN:2306-5354, 2306-5354
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Electroencephalography signal generation remains a challenging task due to its non-stationarity, multi-scale oscillations, and strong spatiotemporal coupling. Conventional generative models, including VAEs and GAN variants such as DCGAN, WGAN, and WGAN-GP, often yield blurred waveforms, unstable spectral distributions, or lack semantic controllability, limiting their effectiveness in emotion-related applications. To address these challenges, this research proposes a Transformer-based conditional variational autoencoder–generative adversarial network (Trans-cVAE-GAN) that combines Transformer-driven temporal modeling, label-conditioned latent inference, and adversarial learning. A multi-dimensional structural loss further constrains generation by preserving temporal correlation, frequency-domain consistency, and statistical distribution. Experiments on three SEED-family datasets—SEED, SEED-FRA, and SEED-GER—demonstrate high similarity to real EEG, with representative mean ± SD correlations of Pearson ≈ 0.84 ± 0.08/0.74 ± 0.12/0.84 ± 0.07 and Spearman ≈ 0.82 ± 0.07/0.72 ± 0.12/0.83 ± 0.08, together with low spectral divergence (KL ≈ 0.39 ± 0.15/0.41 ± 0.20/0.37 ± 0.18). Comparative analyses show consistent gains over classical GAN baselines, while ablations verify the indispensable roles of the Transformer encoder, label conditioning, and cVAE module. In downstream emotion recognition, augmentation with generated EEG raises accuracy from 86.9% to 91.8% on SEED (with analogous gains on SEED-FRA and SEED-GER), underscoring enhanced generalization and robustness. These results confirm that the proposed approach simultaneously ensures fidelity, stability, and controllability across cohorts, offering a scalable solution for affective computing and brain–computer interface applications.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2306-5354
2306-5354
DOI:10.3390/bioengineering12101028