Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Oct 8, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.4K

Data Augmentation for EEG-Based Emotion Recognition Using Generative Adversarial Networks.

Guangcheng Bao1, Bin Yan1, Li Tong1

  • 1Henan Key Laboratory of Imaging and Intelligent Processing, PLA Strategic Support Force Information Engineering University, Zhengzhou, China.

Frontiers in Computational Neuroscience
|December 27, 2021
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Direct Tissue Mass Spectrometry Imaging by Atmospheric Pressure UV-Laser Desorption Plasma Postionization.

Journal of the American Society for Mass Spectrometry·2020
Same author

A novel secretagogin/ATF4 pathway is involved in oxidized LDL-induced endoplasmic reticulum stress and islet β-cell apoptosis.

Acta biochimica et biophysica Sinica·2020
Same author

Intravenous Thrombolysis before Thrombectomy may Increase the Incidence of Intracranial Hemorrhage inTreating Carotid T Occlusion.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2020
Same author

Safety and efficacy of traditional Chinese medicine, Qiaoshao formula, combined with dapoxetine in the treatment of premature ejaculation: An open-label, real-life, retrospective multicentre study in Chinese men.

Andrologia·2020
Same author

New insights into the interplay between miRNAs and autophagy in the aging of intervertebral discs.

Ageing research reviews·2020
Same author

Characterization of a Plasmid-Encoded Resistance-Nodulation-Division Efflux Pump in <i>Klebsiella pneumoniae</i> and <i>Klebsiella quasipneumoniae</i> from Patients in China.

Antimicrobial agents and chemotherapy·2020
Same journal

Learning under constraints: a theoretical framework for comparing resource-constrained learning in biological and artificial systems.

Frontiers in computational neuroscience·2026
Same journal

MsGCN: a multi-stream graph convolutional network for multiband PLV graph fusion in EEG-based biometric identification.

Frontiers in computational neuroscience·2026
Same journal

AI-driven neuroanalytic modeling for mental health: multichannel CNN-based autism spectrum disorder detection via facial pattern analysis.

Frontiers in computational neuroscience·2026
Same journal

Modeling multiscale neural dynamics for EEG-based emotion recognition using an attentive wavelet-transformer framework.

Frontiers in computational neuroscience·2026
Same journal

New directions for complex systems in contemporary neuroscience: a morphodynamic and emergent function approach.

Frontiers in computational neuroscience·2026
Same journal

NMDA receptor kinetics drive distinct routes to chaotic firing in pyramidal neurons.

Frontiers in computational neuroscience·2026
See all related articles
This summary is machine-generated.

This study introduces VAE-D2GAN, a novel generative model that enhances electroencephalography (EEG)-based emotion recognition by creating artificial training samples. This data augmentation significantly improves accuracy in recognizing emotions from EEG data.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Machine Learning

Background:

  • Limited training data hinders effective electroencephalography (EEG)-based emotion recognition models.
  • Generative models show promise in overcoming data scarcity in various fields, including image processing.

Purpose of the Study:

  • To propose a novel data augmentation model, VAE-D2GAN, for improving EEG-based emotion recognition.
  • To address the challenge of insufficient training samples in EEG emotion recognition.

Main Methods:

  • Extracted EEG features as topological maps of differential entropy (DE) across five frequency bands.
  • Developed a Variational Auto-Encoder (VAE) integrated into a dual discriminator Generative Adversarial Network (GAN) to learn data distributions and generate diverse artificial samples.
Keywords:
data augmentationelectroencephalography (EEG)emotion recognitiongenerative adversarial network (GAN)variational auto encoder (VAE)

More Related Videos

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

13.8K

Related Experiment Videos

Last Updated: Oct 8, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.4K
Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

13.8K
  • Employed VAE-D2GAN for data augmentation in EEG emotion recognition.

    • Main Results:

    • Achieved recognition accuracies of 92.5% on the SEED dataset and 82.3% on the SEED-IV dataset.
    • Demonstrated a performance improvement of 1.5% and 3.5% compared to methods without data augmentation.
    • Validated the effectiveness of generated artificial samples in enhancing EEG emotion recognition.

    Conclusions:

    • The VAE-D2GAN model successfully generates artificial EEG samples that significantly improve emotion recognition accuracy.
    • Data augmentation using VAE-D2GAN is a viable strategy to overcome data limitations in EEG-based emotion recognition.
    • The proposed method offers a promising solution for developing more robust and accurate EEG emotion recognition systems.