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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

PSWGAN-GP and MedicalDISTS synergistic optimization framework for few-shot fetal ultrasound image augmentation.

Biomedical physics & engineering express·2026
Same author

Activating ZBP1-centered PANoptosis and a collaborative innate-adaptive immune response sensitizes glioblastoma to PD-1 blockade.

Drug resistance updates : reviews and commentaries in antimicrobial and anticancer chemotherapy·2026
Same author

Hypothalamic arcuate microglia in sepsis: AgRP circuit engagement and ARHGAP24-dependent remodeling.

Journal of neuroinflammation·2026
Same author

Semaglutide treatment reverses HFD induced hippocampal microglia activation and improves cognitive dysfunction.

Tissue & cell·2026
Same author

Influence of Stabilizers, Milk Proteins, and Heat Treatment on the Tribology and Rheology of Drinking Yogurt.

Journal of food science·2026
Same author

Shenqi Dihuang Decoction Attenuates ALOX5-Mediated Ferroptosis in Diabetic Nephropathy via AMPK/mTOR and TGF-<i>β</i>/Smads Pathways.

Journal of diabetes research·2026

Related Experiment Video

Updated: Jan 7, 2026

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.3K

EEG emotion recognition based on hierarchical multi-scale graph neural networks.

Wenjuan Gu1, Junxiang Peng1, Shiying Ma1

  • 1Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, 650500 China.

Cognitive Neurodynamics
|December 29, 2025
PubMed
Summary

This study introduces a Hierarchical Multi-Scale Graph Neural Network (HMSGNN) for advanced emotion recognition using electroencephalogram (EEG) signals. The novel method significantly improves accuracy and robustness in classifying emotions from brain activity.

Keywords:
EEG signalEmotion recognitionGraph convolutional networksHierarchical multi-scale modelingSESimpli-transformer

More Related Videos

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

5.2K
Investigating Social Cognition in Infants and Adults Using Dense Array Electroencephalography dEEG
12:48

Investigating Social Cognition in Infants and Adults Using Dense Array Electroencephalography dEEG

Published on: June 27, 2011

18.2K

Related Experiment Videos

Last Updated: Jan 7, 2026

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.3K
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

5.2K
Investigating Social Cognition in Infants and Adults Using Dense Array Electroencephalography dEEG
12:48

Investigating Social Cognition in Infants and Adults Using Dense Array Electroencephalography dEEG

Published on: June 27, 2011

18.2K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Signal Processing

Background:

  • Emotion recognition leverages electroencephalogram (EEG) signals for direct brain activity insights.
  • Existing graph neural network (GNN) methods struggle with spatiotemporal dependencies and cross-regional interactions in EEG data.
  • Limitations in current GNNs hinder accuracy and robustness in EEG-based emotion recognition.

Purpose of the Study:

  • To develop an advanced model for enhanced emotion recognition from EEG signals.
  • To overcome limitations of existing GNNs in capturing complex spatiotemporal EEG dynamics.
  • To improve the accuracy and robustness of emotion recognition systems.

Main Methods:

  • Proposes a novel Hierarchical Multi-Scale Graph Neural Network (HMSGNN).
  • Employs multi-level feature extraction, from local to global, to model EEG signals.
  • Enhances spatiotemporal feature modeling capabilities for improved signal analysis.

Main Results:

  • HMSGNN achieved high subject-dependent accuracies: 98.67% (SEED) and 85.72% (SEED-IV).
  • Subject-independent experiments yielded accuracies of 87.11% (SEED) and 76.14% (SEED-IV).
  • Results represent the highest accuracies among compared methods with comparable or lower variance.

Conclusions:

  • HMSGNN effectively enhances spatiotemporal feature modeling for EEG signals.
  • The proposed method significantly improves accuracy and robustness in emotion recognition.
  • HMSGNN demonstrates state-of-the-art performance in both subject-dependent and independent settings.