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

Dynamic domain adaptive EEG emotion recognition based on multi-source selection.

The Review of scientific instruments·2025
Same author

P300 intention recognition based on phase lag index (PLI)-rich-club brain functional network.

The Review of scientific instruments·2024
Same author

A Novel Drinking Category Detection Method Based on Wireless Signals and Artificial Neural Network.

Entropy (Basel, Switzerland)·2022
Same author

Nasopharyngeal adenoid cystic carcinoma: magnetic resonance imaging features in ten cases.

Chinese journal of cancer·2011
Same author

Amyloid fibril formation by the glaucoma-associated olfactomedin domain of myocilin.

Journal of molecular biology·2011
Same author

Moxibustion down-regulates colonic epithelial cell apoptosis and repairs tight junctions in rats with Crohn's disease.

World journal of gastroenterology·2011
Same journal

Compressed multi-scale entropy and its application in mechanical fault diagnosis.

The Review of scientific instruments·2026
Same journal

Bidirectional drive and multi-resolution adjustment across frequency bands in inertial impact piezoelectric motors via multimodal resonant vibration.

The Review of scientific instruments·2026
Same journal

A magnetic field sensor based on flaky Terfenol-D material and dual fiber grating.

The Review of scientific instruments·2026
Same journal

A novel E-field eight-way cavity combiner for high-power S-band applications.

The Review of scientific instruments·2026
Same journal

Constant radius blade spring suspended bench for vibration isolation.

The Review of scientific instruments·2026
Same journal

Qualification of infrared optical fibers and emitters for a spectrometer for in situ planetary exploration: Results from the TRIS (TRansmission and Illumination System) project.

The Review of scientific instruments·2026
See all related articles

Related Experiment Video

Updated: Jan 12, 2026

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

10.6K

Emotion recognition based on microstate brain functional network using graph attention network.

Zhongmin Wang1,2,3, Zhao Feng1, Yan He1,2,3

  • 1School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an, Shaanxi 710121, China.

The Review of Scientific Instruments
|November 7, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel dynamic microstate temporal graph attention network (DMT-GAT) for precise emotion recognition using electroencephalogram (EEG) data. The DMT-GAT effectively decodes rapid emotional transitions and brain network dynamics.

More Related Videos

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.5K
Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation
08:50

Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation

Published on: August 20, 2019

15.0K

Related Experiment Videos

Last Updated: Jan 12, 2026

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

10.6K
Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.5K
Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation
08:50

Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation

Published on: August 20, 2019

15.0K

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Machine Learning

Background:

  • Electroencephalogram (EEG) signals offer high temporal resolution but limited spatial resolution for studying brain dynamics.
  • Identifying stable neural states during rapid emotional transitions and decoding interregional interactions remain significant challenges.
  • Existing methods struggle to capture millisecond-scale neural dynamics crucial for understanding affective transitions.

Purpose of the Study:

  • To develop a novel framework for high-resolution emotion recognition by integrating transient EEG microstates with brain functional networks.
  • To decode dynamic interregional interactions during emotional shifts with millisecond-scale precision.
  • To advance the understanding of neural mechanisms underlying affective transitions.

Main Methods:

  • Proposed a dynamic microstate temporal graph attention network (DMT-GAT) integrating EEG microstates and functional brain networks.
  • Segmented EEG signals into microstates (MS1-MS4), selected emotion-related microstates (MS3/MS4), and constructed brain functional networks using phase-locked value synchronization.
  • Integrated frequency-domain features into graph-structured data and employed a graph attention network (GAT) with multi-head mechanisms for emotion classification.

Main Results:

  • Achieved high average accuracies of 99.19% (valence) and 99.26% (arousal) on the DEAP dataset.
  • Maintained a robust accuracy of 95.29% on the SEED dataset for emotion classification.
  • Uniquely revealed prefrontal-amygdala interactions during emotional regulation, bridging dynamic brain networks and rapid neurodynamics.

Conclusions:

  • The DMT-GAT provides a novel and effective framework for high-resolution emotion recognition.
  • The study advances the understanding of neural mechanisms underlying affective transitions by capturing dynamic interregional interactions.
  • This approach offers a significant step forward in decoding complex brain dynamics related to emotions.