Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Tissue derived extracellular vesicles advance from disease mechanisms to clinical application.

Discover nano·2026

Same author

Blue Rubber Bleb Nevus Syndrome.

Radiographics : a review publication of the Radiological Society of North America, Inc·2026

Same author

Reorganization of Human Brain Waves Across Diverse States of Consciousness.

bioRxiv : the preprint server for biology·2026

Same author

Safety and efficacy of Da Vinci robot-assisted atrial septal defect repair in patients with different body mass index levels: a single-center retrospective analysis.

Journal of cardiothoracic surgery·2026

Same author

Risk factors for rebleeding at different time points after TIPS in cirrhotic patients with AEVB: A case-control study.

Medicine·2026

Same author

A retrospective study of the efficacy and safety of rituximab biosimilar for the treatment of membranous nephropathy.

BMC pharmacology & toxicology·2026

Search research articles

Related Experiment Video

Updated: Jun 18, 2025

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

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

Published on: December 15, 2023

EEG-based emotion recognition using graph convolutional neural network with dual attention mechanism.

Wei Chen¹, Yuan Liao¹, Rui Dai¹

¹College of Electronic and Optical Engineering & College of Flexible Electronics (Future Technology), Nanjing University of Posts and Telecommunications, Nanjing, China.

Frontiers in Computational Neuroscience

|August 5, 2024

Summary

This study introduces a Dual Attention Mechanism Graph Convolutional Neural Network (DAMGCN) for more interpretable electroencephalogram (EEG)-based emotion recognition. The model effectively identifies key brain regions and frequencies, achieving high accuracy in recognizing emotions from brain signals.

Keywords:

EEG attention mechanism electrode channels emotion recognition frequency bands graph convolutional neural network transformer

More Related Videos

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

Related Experiment Videos

Last Updated: Jun 18, 2025

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

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

Published on: December 15, 2023

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

Area of Science:

Neuroscience
Artificial Intelligence
Signal Processing

Background:

Electroencephalogram (EEG)-based emotion recognition is vital for brain-computer interfaces (BCIs).
Existing models often prioritize accuracy over interpretability, limiting understanding of underlying neural mechanisms.
Analyzing the influence of specific brain regions and frequency bands on emotion generation is crucial.

Purpose of the Study:

To propose a novel method, the Dual Attention Mechanism Graph Convolutional Neural Network (DAMGCN), for enhanced EEG-based emotion recognition.
To improve the interpretability of emotion recognition models by analyzing brain region and frequency band contributions.
To leverage graph convolutional networks and self-attention mechanisms for feature extraction and weighting.

Main Methods:

Utilized graph convolutional networks (GCNs) to model brain networks as graphs for spatial feature extraction.
Employed the self-attention mechanism from Transformer models to assign weights to electrode channels and frequency bands.
Visualized attention mechanisms to demonstrate learned weight allocations for key brain regions and frequencies.

Main Results:

Achieved state-of-the-art performance on the SEED dataset, with 99.42% accuracy in subject-dependent experiments and 73.21% in subject-independent experiments.
Demonstrated superior accuracy compared to most existing models in EEG-based emotion recognition.
The attention mechanism visualization provided insights into the model's decision-making process regarding brain regions and frequency bands.

Conclusions:

The DAMGCN model offers a significant advancement in EEG-based emotion recognition, balancing high accuracy with improved interpretability.
The approach effectively highlights the importance of specific brain regions and frequency bands in emotional processing.
This work paves the way for more transparent and reliable BCIs.