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

Hybrid zeolitic imidazolate frameworks with catalytically active TO4 building blocks.

Angewandte Chemie (International ed. in English)·2010

Same author

Whiter matter abnormalities in medication-naive subjects with a single short-duration episode of major depressive disorder.

Psychiatry research·2010

Same author

A new comorbidity index: the health-related quality of life comorbidity index.

Journal of clinical epidemiology·2010

Same author

S-adenosylmethionine inhibits the growth of cancer cells by reversing the hypomethylation status of c-myc and H-ras in human gastric cancer and colon cancer.

International journal of biological sciences·2010

Same author

Nano-sized SnSbAgx alloy anodes prepared by reductive co-precipitation method used as lithium-ion battery materials.

Journal of nanoscience and nanotechnology·2010

Same author

Complementary diffusion tensor imaging study of the corpus callosum in patients with first-episode and chronic schizophrenia.

Journal of psychiatry & neuroscience : JPN·2010

Same journal

Vowel acoustic parameters in speech assessment and rehabilitation of minimally verbal and speech-motor-impaired autistic children: a narrative review.

Frontiers in human neuroscience·2026

Same journal

Toward clinical translation of TMS-EEG: an integrative review of multidimensional neurophysiological measures.

Frontiers in human neuroscience·2026

Same journal

The causal efficacy of consciousness: a neuroscientific analysis and explanation.

Frontiers in human neuroscience·2026

Same journal

Temporal-oscillatory entrainment: a multi-timescale framework for rhythmic coordination from neural to social frequencies.

Frontiers in human neuroscience·2026

Same journal

Role of AQP4 in ameliorating heat stress-induced cellular injury in a cell line model through active heat acclimation.

Frontiers in human neuroscience·2026

Same journal

Correction: Cognitive state monitoring for neuroadaptive information visualization.

Frontiers in human neuroscience·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 31, 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

STGATE: Spatial-temporal graph attention network with a transformer encoder for EEG-based emotion recognition.

Jingcong Li¹, Weijian Pan¹, Haiyun Huang¹

¹School of Software, South China Normal University, Guangzhou, China.

Frontiers in Human Neuroscience

|May 1, 2023

Summary

This summary is machine-generated.

We developed a new AI model, the spatial-temporal graph attention network with a transformer encoder (STGATE), for analyzing electroencephalogram (EEG) signals. This model significantly improves emotion recognition accuracy from brainwaves.

Keywords:

EEG EEG-based emotion classification deep learning graph neural network transformer encoder

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

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Published on: November 16, 2017

Related Experiment Videos

Last Updated: Jul 31, 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

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Central and Divided Visual Field Presentation of Emotional Images to Measure Hemispheric Differences in Motivated Attention

Published on: November 16, 2017

Area of Science:

Neuroscience
Artificial Intelligence
Machine Learning

Background:

Electroencephalogram (EEG) is a vital tool in neuroscience for studying brain activity.
Accurate emotion recognition from EEG signals remains a challenge, particularly across different individuals.

Purpose of the Study:

To introduce a novel deep learning model, the spatial-temporal graph attention network with a transformer encoder (STGATE), for enhanced EEG-based emotion recognition.
To improve the accuracy and robustness of cross-subject emotion recognition using graph representations of EEG data.

Main Methods:

Utilized a transformer encoder to capture time-frequency features from EEG signals.
Employed a spatial-temporal graph attention mechanism with a dynamic adjacency matrix to model inter-channel relationships.
Evaluated the STGATE model on three public datasets (SEED, SEED-IV, DREAMER) using leave-one-subject-out cross-validation.

Main Results:

Achieved state-of-the-art cross-subject emotion recognition accuracies: 90.37% on SEED, 76.43% on SEED-IV, and 76.35% on DREAMER.
Demonstrated the model's ability to adaptively learn intrinsic connections between EEG channels.
Validated the effectiveness of STGATE for generalized emotion recognition across diverse subjects.

Conclusions:

The proposed STGATE model offers a powerful approach for EEG-based emotion recognition.
This graph-based method shows significant potential for advancing neuroscience research and brain-computer interfaces.
STGATE effectively captures complex spatial-temporal dynamics in EEG for improved emotion classification.