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

Effects of Environmental Arsenic Exposure on the Morphology of Multiple Organs in Female Mice During Pre-Pregnancy, Gestation, and Lactation.

Journal of applied toxicology : JAT·2026
Same author

Machine Learning Inverse Design Reveals a Double Narrow-Band Absorption Approach for Effective Colored Radiative Cooling Paints.

Nano letters·2026
Same author

Task-tailored Pre-processing: Fair Downstream Supervised Learning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

TRAF6, a gga-miR-7b Target, Promotes <i>Eimeria tenella</i>-Induced Inflammation and Apoptosis in Chickens by Activating NF-κB Pathway.

Biomolecules·2026
Same author

Association of 24-Hour Computed Tomography Infarct Density on Functional Outcomes in Stroke: Secondary Analysis From the AcT Trial.

Journal of the American Heart Association·2026
Same author

MPAN: A Multi-Prototype Adaptive Network for Few-Shot EEG-Based Biometric Recognition.

IEEE journal of biomedical and health informatics·2026
Same journal

Olfactory Perception and Neural Rhythms: A Simulation-Based EEG Analysis Using Power Spectral Density FeaturesOlfactory perception and neural rhythms: a simulation-based eeg analysis using power spectral density features.

Cognitive neurodynamics·2026
Same journal

An event-related potentials account of brain predictive coding.

Cognitive neurodynamics·2026
Same journal

A recurrent neural network model for a decision-making task based on sequential evidence accumulation.

Cognitive neurodynamics·2026
Same journal

Synaptic neurotransmitter concentration modulation during learning in bio-inspired spiking neural network.

Cognitive neurodynamics·2026
Same journal

A two-neuron HETUF-memristive hopfield neural network and its application in image encryption.

Cognitive neurodynamics·2026
Same journal

MEK-ERK inhibition enhances synaptic input-output coupling and neuronal excitability in the rat dentate gyrus: association with site-specific Kv4.2 phosphorylation.

Cognitive neurodynamics·2026
See all related articles

Related Experiment Video

Updated: Dec 4, 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

4.9K

EEG-based emotion recognition using 4D convolutional recurrent neural network.

Fangyao Shen1, Guojun Dai1,2, Guang Lin1

  • 1School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China.

Cognitive Neurodynamics
|October 26, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces a novel four-dimensional convolutional recurrent neural network (4D-CRNN) for enhanced electroencephalogram (EEG)-based emotion recognition. The method effectively integrates frequency, spatial, and temporal EEG data, achieving state-of-the-art accuracy.

Keywords:
4D dataConvolutional recurrent neural networkEEGEmotion recognition

More Related Videos

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.3K
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

14.2K

Related Experiment Videos

Last Updated: Dec 4, 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

4.9K
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.3K
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

14.2K

Area of Science:

  • Neuroscience
  • Machine Learning
  • Signal Processing

Background:

  • Electroencephalogram (EEG) signals offer a rich source of information for understanding human emotions.
  • Accurate EEG-based emotion recognition is crucial for applications in affective computing and brain-computer interfaces.
  • Existing methods often struggle to fully leverage the complex spatio-temporal and frequency characteristics inherent in multichannel EEG data.

Purpose of the Study:

  • To develop a novel deep learning model that explicitly integrates frequency, spatial, and temporal information from multichannel EEG signals.
  • To improve the accuracy of EEG-based emotion recognition by effectively utilizing these integrated features.
  • To validate the proposed model's performance on established EEG emotion recognition datasets.

Main Methods:

  • A four-dimensional convolutional recurrent neural network (4D-CRNN) architecture was proposed.
  • Differential entropy features from multichannel EEG signals were transformed into 4D structures to preserve frequency, spatial, and temporal information.
  • A hybrid model combining Convolutional Neural Networks (CNNs) for feature extraction and Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) cells for temporal dependency modeling was employed.
  • The CNN component processed frequency and spatial information within temporal slices, while the LSTM component captured temporal dynamics.

Main Results:

  • The 4D-CRNN model achieved state-of-the-art performance on both the SEED and DEAP datasets.
  • The model demonstrated superior accuracy in EEG-based emotion recognition under intra-subject settings.
  • Experimental results confirmed the effectiveness of integrating frequency, spatial, and temporal EEG information for improved emotion recognition.

Conclusions:

  • The proposed 4D-CRNN method effectively integrates multi-faceted EEG information for enhanced emotion recognition.
  • Explicitly incorporating frequency, spatial, and temporal features significantly boosts the accuracy of EEG-based emotion recognition.
  • The study highlights the potential of advanced deep learning architectures for analyzing complex neural signals in affective computing.