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 Experiment Videos

MSBiLSTM-Attention: EEG Emotion Recognition Model Based on Spatiotemporal Feature Fusion.

Yahong Ma1, Zhentao Huang1, Yuyao Yang1

  • 1Xi'an Key Laboratory of High Precision Industrial Intelligent Vision Measurement Technology, School of Electronic Information, Xijing University, Xi'an 710123, China.

Biomimetics (Basel, Switzerland)
|March 26, 2025
PubMed
Summary

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

Reliability-Aware Neural Decoding with Adaptive Multi-Source Information Fusion.

Entropy (Basel, Switzerland)·2026
Same author

MASleepNet: A Sleep Staging Model Integrating Multi-Scale Convolution and Attention Mechanisms.

Biomimetics (Basel, Switzerland)·2025
Same author

Emotion Recognition Model of EEG Signals Based on Double Attention Mechanism.

Brain sciences·2025
Same author

Neural specialization with generalizable representations underlies children's cognitive development of attention.

The American psychologist·2024
Same author

Development of the triadic neural systems involved in risky decision-making during childhood.

Developmental cognitive neuroscience·2024
Same author

Structural connectome architecture shapes the maturation of cortical morphology from childhood to adolescence.

Nature communications·2024
Same journal

Multiphysics Investigation on Thermal Characteristics of Internal Bio-Inspired V-Ribbed Cooling Channels for Outer Rotor PMSM.

Biomimetics (Basel, Switzerland)·2026
Same journal

Smart Logistics Model for Supply Chain Management via Brain-Inspired Geometric Deep Networks.

Biomimetics (Basel, Switzerland)·2026
Same journal

A Systematic Taxonomy of the Sunflower Optimization Algorithm: Variants, Hybridization Strategies, Applications, and Research Directions.

Biomimetics (Basel, Switzerland)·2026
Same journal

Toward a Compositional Theory of Trust in Embodied Intelligence: A QNLP Framework for Modeling Context, Interaction, and Trustworthiness.

Biomimetics (Basel, Switzerland)·2026
Same journal

Empirical Logic for Bio-Inspired Soft Computing: Illustrative Applications in Control Engineering and Cluster Analysis.

Biomimetics (Basel, Switzerland)·2026
Same journal

A Modified Multi-Strategy Dhole Optimization Algorithm and Its Engineering Applications.

Biomimetics (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces a novel deep learning model for accurate emotion recognition from electroencephalogram (EEG) signals. The MSBiLSTM-Attention model automates feature extraction and classification, achieving high accuracy in emotion analysis.

Area of Science:

  • Artificial Intelligence
  • Neuroscience
  • Human-Computer Interaction

Background:

  • Emotional states significantly influence decision-making and social interactions.
  • Sentiment analysis is crucial for human-computer emotional engagement, driving AI research.
  • EEG-based emotion analysis faces challenges in feature extraction and classifier design.

Purpose of the Study:

  • To develop a novel deep learning technique for automatic EEG feature extraction and classification.
  • To improve the accuracy and convenience of EEG-based emotion recognition.
  • To address limitations of manual preprocessing in existing deep learning approaches.

Main Methods:

  • A novel deep learning model integrating multi-scale convolution and bidirectional long short-term memory networks with an attention mechanism (MSBiLSTM-Attention).
Keywords:
attention mechanismbidirectional long short-term memory (Bi-LSTM)convolutional neural network (CNN)emotion recognitionmulti-scale

Related Experiment Videos

  • Automatic extraction and merging of spatiotemporal features from raw EEG data.
  • Classification of emotional EEG signals using a fully connected layer after attention-based feature selection.

    • Main Results:

    • The MSBiLSTM-Attention model achieved high classification accuracies on the SEED dataset.
    • Single validation accuracies reached 99.44% for three-class and 99.85% for four-class emotion tasks.
    • Average 10-fold cross-validation accuracies were 99.49% (three-class) and 99.70% (four-class).

    Conclusions:

    • The proposed MSBiLSTM-Attention model demonstrates effectiveness in EEG-based emotion recognition.
    • This approach offers a powerful solution for automated emotion analysis from neural signals.
    • The findings highlight the potential of deep learning with attention mechanisms for advancing affective computing.