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 Video

Updated: Jun 28, 2026

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

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

Published on: October 24, 2012

Modeling multiscale neural dynamics for EEG-based emotion recognition using an attentive wavelet-transformer

R S Soundariya1, P Thangaraj2

  • 1Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Sathyamangalam, Tamil Nadu, India.

Frontiers in Computational Neuroscience
|June 25, 2026
PubMed
Summary
This summary is machine-generated.

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

EEG-based dynamic emotion recognition using multi-scale wavelet transform with a Spatio-Temporal neural network.

Scientific reports·2026
Same author

Ensemble fuzzy multilayer neural perceptron with optimized feature selection for cardiac disease prediction using MRI and ECG data.

Frontiers in physiology·2026
Same author

A Computer Aided Diagnosis System for Identifying Alzheimer's from MRI Scan using Improved Adaboost.

Journal of medical systems·2019
Same author

Study of soy-fortified green tea curd formulated using potential hypocholesterolemic and hypotensive probiotics isolated from locally made curd.

Food chemistry·2018
Same journal

Detection and localization of conspecifics in ghost knifefish are influenced by the relationship between the spatial organization of receptors and signals.

Frontiers in computational neuroscience·2026
Same journal

Learning under constraints: a theoretical framework for comparing resource-constrained learning in biological and artificial systems.

Frontiers in computational neuroscience·2026
Same journal

MsGCN: a multi-stream graph convolutional network for multiband PLV graph fusion in EEG-based biometric identification.

Frontiers in computational neuroscience·2026
Same journal

AI-driven neuroanalytic modeling for mental health: multichannel CNN-based autism spectrum disorder detection via facial pattern analysis.

Frontiers in computational neuroscience·2026
Same journal

New directions for complex systems in contemporary neuroscience: a morphodynamic and emergent function approach.

Frontiers in computational neuroscience·2026
Same journal

NMDA receptor kinetics drive distinct routes to chaotic firing in pyramidal neurons.

Frontiers in computational neuroscience·2026
See all related articles

The Attentive Wavelet-Transformer Network (AWT-Net) significantly improves electroencephalography (EEG)-based emotion recognition by reducing noise and inter-subject variability. This novel framework achieves high accuracy, paving the way for advanced affective computing and clinical diagnostics.

Area of Science:

  • Neuroscience
  • Computer Science
  • Signal Processing

Background:

  • Electroencephalography (EEG)-based emotion recognition is crucial for affective computing and clinical diagnostics.
  • Existing methods struggle with EEG signal noise, non-stationarity, inter-subject variability, and class imbalance.
  • These challenges limit the practical application and accuracy of current EEG emotion recognition systems.

Purpose of the Study:

  • To introduce a novel framework, the Attentive Wavelet-Transformer Network (AWT-Net), to overcome limitations in EEG-based emotion recognition.
  • To enhance signal processing and feature extraction for more robust emotion recognition.
  • To improve the accuracy and generalizability of EEG emotion recognition models.

Main Methods:

  • The Attentive Wavelet-Transformer Network (AWT-Net) integrates Hierarchical Wavelet Packet Decomposition (HWPD), Empirical Wavelet Transform with Kalman filtering (EWT-Kalman), Multi-Head Self-Attention (MHSA), and a Hybrid Spatio-Temporal Transformer (HSTT).
Keywords:
affective computingdeep learningelectroencephalography (EEG)emotion recognitionmultiscale neural dynamicsspatio-temporal modellingtransformer networkswavelet transform

Related Experiment Videos

Last Updated: Jun 28, 2026

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

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

Published on: October 24, 2012

  • The model employs an adaptive focal loss function to address class imbalance.
  • Evaluations were conducted on a custom EEG dataset and the publicly available DEAP dataset.

    • Main Results:

    • AWT-Net achieved high window-level, subject-dependent accuracies: 99.61% on DEAP and 99.34% on the custom EEG dataset.
    • Under stricter protocols, accuracies were 99.30% (trial-wise grouped) and 97.23% (subject-independent LOSO) on DEAP, demonstrating robust generalization.
    • Error rates were significantly reduced to 0.70% (custom EEG) and 0.39% (DEAP), compared to baseline models (6.69-10.58%).

    Conclusions:

    • AWT-Net effectively addresses challenges in EEG-based emotion recognition, including noise and inter-subject variability.
    • The framework demonstrates superior performance and generalization capabilities compared to existing baseline models.
    • AWT-Net shows significant potential for real-time emotion recognition applications in healthcare and human-computer interaction.