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

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

Biomimetics (Basel, Switzerland)·2026
Same author

Developing an Artificial Intelligence Solution to Autosegment the Edentulous Maxillary Bone for Implant Planning.

European journal of dentistry·2026
Same author

GAN-Based Cross-Modality Brain MRI Synthesis: Paired Versus Unpaired Training and Comparison with Diffusion and Transformer Models.

Biomimetics (Basel, Switzerland)·2026
Same author

An Intelligent Multi-Task Supply Chain Model Based on Bio-Inspired Networks.

Biomimetics (Basel, Switzerland)·2026
Same author

State-Dependent CNN-GRU Reinforcement Framework for Robust EEG-Based Sleep Stage Classification.

Biomimetics (Basel, Switzerland)·2026
Same author

A Bionic Sensing Platform for Cell Separation: Simulation of a Dielectrophoretic Microfluidic Device That Leverages Dielectric Fingerprints.

Biomimetics (Basel, Switzerland)·2025

Related Experiment Video

Updated: Jun 3, 2025

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

14.6K

Selective Auditory Attention Detection Using Combined Transformer and Convolutional Graph Neural Networks.

Masoud Geravanchizadeh1, Amir Shaygan Asl1, Sebelan Danishvar2

  • 1Faculty of Electrical & Computer Engineering, University of Tabriz, Tabriz 51666-15813, Iran.

Bioengineering (Basel, Switzerland)
|January 8, 2025
PubMed
Summary
This summary is machine-generated.

A new TraGCNN method effectively detects auditory attention from electroencephalograms (EEGs) without speech stimuli. This approach achieves 80.12% accuracy, outperforming existing methods and offering faster computation for BCI applications.

Keywords:
brain connectivityconvolutional neural networksgraph neural networkhybrid neural networksselective auditory attention detectiontransformer

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

463

Related Experiment Videos

Last Updated: Jun 3, 2025

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

14.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

463

Area of Science:

  • Neuroscience
  • Machine Learning
  • Signal Processing

Background:

  • Auditory attention is a crucial cognitive function for focusing on specific sounds in complex environments.
  • Existing methods for detecting auditory attention from electroencephalograms (EEGs) often rely on manual feature extraction or require speech stimuli.
  • Developing automated and efficient methods for auditory attention detection is vital for advancing brain-computer interfaces (BCIs) and hearing technologies.

Purpose of the Study:

  • To propose and evaluate a novel end-to-end method, the combined transformer and graph convolutional neural network (TraGCNN), for detecting auditory attention from EEGs.
  • To eliminate the need for manual feature extraction in auditory attention detection.
  • To assess the performance and computational efficiency of the TraGCNN model compared to existing methods.

Main Methods:

  • EEG signals were converted into graph representations.
  • Spatial and temporal features were extracted from the graph representations using transformer and graph convolutional layers.
  • The TraGCNN model was trained and tested on the Fuglsang 2020 dataset.

Main Results:

  • The TraGCNN approach achieved a classification accuracy of 80.12%, outperforming state-of-the-art methods.
  • The model demonstrated superior performance compared to a previous graph-based model across varying EEG segment lengths.
  • Auditory attention detection was achieved without the necessity of speech stimuli, a significant advantage over conventional methods.

Conclusions:

  • The proposed TraGCNN method offers an effective, automated, and efficient approach for detecting auditory attention from EEG signals.
  • The model's ability to function without speech stimuli and its computational efficiency have significant implications for real-world applications.
  • This research paves the way for improved BCI systems, speech separation technologies, and neuro-steered hearing aid development.