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

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Healthcare utilization patterns and diagnostic delays among international migrant workers with imported malaria in China: a retrospective cohort analysis.

Malaria journal·2026

Same author

VE-MLM: A variable endmember-based multilinear mixing framework for crop FAPAR estimation using UAV multispectral imagery.

Plant phenomics (Washington, D.C.)·2026

Same author

Injectable Thermal-Protective Hydrogel Enables Curative Tumor Ablation via Chemo-Immunomodulation.

ACS applied materials & interfaces·2026

Same author

Berberine Hydrochloride Induces Apoptosis in Triple-Negative Breast Cancer Cells Through Modulation of the sirtuin/p65 Signaling Axis.

Xenobiotica; the fate of foreign compounds in biological systems·2026

Same author

A Color Preference Recognition System for Children with Autism Spectrum Disorder Based on Fully Flexible Triboelectric Sensors and Artificial Intelligence Technology.

ACS applied materials & interfaces·2026

Same author

Primary diffuse large B-cell lymphoma of the rectus abdominis muscle: a presumed primary case report and literature review.

Frontiers in oncology·2026

Search research articles

Related Experiment Video

Updated: Aug 9, 2025

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Convolutional Neural Network with a Topographic Representation Module for EEG-Based Brain-Computer Interfaces.

Xinbin Liang¹, Yaru Liu¹, Yang Yu¹

¹College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China.

|February 25, 2023

Summary

This summary is machine-generated.

Convolutional neural networks (CNNs) for brain-computer interfaces (BCIs) can now better process electroencephalogram (EEG) signals. A new topographic representation module (TRM) enhances CNNs by incorporating spatial information, improving classification accuracy without altering network structure.

Keywords:

EEG decoding brain–computer interface (BCI)convolutional neural network (CNN)deep learning electroencephalogram (EEG)topographic representation

More Related Videos

Wholemount Immunohistochemistry for Revealing Complex Brain Topography

Wholemount Immunohistochemistry for Revealing Complex Brain Topography

Published on: April 5, 2012

Assessment and Communication for People with Disorders of Consciousness

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

Related Experiment Videos

Last Updated: Aug 9, 2025

Revealing Neural Circuit Topography in Multi-Color

Revealing Neural Circuit Topography in Multi-Color

Published on: November 14, 2011

Wholemount Immunohistochemistry for Revealing Complex Brain Topography

Wholemount Immunohistochemistry for Revealing Complex Brain Topography

Published on: April 5, 2012

Assessment and Communication for People with Disorders of Consciousness

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

Area of Science:

Neuroscience
Machine Learning
Biomedical Engineering

Background:

Convolutional neural networks (CNNs) show promise in brain-computer interfaces (BCIs) for processing electroencephalogram (EEG) signals.
Current CNNs often neglect the spatial topological information of EEG electrodes, processing signals as 2-D matrices.
This limitation can hinder classification performance by failing to leverage the full spatial context of brain activity.

Purpose of the Study:

To develop a CNN module that integrates spatial topological features from raw EEG signals.
To enhance the classification performance of existing CNN architectures for BCIs.
To maintain the original structure of CNNs when incorporating the new topographic representation module.

Main Methods:

Proposed an EEG topographic representation module (TRM) comprising a mapping block to a 3-D topographic map and a convolution block.
Designed two TRM variants: TRM-(5,5) and TRM-(3,3), differing in convolutional kernel size.
Integrated TRMs into ShallowConvNet, DeepConvNet, and EEGNet, and evaluated on the Emergency Braking During Simulated Driving Dataset (EBDSDD) and High Gamma Dataset (HGD).

Main Results:

All tested CNNs demonstrated improved classification accuracy on both EBDSDD and HGD datasets after TRM integration.
TRM-(5,5) improved accuracies by up to 6.54% (DeepConvNet on EBDSDD) and 6.05% (DeepConvNet on HGD).
TRM-(3,3) yielded even greater improvements, up to 7.76% (DeepConvNet on EBDSDD) and 7.61% (DeepConvNet on HGD).

Conclusions:

The proposed TRM effectively captures and utilizes spatial topological EEG information to enhance CNN classification performance.
TRMs can be seamlessly integrated into existing CNN architectures without structural modifications, offering a versatile enhancement.
This approach significantly boosts the efficacy of EEG-based BCIs by leveraging both temporal and spatial signal characteristics.