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

You might also read

Related Articles

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

Sort by

Same author

Search-guided regression ensembles for accurate, interpretable, and uncertainty-aware construction cost estimation.

Scientific reports·2026

Same author

Domain generalized feature embedded learning for calibration-free event-related potentials recognition.

Cognitive neurodynamics·2026

Same author

Entomopathogenic Potential of a Species of Serratia marcescens Originating from the Gut of Melon Fly: Isolation, Characterization and Effect of Oral Administration.

Journal of experimental zoology. Part A, Ecological and integrative physiology·2026

Same author

Uncertainty aware and explainable construction cost prediction using a hybrid probabilistic learning model.

Scientific reports·2026

Same author

Torque teno virus in the lower respiratory tract: association with immunosuppression but not mortality in severe pneumonia-a multicenter retrospective cohort study.

European journal of clinical microbiology & infectious diseases : official publication of the European Society of Clinical Microbiology·2026

Same author

[Design of a bedsheet specifically for the integrated external counterpulsation device].

Zhonghua wei zhong bing ji jiu yi xue·2026

Same journal

Predicting vasovagal syncope during head-up tilt test: three machine learning approaches.

Frontiers in neuroinformatics·2026

Same journal

Decoding basal ganglia motor circuit dysfunction from handwriting: a physics-informed neural signal interpretation framework for Parkinson's disease screening.

Frontiers in neuroinformatics·2026

Same journal

FUSION-AD: interpretable AI framework for risk assessment and subgroup discovery in Alzheimer's disease.

Frontiers in neuroinformatics·2026

Same journal

A 3D-printed phantom to validate subject orientation in 3D imaging and recordings.

Frontiers in neuroinformatics·2026

Same journal

IntegriLAB: a blockchain-enabled electronic lab notebook for reproducible neuroimaging research.

Frontiers in neuroinformatics·2026

Same journal

Long-range correlations in alpha-band of electroencephalogram: a nonlinear embedding and detrended fluctuation analysis.

Frontiers in neuroinformatics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 21, 2025

Cortical Source Analysis of High-Density EEG Recordings in Children

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

EEG Signal Reconstruction Using a Generative Adversarial Network With Wasserstein Distance and

Tian-Jian Luo^1,2,3, Yachao Fan², Lifei Chen^1,3

¹College of Mathematics and Informatics, Fujian Normal University, Fuzhou, China.

Frontiers in Neuroinformatics

|May 20, 2020

Summary

This summary is machine-generated.

This study introduces a new method for reconstructing electroencephalography (EEG) signals using generative adversarial networks and a novel loss function. This approach enhances brain-computer interface systems by improving classification accuracy while maintaining low costs.

Keywords:

EEG signals reconstruction Wasserstein distance generative adversarial network sampling rate sensitivity

More Related Videos

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Related Experiment Videos

Last Updated: Dec 21, 2025

Cortical Source Analysis of High-Density EEG Recordings in Children

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Area of Science:

Neuroscience
Biomedical Engineering
Signal Processing

Background:

Electroencephalography (EEG) signal applications face a trade-off between high performance and low cost.
Conventional EEG signal reconstruction methods often lose critical brain activity details and retain artifacts due to limitations in minimizing temporal mean-squared-error (MSE).
High sampling rates and sensitivity in EEG signal reconstruction present significant challenges.

Purpose of the Study:

To develop a novel EEG signal reconstruction algorithm that overcomes the limitations of conventional methods.
To improve the classification performance of reconstructed EEG signals.
To enable high-performance brain-computer interface (BCI) systems with reduced costs.

Main Methods:

Introduction of a novel reconstruction algorithm utilizing Wasserstein distance-based Generative Adversarial Networks (WGAN).
Implementation of a temporal-spatial-frequency (TSF-MSE) loss function for signal reconstruction.
TSF-MSE loss function computes MSE across time-series, common spatial pattern, and power spectral density features, unlike conventional temporal MSE.

Main Results:

The proposed WGAN with TSF-MSE loss function demonstrated promising reconstruction and classification results on motor-related EEG datasets.
Significant improvements in classification performance were observed for reconstructed EEG signals at the same sensitivity.
Average classification accuracy improvements were noted for reconstructed EEG signals with varying sensitivities.

Conclusions:

The WGAN reconstruction model with TSF-MSE loss function effectively addresses the contradiction between high classification performance and low cost in EEG applications.
The method facilitates the design of high-performance and cost-effective brain-computer interface systems.
This approach offers a superior alternative to conventional reconstruction algorithms for detailed and artifact-free EEG signal representation.