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

An adaptive session-incremental broad learning system for continuous motor imagery EEG classification.

Medical & biological engineering & computing·2024
Same author

Recognize enhanced temporal-spatial-spectral features with a parallel multi-branch CNN and GRU.

Medical & biological engineering & computing·2023
Same author

Applying correlation analysis to electrode optimization in source domain.

Medical & biological engineering & computing·2023
Same author

A novel decoding method for motor imagery tasks with 4D data representation and 3D convolutional neural networks.

Journal of neural engineering·2021
Same author

Augmented autophagy suppresses thymocytes development via Bcl10/p-p65 pathway in prenatal nicotine exposed fetal mice.

Ecotoxicology and environmental safety·2020
Same author

An Incremental Version of L-MVU for the Feature Extraction of MI-EEG.

Computational intelligence and neuroscience·2019
Same journal

Non-local modeling of enhancer-promoter interactions, a correspondence on "LOCO-EPI: Leave-one-chromosome-out (LOCO) as a benchmarking paradigm for deep learning based prediction of enhancer-promoter interactions".

Applied intelligence (Dordrecht, Netherlands)·2026
Same journal

Collaborative penetration testing suite for emerging generative AI algorithms.

Applied intelligence (Dordrecht, Netherlands)·2025
Same journal

AI-driven 5G IoT e-nose for whiskey classification.

Applied intelligence (Dordrecht, Netherlands)·2025
Same journal

DAGAF: A directed acyclic generative adversarial framework for joint structure learning and tabular data synthesis.

Applied intelligence (Dordrecht, Netherlands)·2025
Same journal

ROCIP: robust continuous inertial position tracking for complex actions emerging from the interaction of human actors and environment.

Applied intelligence (Dordrecht, Netherlands)·2025
Same journal

RETRACTED ARTICLE: Deep learning system to screen coronavirus disease 2019 pneumonia.

Applied intelligence (Dordrecht, Netherlands)·2024
See all related articles

Related Experiment Video

Updated: Aug 30, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

1.1K

A dual alignment-based multi-source domain adaptation framework for motor imagery EEG classification.

Dong-Qin Xu1, Ming-Ai Li1,2,3

  • 1Beijing, 100124 China Faculty of Information Technology, Beijing University of Technology.

Applied Intelligence (Dordrecht, Netherlands)
|August 30, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a dual alignment framework for motor imagery electroencephalography (MI-EEG) brain-computer interfaces, improving classification accuracy by effectively selecting and aligning informative source domains.

Keywords:
Domain adaptationMaximum mean discrepancyMotor imageryTransfer learningWeighted alignment

More Related Videos

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.8K
Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
09:42

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

1.4K

Related Experiment Videos

Last Updated: Aug 30, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

1.1K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.8K
Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
09:42

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

1.4K

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Neuroscience

Background:

  • Motor imagery electroencephalography (MI-EEG) based brain-computer interfaces (BCIs) face challenges due to data insufficiency and subject variability.
  • Existing domain adaptation methods primarily focus on aligning data and feature distributions, neglecting the selection of informative target samples and optimal source domains.

Purpose of the Study:

  • To propose a novel dual alignment-based multi-source domain adaptation framework (DAMSDAF) for enhancing MI-EEG classification.
  • To address the limitations of existing methods by aligning source domains with informative target samples and selecting optimal source domains.

Main Methods:

  • Continuous wavelet transform (CWT) converts MI-EEG signals into time-frequency spectrum images, constructing multi-source and target domains.
  • Entropy-based identification of informative target samples near the decision boundary for source domain alignment using normalized mutual information.
  • A multi-branch deep network (MBDN) with embedded maximum mean discrepancy (MMD) for feature distribution realignment, weighted prediction based on transfer accuracy, and automatic source domain selection.

Main Results:

  • DAMSDAF achieved high classification accuracies on three public MI-EEG datasets: 92.56%, 69.45%, and 89.57%.
  • Statistical analysis using kappa value and t-test confirmed significant improvements over existing methods.
  • The framework demonstrated effective utilization of weighted samples and source domains at different levels, enabling optimal multi-source domain selection.

Conclusions:

  • The proposed DAMSDAF framework significantly enhances transfer learning effects in MI-EEG BCIs.
  • Dual alignment effectively leverages informative target samples and optimally selects relevant source domains.
  • This approach offers a robust solution for data insufficiency and subject variability in BCI applications.