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: Nov 22, 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

1.5K

Adaptive transfer learning for EEG motor imagery classification with deep Convolutional Neural Network.

Kaishuo Zhang1, Neethu Robinson1, Seong-Whan Lee2

  • 1School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore.

Neural Networks : the Official Journal of the International Neural Network Society
|January 5, 2021
PubMed
Summary

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

Neuroscience-Inspired Hierarchical GNN for Grasping Attempt Classification.

IEEE journal of biomedical and health informatics·2026
Same author

Negative prompt-guided optimization: Enhancing soft prompt generalization in vision-language models.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

E2T: EEG-to-Trajectory Transformer for Motor Imagery-Based Fully-DoF Motion Prediction.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Leveraging contextual confidence for smarter retrieval in large language models.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Discovering Interpretable Semantics from Radio Signals for Contactless Cardiac Monitoring.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

SSF-SET: A Discrete EEG Token-based Framework for Sleep Stage Forecasting.

IEEE journal of biomedical and health informatics·2026

Deep learning Brain-Computer Interface (BCI) models struggle with limited individual data. This study introduces 5 adaptation schemes for Convolutional Neural Network (CNN) based electroencephalography (EEG)-BCI systems, significantly improving motor imagery decoding accuracy.

Area of Science:

  • Neuroscience
  • Machine Learning
  • Biomedical Engineering

Background:

  • Deep learning models for Brain-Computer Interface (BCI) systems show promise but are limited by subject-specific data availability.
  • Transfer learning approaches, while common, face challenges due to significant inter-subject variability in brain data.

Purpose of the Study:

  • To propose and evaluate 5 adaptation schemes for a deep Convolutional Neural Network (CNN) based electroencephalography (EEG)-BCI system.
  • To enhance the performance of EEG-BCI systems for decoding hand motor imagery (MI) in target subjects by fine-tuning pre-trained models.

Main Methods:

  • Development of 5 distinct adaptation schemes to fine-tune a pre-trained deep CNN model.
  • Application of these schemes to an EEG-BCI system for decoding two-class motor imagery.
Keywords:
Brain–computer interface (BCI)Convolutional Neural Network (CNN)Electroencephalography (EEG)Transfer learning

More Related Videos

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

1.8K

Related Experiment Videos

Last Updated: Nov 22, 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

1.5K
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

1.8K
  • Evaluation of performance on target subjects, comparing against baseline subject-independent models.

    • Main Results:

    • Achieved the highest reported subject-independent performance with an average accuracy of 84.19% (±9.98%) for two-class motor imagery.
    • Outperformed the current literature's best accuracy of 74.15% (±15.83%) on the same dataset.
    • Demonstrated statistically significant improvement (p=0.005) in classification accuracy using the proposed adaptation schemes.

    Conclusions:

    • The proposed adaptation schemes effectively address inter-subject variability in EEG data for BCI applications.
    • Fine-tuning pre-trained CNN models significantly enhances the performance of EEG-BCI systems for motor imagery decoding.
    • This work offers a promising direction for developing more robust and accurate subject-independent BCI systems.