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

Six anthropometric indices and all-cause mortality in ageing populations: an observational cohort study in six longitudinal studies.

BMC public health·2026
Same author

A Wearable Bioelectronic Patch With Adaptive Photodynamic and Electrical Stimulation for Drug-Resistant Bacteria Infected Burn Wound Healing.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

[A time-frequency transform and Riemannian manifold-based domain adaptation method for motor imagery in brain source space].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same author

Integrated Proteomic and Metabolomic Profiling for Developing Novel Plasma-Based Diagnostic Models of Sarcopenia.

Journal of cachexia, sarcopenia and muscle·2026
Same author

Targeting TFAP2β condensation suppresses the development of esophageal squamous cell carcinoma.

Cell·2025
Same author

Plasma Proteomic High-Performance Biomarkers for Early Diagnosis of Colorectal Cancer.

Journal of proteome research·2025

Related Experiment Video

Updated: Oct 1, 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

1.2K

[Parameter transfer learning based on shallow visual geometry group network and its application in motor imagery

Dongqin Xu1, Ming'ai Li1,2,3

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

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi = Journal of Biomedical Engineering = Shengwu Yixue Gongchengxue Zazhi
|March 1, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a parameter transfer learning method (PTL-sVGG) for motor imagery electroencephalography (MI-EEG) brain-computer interface (BCI) systems. The approach enhances cross-subject model transfer, improving BCI rehabilitation efficiency.

Keywords:
Motor imageryParameter transfer learningPearson correlation coefficientTransfer strategyVisual geometry group network

More Related Videos

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Related Experiment Videos

Last Updated: Oct 1, 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

1.2K
Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Neuroscience

Background:

  • Motor imagery electroencephalography (MI-EEG) is crucial for brain-computer interface (BCI) rehabilitation systems.
  • Transfer learning significantly impacts BCI performance, with source domain models and transfer strategies being key factors.
  • Existing methods face challenges in efficient and effective cross-subject model transfer.

Purpose of the Study:

  • To propose a novel parameter transfer learning method (PTL-sVGG) for MI-EEG-based BCI systems.
  • To enhance the transfer efficiency and performance of target domain models across different subjects.
  • To reduce the calibration time and promote the application of BCI technology in rehabilitation.

Main Methods:

  • Developed a parameter transfer learning method (PTL-sVGG) using a shallow visual geometry group network.
  • Screened source domain subjects using Pearson correlation and processed MI-EEG data into time-frequency spectrogram images (TFSI).
  • Employed a block-based frozen-fine-tuning strategy for efficient model parameter transfer across subjects.

Main Results:

  • Achieved an average recognition rate of 94.9% and a Kappa value of 0.898 on public MI-EEG datasets.
  • Demonstrated that subject optimization improves source domain model performance.
  • Showcased enhanced transfer efficiency and effective cross-subject parameter transfer, even with varying channel numbers.

Conclusions:

  • The PTL-sVGG method effectively transfers model parameters across subjects in MI-EEG BCI systems.
  • Subject optimization and block-based transfer strategies are beneficial for improving model performance and transfer efficiency.
  • This approach facilitates reduced BCI system calibration time, promoting wider adoption in rehabilitation engineering.