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 interpretable machine learning framework for classifying human and machine translations across genres.

Frontiers in artificial intelligence·2026
Same author

Using machine learning to identify individuals at elevated risk of diabetes from low-cost complete blood count data for opportunistic screening.

Scientific reports·2026
Same author

DuA: Dual Attentive Transformer in Long-Term Continuous EEG Emotion Analysis.

IEEE journal of biomedical and health informatics·2026
Same author

Occupational Exposures in the Culinary Underbelly: Air Pollution in Restaurants.

Environmental science & technology·2026
Same author

High Efficiency Hole-Transport-Layer-Free Sb<sub>2</sub>S<sub>3</sub> Solar Cells via Platinum Back-Surface Doping.

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

Efficacy and safety of FLT3 inhibitors for acute myeloid leukemia: a network meta-analysis.

Frontiers in oncology·2026

Related Experiment Video

Updated: Aug 8, 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

Discrepancy between inter- and intra-subject variability in EEG-based motor imagery brain-computer interface:

Gan Huang1,2, Zhiheng Zhao1,2, Shaorong Zhang1,2,3

  • 1School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, China.

Frontiers in Neuroscience
|March 2, 2023
PubMed
Summary

Inter- and intra-subject variability in Brain-Computer Interfaces (BCI) hinder machine learning generalization. This study reveals distinct feature distribution changes in cross-subject versus cross-session electroencephalography (EEG) data, guiding improved BCI transfer learning methods.

Keywords:
brain-computer interfaceelectroencephalography (EEG)inter- and intra-subject variabilitymotor imagerysensorimotor rhythms (SMR)

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

1.3K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

942

Related Experiment Videos

Last Updated: Aug 8, 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
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

1.3K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

942

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Inter- and intra-subject variability in electroencephalography (EEG) signals significantly challenge the generalization of machine learning models in Brain-Computer Interfaces (BCI).
  • Existing transfer learning methods offer partial compensation, yet a clear understanding of feature distribution shifts in cross-subject and cross-session EEG data remains elusive.
  • This variability limits the practical application of BCI technologies.

Purpose of the Study:

  • To investigate the distinct feature distribution changes between cross-subject and cross-session EEG signals.
  • To enhance the understanding of inter- and intra-subject variability in motor-imagery BCI.
  • To provide insights for developing more effective transfer learning strategies for BCI.

Main Methods:

  • An online platform for motor-imagery BCI decoding was developed.
  • EEG data from multi-subject (Exp1) and multi-session (Exp2) experiments were analyzed.
  • Time-frequency responses and Common Spatial Pattern (CSP) feature standard deviations were compared across experimental conditions.

Main Results:

  • Within-subject EEG time-frequency responses in multi-session experiments were more consistent than in multi-subject experiments, despite similar classification result variability.
  • A significant difference in the standard deviation of CSP features was observed between cross-subject and cross-session analyses.
  • Different training sample selection strategies are recommended for cross-subject versus cross-session BCI model training.

Conclusions:

  • The findings deepen the understanding of inter- and intra-subject variability in EEG-based BCI.
  • These results offer practical guidance for the development of novel transfer learning methods in BCI.
  • BCI inefficiency is not attributed to the subject's inability to generate event-related desynchronization/synchronization (ERD/ERS) signals during motor imagery.