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: Aug 16, 2025

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.8K

Tangent space alignment: Transfer learning for Brain-Computer Interface.

Alexandre Bleuzé1, Jérémie Mattout2, Marco Congedo1

  • 1GIPSA-Lab, University Grenoble Alpes, CNRS, Grenoble INP, Grenoble, France.

Frontiers in Human Neuroscience
|December 19, 2022
PubMed
Summary
This summary is machine-generated.

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

Modification of cortical activation pattern after long-term BCI training and its impact on decoding model performances.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Disorder of consciousness rather than complete Locked-In Syndrome for end stage Amyotrophic Lateral Sclerosis: a case series.

Communications medicine·2025
Same author

Systematic Review and Meta-Analysis of Mismatch Negativity in Autism: Insights Into Predictive Mechanisms.

Autism research : official journal of the International Society for Autism Research·2025
Same author

EEG-Metabolic Coupling and Time Limit at V˙O<sub>2</sub>max During Constant-Load Exercise.

Journal of functional morphology and kinesiology·2025
Same author

The Mismatch Negativity Compared: EEG, SQUID-MEG, and Novel <sup>4</sup>Helium-OPMs.

Human brain mapping·2025
Same author

Surfing beta burst waveforms to improve motor imagery-based BCI.

Imaging neuroscience (Cambridge, Mass.)·2025
Same journal

Role of AQP4 in ameliorating heat stress-induced cellular injury in a cell line model through active heat acclimation.

Frontiers in human neuroscience·2026
Same journal

Correction: Cognitive state monitoring for neuroadaptive information visualization.

Frontiers in human neuroscience·2026
Same journal

The synthetic self-hypothesis: dopaminergic redirection through self-face recognition in stuttering therapy.

Frontiers in human neuroscience·2026
Same journal

A randomised, placebo-controlled, triple-blind clinical trial to investigate the efficacy of <i>Ginkgo biloba</i> extract EGb 761<sup>®</sup> in cognitive impairment associated with post COVID-19 syndrome-the EGb COCOS protocol.

Frontiers in human neuroscience·2026
Same journal

Examining the independent and combined effects of autistic and ADHD traits on multisensory integration.

Frontiers in human neuroscience·2026
Same journal

Prediction of hormone receptor status in breast cancer brain metastases using an MRI-based multimodal deep learning framework.

Frontiers in human neuroscience·2026
See all related articles

This study introduces a novel transfer learning (TL) method for Brain-Computer Interfaces (BCI) to address electroencephalography (EEG) variability. The method aligns EEG data in Riemannian geometry, improving accuracy and reducing calibration time for BCI systems.

Area of Science:

  • Neuroscience
  • Machine Learning
  • Signal Processing

Background:

  • Statistical variability in electroencephalography (EEG) between subjects and sessions is a major challenge in Brain-Computer Interface (BCI) development.
  • This variability necessitates frequent recalibration, limiting the practical application of pre-trained machine learning models.

Purpose of the Study:

  • To present a novel transfer learning (TL) method designed to mitigate EEG variability in BCI systems.
  • The goal is to reduce calibration time and enhance BCI accuracy by aligning subject-specific EEG data.

Main Methods:

  • The proposed TL method aligns EEG data within the tangent space of Riemannian manifolds of positive definite matrices.
  • A support vector classifier was used for feature classification across three BCI paradigms: event-related potentials (ERP), motor imagery (MI), and steady-state visually evoked potentials (SSVEP).
Keywords:
Brain-Computer InterfaceERPRiemannian geometrySSVEPdomain adaptationmotor imagerytransfer learning

More Related Videos

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.2K

Related Experiment Videos

Last Updated: Aug 16, 2025

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.8K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.2K
  • The method was evaluated on 18 BCI databases involving 349 subjects.

    • Main Results:

    • Significant classification accuracy improvement was observed for the ERP paradigm compared to a standard training-test pipeline.
    • No performance degradation was noted for the motor imagery (MI) and steady-state visually evoked potentials (SSVEP) paradigms.
    • A 2.7% overall accuracy improvement was achieved compared to the Riemannian Procrustes Analysis (RPA) method. The method also handles datasets with varying channel numbers.

    Conclusions:

    • The proposed Riemannian geometry-based TL method effectively addresses EEG variability in BCI.
    • This approach offers a promising solution for reducing calibration needs and improving BCI performance, particularly for the ERP paradigm.
    • The method's inherent ability to manage differing channel counts facilitates inter-dataset transfer learning.