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 Videos

An effective BCI speller based on semi-supervised learning.

Huiqi Li1, Yuanqing Li, Cuntai Guan

  • 1Institute for Infocomm Research, 21 Heng Mui Keng Terrace, Singapore. huiqili@i2r.a-star.edu.sg

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|October 20, 2007
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

SARS-CoV-2 infection and COVID-19 vaccination and the risk for new-onset type 1 diabetes: a register-based population study in Sweden.

Diabetologia·2026
Same author

Mental illness after bereavement before and during the COVID-19 pandemic in Sweden: A matched cohort study.

PLOS mental health·2026
Same author

Bereavement and Risk of Cardiovascular Disease Before and During the COVID-19 Pandemic.

JAMA network open·2026
Same author

Ursodeoxycholic acid treatment did not show protective effect for severe COVID-19 outcomes - a nationwide register study.

BMC public health·2026
Same author

Cardiovascular and mortality risks following COVID-19-related vs. non-COVID-19 COPD exacerbations.

Annals of the American Thoracic Society·2026
Same author

Taming Proton Transfer Through Proton Conductors to Boost Hydrogen Evolution.

Angewandte Chemie (International ed. in English)·2026
Same journal

Highly Articulated Robotic Probe for Minimally Invasive Surgery.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2010
Same journal

Combined peripheral and cortical neural stimulation in motor neurorehabilitation.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2008
Same journal

Embedded assessment algorithms within home-based cognitive computer game exercises for elders.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2008
Same journal

Digital signal processing of the wideband external pulse recorded during cuff deflation: a new way to measure blood pressure.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2008
Same journal

Immune cells detection of the in vivo rejecting heart in USPIO-enhanced magnetic resonance imaging.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2008
Same journal

wHospital: a web-based application with digital signature for drugs dispensing management.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2007
See all related articles

This study introduces a semi-supervised learning method to significantly reduce calibration time for brain-computer interfaces (BCIs). The approach enhances P300 speller feasibility by updating models with online data, cutting training time by 93.4%.

Area of Science:

  • Biomedical Engineering
  • Neuroscience
  • Machine Learning

Background:

  • Brain-computer interfaces (BCIs) offer communication pathways for individuals with paralysis.
  • Minimizing initial calibration time is crucial for P300-based BCI usability.
  • Current P300 BCIs often require extensive training data, limiting practical application.

Purpose of the Study:

  • To reduce the training time for P300-based BCIs using a semi-supervised learning approach.
  • To develop a robust and adaptive P300 speller model with minimal initial calibration.
  • To enhance the overall feasibility and practicality of P300-based BCIs for users.

Main Methods:

  • A semi-supervised learning strategy was employed, initially training a model on a small dataset.

Related Experiment Videos

  • Online test data with predicted labels were iteratively added to augment the training set.
  • The model was continuously updated online using the dynamically extended training data.

    • Main Results:

    • The proposed method achieved a 93.4% reduction in training time on a P300-based word speller dataset.
    • Satisfactory accuracy rates were maintained despite the significant reduction in training duration.
    • The online application of the semi-supervised approach resulted in a robust and adaptive BCI model.

    Conclusions:

    • Semi-supervised learning effectively reduces P300 BCI calibration time while preserving accuracy.
    • The developed method enhances the practicality of P300 spellers for paralyzed users.
    • This approach is vital for improving the real-world feasibility of brain-computer interfaces.