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: Jun 10, 2026

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

Adaptation in P300 brain-computer interfaces: a two-classifier cotraining approach.

Rajesh C Panicker1, Sadasivan Puthusserypady, Ying Sun

  • 1Department of Electrical and Computer Engineering, National University of Singapore, Singapore. rajesh.c@nus.edu.sg

IEEE Transactions on Bio-Medical Engineering
|July 20, 2010
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

Toward future diagnostics of Parkinson's disease: a perspective on multimodal motor assessment and personalized digital twins.

Frontiers in aging neuroscience·2026
Same author

Exploring the potential of explainable deep learning for EEG-based cognitive decline prediction.

Computers in biology and medicine·2026
Same author

Translational perspectives on brain-heart interplay: From methodologies to clinical applications.

Computers in biology and medicine·2026
Same author

Collection of Ambulatory Electrocardiogram and Behavioral Data for the Identification of Digital Biomarkers for Heart Failure (CATCH-ECG): Protocol for a Prospective Cohort Study.

JMIR research protocols·2025
Same author

Leveraging Self-Supervised Learning Methods for Remote Screening of Subjects with Paroxysmal Atrial Fibrillation.

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

SViT-ECG: Spectrogram Vision Transformer for Detection of Short-Term Atrial Fibrillation from ECG Signals.

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

Highly Accelerated 1-mm Isotropic 3D Chemical Exchange Saturation Transfer MRI Using Wave-Co-CAIPI at 5 Tesla.

IEEE transactions on bio-medical engineering·2026
Same journal

Systematic Evaluation of Hip Exoskeleton Assistance Parameters for Enhancing Gait Stability During Ground Slip Perturbations.

IEEE transactions on bio-medical engineering·2026
Same journal

SleepConFormer: A Single-Channel EEG Framework for Sleep Staging and Consciousness Assessment in Patients with Disorders of Consciousness.

IEEE transactions on bio-medical engineering·2026
Same journal

Modeling Partial and Total Support of Left Ventricular Assist Device for Discrete Hemodynamic Control Framework.

IEEE transactions on bio-medical engineering·2026
Same journal

A Low-Cost Wearable TI-TACS Stimulator With Bipolar Quadratic-Boost Converter for Current Stimulation Validation in the Rat Brain.

IEEE transactions on bio-medical engineering·2026
Same journal

EMG-Based Gait Estimation Using Koopman-Inspired Method.

IEEE transactions on bio-medical engineering·2026
See all related articles

This study introduces a cotraining method for P300-based brain-computer interfaces (BCIs), enabling high-performance classifiers with minimal labeled data. The approach efficiently utilizes unlabeled data, significantly improving communication rates for practical BCI systems.

Area of Science:

  • Neuroscience
  • Computer Science
  • Biomedical Engineering

Background:

  • Brain-computer interfaces (BCIs) require high-performance classifiers, often demanding substantial labeled training data.
  • P300-based BCIs are a common type, but their performance can be limited by data scarcity.
  • Existing methods like self-training may not fully leverage available unlabeled data.

Purpose of the Study:

  • To develop a cotraining-based approach for constructing high-performance P300-based BCI classifiers with limited labeled data.
  • To enhance the efficiency of learning from unlabeled data in BCI applications.
  • To improve the robustness and performance of BCI systems under data-scarce conditions.

Main Methods:

  • Introduced a cotraining framework utilizing two classifiers: Fisher's linear discriminant analysis and Bayesian linear discriminant analysis.

More Related Videos

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

Related Experiment Videos

Last Updated: Jun 10, 2026

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

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

  • Implemented a progressive learning strategy where classifiers teach each other.
  • Employed extensive cross-validation for performance analysis.

    • Main Results:

    • Achieved high-performance classifiers using only a few minutes of labeled data and efficient use of unlabeled data.
    • Attained an average bit rate exceeding 37 bits/min with just 1.5 minutes of training.
    • Demonstrated significant performance gains compared to fully supervised methods, especially with limited training data and trials.

    Conclusions:

    • The proposed cotraining approach effectively builds robust P300-based BCI classifiers from minimal labeled data.
    • This method offers a practical solution for BCI systems by maximizing the utility of unlabeled data.
    • Outperformed self-training methods, highlighting its advantage in data-efficient BCI development.