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 extended EM algorithm for joint feature extraction and classification in brain-computer interfaces.

Yuanqing Li1, Cuntai Guan

  • 1yqli2@i2r.a-star.edu.sg

Neural Computation
|September 27, 2006
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

An opposite pH-responsiveness "gating" strategy: Intelligent sporopollenin exine armor for targeted therapy of colitis.

Asian journal of pharmaceutical sciences·2026
Same author

Plasma cell mastitis: a comprehensive review of etiological advances and future directions.

Frontiers in immunology·2026
Same author

Calibration-Free Online Detection in Wearable Motor Imagery Brain-Computer Interfaces.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Accurate prediction of intradialytic hypo- and hypertension in haemodialysis patients: the dual-attention Transformer model.

Clinical kidney journal·2026
Same author

Semantic knowledge enhanced 3D human-object interaction learning.

Scientific reports·2026
Same author

Relationship between A Body Shape Index and sleep disorders among the U.S. population: A cross-sectional analysis of the National Health and Nutrition Examination Survey data.

The Journal of international medical research·2026
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces an extended Expectation-Maximization (EM) algorithm to reduce training time for electroencephalogram (EEG)-based brain-computer interfaces (BCIs). The new method allows for online adaptation and achieves good accuracy in semi-supervised and unsupervised settings.

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) often require extensive training for parameter tuning.
  • BCI systems need to adapt to dynamic changes in brain signals, necessitating online parameter adjustment.
  • Reducing the training burden was a key challenge in BCI research, as highlighted in BCI Competition 2005.

Purpose of the Study:

  • To develop an adaptive algorithm for EEG-based BCIs that minimizes training time and allows for online parameter adjustment.
  • To jointly and iteratively extract and classify Common Spatial Pattern (CSP) features using an extended Expectation-Maximization (EM) algorithm.
  • To enable BCI operation in semi-supervised and unsupervised learning scenarios with minimal or no initial labeled data.

Main Methods:

Related Experiment Videos

  • An extended EM algorithm was developed, integrating CSP feature extraction and classification iteratively.
  • The training dataset is dynamically updated with predicted labels from test data in each iteration.
  • CSP features, Bayes classifier parameters, and the CSP transformation matrix are updated concurrently during iterations.

Main Results:

  • The proposed algorithm demonstrated effectiveness in achieving satisfying prediction accuracy on the BCI Competition 2005 dataset IVa.
  • Satisfactory results were obtained in both semi-supervised and unsupervised learning conditions.
  • The algorithm's convergence and the robustness of CSP features to noise were validated through data analysis.

Conclusions:

  • The extended EM algorithm significantly reduces the training requirements for EEG-BCIs.
  • The approach allows for effective online adaptation of BCI system parameters using unlabeled data.
  • The method shows promise for developing more efficient and adaptable brain-computer interfaces.