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: May 12, 2026

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals
08:22

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals

Published on: April 26, 2024

Dynamically weighted ensemble classification for non-stationary EEG processing.

Sidath Ravindra Liyanage1, Cuntai Guan, Haihong Zhang

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

Journal of Neural Engineering
|April 12, 2013
PubMed
Summary

This study introduces a novel dynamically weighted ensemble classification (DWEC) method to improve brain-computer interface (BCI) performance by addressing non-stationary electroencephalography (EEG) data. The DWEC framework significantly enhances classification accuracy compared to traditional methods.

Related Concept Videos

Classification of Signals01:30

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Discovering Interpretable Semantics from Radio Signals for Contactless Cardiac Monitoring.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Decoupled Hierarchical Distillation for Multimodal Emotion Recognition.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

EEG-to-gait decoding via phase-aware representation learning.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Decoding Covert Speech From EEG by Functional Areas Spatio-Temporal Transformer.

IEEE journal of biomedical and health informatics·2026
Same author

Bioinspired Heat-Induced Viscoelasticity-Switchable Electrodes for Conformal Brain-Computer Interfaces.

Advanced materials (Deerfield Beach, Fla.)·2025
Same author

EEG2GAIT: A Hierarchical Graph Convolutional Network for EEG-Based Gait Decoding.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2025

Area of Science:

  • Neuroscience
  • Computer Science
  • Biomedical Engineering

Background:

  • Electroencephalography (EEG) signals are inherently non-stationary, posing a significant challenge for reliable brain-computer interface (BCI) operation.
  • Existing BCI classification methods often struggle with performance degradation due to session-to-session variations in EEG data.

Purpose of the Study:

  • To propose and evaluate a novel computational method for robust EEG classification that effectively addresses non-stationarity.
  • To investigate the efficacy of a dynamically weighted ensemble classification (DWEC) framework in improving BCI performance.

Main Methods:

  • Developed a Dynamically Weighted Ensemble Classification (DWEC) framework.
  • Trained an ensemble of classifiers on clustered features.

Related Experiment Videos

Last Updated: May 12, 2026

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals
08:22

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals

Published on: April 26, 2024

  • Dynamically combined classifier decisions based on cluster center distances to test samples.

    • Main Results:

    • Cluster analysis revealed distinct feature spaces between sessions, confirming session-to-session non-stationarity in EEG.
    • The DWEC method achieved significantly higher mean accuracy (81.48%) on the BCI Competition IV dataset 2A compared to a baseline SVM (75.9%).
    • On in-house data, DWEC yielded a mean accuracy of 73%, outperforming the baseline SVM (69.4%).

    Conclusions:

    • Cluster-based analysis offers valuable insights into session-to-session non-stationarity in EEG.
    • The proposed DWEC method effectively mitigates non-stationarity challenges in EEG data, enhancing BCI operational robustness.