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

A time-series prediction approach for feature extraction in a brain-computer interface.

Damien Coyle1, Girijesh Prasad, Thomas Martin McGinnity

  • 1Intelligent Systems Engineering Laboratory, School of Computing and Intelligent Systems, Faculty of Engineering, University of Ulster, Derry, Northern Ireland, UK. dh.coyle@ulster.ac.uk

IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
|January 24, 2006
PubMed
Summary

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

Advancing EEG-based assessment of consciousness and cognition in prolonged disorders of consciousness.

Communications medicine·2026
Same author

Comparative performance analysis of quantum feature maps for quantum kernel-based machine learning.

Scientific reports·2026
Same author

Graph-BrainConvNet: A One-class GCN-based approach for MCI detection from source-level MEG.

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

Decoding the Variable Velocity of Lower-Limb Stepping Movements From EEG.

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

Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning Analysis.

Biology·2025
Same author

Deep predictive coding with bi-directional propagation for classification and reconstruction.

Neural networks : the official journal of the International Neural Network Society·2025

This study introduces a novel feature extraction procedure (FEP) for brain-computer interfaces (BCI) using electroencephalogram (EEG) data. The method achieves high classification accuracy for motor imagery tasks, outperforming existing approaches.

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Signal Processing

Background:

  • Brain-computer interfaces (BCI) enable communication and control through neural signals.
  • Electroencephalogram (EEG) is a non-invasive method for recording brain activity.
  • Accurate feature extraction is crucial for effective BCI performance.

Purpose of the Study:

  • To develop and evaluate a new feature extraction procedure (FEP) for BCI applications.
  • To extract discriminative features from EEG signals during motor imagery tasks.
  • To assess the classification accuracy of the proposed FEP.

Main Methods:

  • Utilized two neural networks (NNs) trained on right and left motor imagery EEG data.
  • Extracted features based on the power of prediction error or predicted signals from EEG time-series.

Related Experiment Videos

  • Employed Linear Discriminant Analysis (LDA) for classification.
  • Calculated features within a sliding window for temporal analysis.

    • Main Results:

    • Achieved high classification accuracy (CA) rates ranging from 88% to 98% across three subjects.
    • Demonstrated superior performance compared to established adaptive autoregressive (AAR) FEP methods.
    • Showcased feature separability due to morphological differences in EEG and NN specialization.

    Conclusions:

    • The proposed FEP is effective for discriminating between left and right motor imagery.
    • This novel approach offers a promising advancement for BCI technology.
    • The method provides a robust and accurate alternative to existing feature extraction techniques.