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

Feature extraction for EEG-based brain-computer interfaces by wavelet packet best basis decomposition.

Bang-hua Yang1, Guo-zheng Yan, Rong-guo Yan

  • 1School of Electronic, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, People's Republic of China. ybh@sjtu.edu.cn

Journal of Neural Engineering
|November 25, 2006
PubMed
Summary

This study introduces a wavelet packet best basis decomposition (WPBBD) method for brain-computer interfaces. WPBBD improves electroencephalogram signal feature extraction for motor imagery tasks, achieving higher classification accuracy.

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

Distribution and genetic diversity of adeno-associated viruses in bats from coastal areas of Southeast China.

Scientific reports·2020
Same author

Biochars from Lignin-rich Residue of Furfural Manufacturing Process for Heavy Metal Ions Remediation.

Materials (Basel, Switzerland)·2020
Same author

Rh(iii)-Catalyzed diastereoselective transfer hydrogenation: an efficient entry to key intermediates of HIV protease inhibitors.

Chemical communications (Cambridge, England)·2020
Same author

Risk factors for treatment resistance and relapse of Chinese patients with MPO-ANCA-associated vasculitis.

Clinical and experimental medicine·2020
Same author

Construction of Various Bridged Polycyclic Skeletons by Palladium-Catalyzed Dearomatization.

Angewandte Chemie (International ed. in English)·2020
Same author

Jasmonate and Ethylene-Regulated Ethylene Response Factor 22 Promotes Lanolin-Induced Anthocyanin Biosynthesis in 'Zaosu' Pear (<i>Pyrus</i><i>bretschneideri</i> Rehd.) Fruit.

Biomolecules·2020

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Neuroscience

Background:

  • Brain-computer interfaces (BCIs) rely on accurate electroencephalogram (EEG) signal analysis.
  • Motor imagery (MI) tasks are crucial for BCI control, requiring effective feature extraction.
  • Existing methods for EEG feature extraction may not fully capture complex signal characteristics.

Purpose of the Study:

  • To develop and evaluate a novel feature extraction method for EEG signals during motor imagery tasks.
  • To improve classification accuracy in BCIs using wavelet packet best basis decomposition (WPBBD).

Main Methods:

  • EEG signals from motor imagery tasks were decomposed using wavelet packet transform (WPT).
  • A wavelet packet library was generated to identify the best basis for classification.

Related Experiment Videos

  • Subband energies from the selected best basis were utilized as features.

    • Main Results:

    • The WPBBD method achieved a classification accuracy of 70.3% for discriminating three different motor imagery tasks.
    • This represents a 4.2% improvement in classification accuracy compared to existing wavelet packet methods.
    • The selected subband energies proved to be effective features for MI tasks.

    Conclusions:

    • Wavelet packet best basis decomposition (WPBBD) is a promising technique for EEG feature extraction in BCIs.
    • WPBBD enhances the performance of BCIs by providing more discriminative features for motor imagery tasks.
    • The improved accuracy suggests WPBBD's potential for more robust and reliable BCI applications.