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

Fuzzy wavelet packet based feature extraction method and its application to biomedical signal classification.

Deqiang Li1, Witold Pedrycz, Nicolino J Pizzi

  • 1Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6G 2G7, Canada.

IEEE Transactions on Bio-Medical Engineering
|June 28, 2005
PubMed
Summary

This study introduces an efficient fuzzy wavelet packet (WP) feature extraction method for classifying biomedical data. The novel approach enhances classification accuracy for magnetic resonance spectra using fuzzy clustering.

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

Growth factors and their roles in cardiac development and regeneration: a narrative review.

Pediatric medicine (Hong Kong, China)·2026
Same author

Prediction of Risk of Unplanned Readmission or Death in Elderly Heart Failure Patients During the Vulnerable Phase: Machine Learning With SHAP Interpretation.

FASEB bioAdvances·2026
Same author

Histone Deacetylase 7 protects against pathologic cardiac hypertrophy.

Journal of molecular and cellular cardiology·2026
Same author

Local Surrogate Models With Residual Fuzzy Rules for Model-Agnostic Explanations.

IEEE transactions on cybernetics·2026
Same author

Combining bioinformatics and machine learning to analyze and validate sepsis-related cell senescence genes and potential drugs.

Renal failure·2026
Same author

Mitochondrial dysfunction activates ADAMTS-5 expression via mt-dsRNA-PKR-Spi-1 axis in osteoarthritic chondrocytes.

iScience·2026

Area of Science:

  • Biomedical Signal Processing
  • Machine Learning
  • Data Science

Background:

  • High-dimensional biomedical data, such as magnetic resonance spectra, present challenges for accurate classification.
  • Traditional feature extraction methods in the wavelet packet (WP) domain often focus on signal compression or energy, potentially missing discriminatory information.

Purpose of the Study:

  • To develop an efficient fuzzy wavelet packet (WP) based feature extraction method for classifying high-dimensional biomedical data.
  • To identify an optimal WP decomposition for signal classification.
  • To extract discriminatory features from WP coefficients using fuzzy clustering.

Main Methods:

  • Wavelet packet (WP) transformation to create multiple feature spaces.
  • Identification of an optimal WP decomposition for signal classification.

Related Experiment Videos

  • Feature extraction from WP coefficients using fuzzy clustering to assess discriminatory effectiveness.
  • Signal classification using a linear classifier.

    • Main Results:

    • The proposed fuzzy WP feature extraction method demonstrates effectiveness in classifying magnetic resonance spectra.
    • Numerical experiments show competitive or improved classification results compared to common WP feature extraction methods.
    • Fuzzy set construction effectively identifies discriminatory features from WP coefficients.

    Conclusions:

    • The developed fuzzy wavelet packet (WP) based feature extraction method is efficient for high-dimensional biomedical data classification.
    • This approach offers a valuable alternative to standard feature extraction techniques in the WP domain.
    • The method shows promise for applications in biomedical data analysis and diagnostics.