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

Classification of respiratory sounds based on wavelet packet decomposition and learning vector quantization

L Pesu1, P Helistö, E Ademovic

  • 1Laboratory of Biomedical Engineering, Helsinki University of Technology, Finland.

Technology and Health Care : Official Journal of the European Society for Engineering and Medicine
|October 1, 1998
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

Impact of rheumatic diseases on oral health and quality of life.

Oral diseases·2014
Same author

Decreased variation of inflammatory markers in gestational diabetes.

Diabetes/metabolism research and reviews·2011
Same author

Associations between sports participation, cardiorespiratory fitness, and adiposity in young adult twins.

Journal of applied physiology (Bethesda, Md. : 1985)·2011
Same author

Fundamental efficiency of nanothermophones: modeling and experiments.

Nano letters·2010
Same author

M-band nonlinear subband decompositions with perfect reconstruction.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

[Application of Bacillus-antagonists for biocontrol of fungi degrading raw wood].

Prikladnaia biokhimiia i mikrobiologiia·2006

This study introduces a novel wavelet packet-based method for detecting abnormal respiratory sounds like crackles and wheezes. While promising, the technique requires further development for clinical application in lung sound analysis.

Area of Science:

  • Medical Signal Processing
  • Respiratory Medicine
  • Artificial Intelligence in Healthcare

Background:

  • Accurate detection of abnormal respiratory sounds is crucial for diagnosing lung conditions.
  • Current methods for lung sound analysis can be subjective and time-consuming.
  • Automated analysis offers potential for improved diagnostic accuracy and efficiency.

Purpose of the Study:

  • To develop and evaluate a wavelet packet-based method for automated detection and classification of respiratory sounds.
  • To differentiate between normal lung sounds, crackles, and wheezes using signal processing and machine learning.
  • To assess the preliminary performance of the proposed method using real patient data.

Main Methods:

  • Respiratory sound signals were segmented for analysis.

Related Experiment Videos

  • A feature vector was created using optimal wavelet packet decomposition.
  • Learning Vector Quantization (LVQ) was employed for sound classification.
  • The method was validated against expert observer analysis on a small patient dataset.

    • Main Results:

    • The wavelet packet-based method demonstrated potential in classifying respiratory sound segments.
    • Preliminary results showed promise in distinguishing between normal, crackles, and wheezes.
    • The system's performance, while encouraging, did not yet meet clinical usability standards.

    Conclusions:

    • The developed wavelet packet decomposition and LVQ classification approach shows feasibility for respiratory sound analysis.
    • Further refinement and larger datasets are necessary to achieve clinical-grade accuracy.
    • This automated approach could potentially aid clinicians in diagnosing respiratory pathologies.