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 based on mel-scaled wavelet transform for heart sound analysis.

P Wang1, Y Kim, C Soh

  • 1BioMedical Engineering Research Centre, Nanyang Technological University, Singapore.

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|February 7, 2007
PubMed
Summary

A novel mel-scaled wavelet transform enhances automatic heart disease diagnosis by providing robust heart sound signal representation, especially in noisy conditions.

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

Neurosurgical contribution within a complex NF1 supraregional service.

Clinical neurology and neurosurgery·2019
Same author

Mitotic Activity in Glioblastoma Correlates with Estimated Extravascular Extracellular Space Derived from Dynamic Contrast-Enhanced MR Imaging.

AJNR. American journal of neuroradiology·2015
Same author

Increased drug resistance is associated with reduced glucose levels and an enhanced glycolysis phenotype.

British journal of pharmacology·2014
Same author

The concepts, diagnosis and management of early imaging changes after therapy for glioblastomas.

Clinical oncology (Royal College of Radiologists (Great Britain))·2011
Same author

Enhancing fraction in glioma and its relationship to the tumoral vascular microenvironment: A dynamic contrast-enhanced MR imaging study.

AJNR. American journal of neuroradiology·2009
Same author

Candidate biomarkers of extravascular extracellular space: a direct comparison of apparent diffusion coefficient and dynamic contrast-enhanced MR imaging--derived measurement of the volume of the extravascular extracellular space in glioblastoma multiforme.

AJNR. American journal of neuroradiology·2009

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Artificial Intelligence in Medicine

Background:

  • Automatic heart disease diagnosis relies on accurate heart sound signal analysis.
  • Traditional methods may struggle with the non-stationary nature and noise in heart sounds.
  • Developing robust feature extraction techniques is crucial for reliable diagnostic systems.

Purpose of the Study:

  • To develop a novel feature extraction method for heart sound signals.
  • To improve the robustness of heart sound representation in noisy environments.
  • To enhance the performance of automatic heart disease diagnosis systems.

Main Methods:

  • A mel-scaled wavelet transform was developed, combining mel mapping and wavelet transform.
  • Heart sound signals were processed by windowing, mel-scaled filterbank analysis, and wavelet transform.

Related Experiment Videos

  • The proposed mel-scaled wavelet features were extracted and evaluated.

    • Main Results:

    • The mel-scaled wavelet transform demonstrated a robust representation of heart sound signals.
    • The proposed method showed superior performance compared to standard mel-frequency cepstral coefficients.
    • Effective feature extraction was achieved even in the presence of noise.

    Conclusions:

    • The developed mel-scaled wavelet transform offers a robust approach for heart sound analysis.
    • This method holds significant potential for improving automatic heart disease diagnosis systems.
    • The technique is particularly effective in handling noisy heart sound data.