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

ANN compression of morphologically similar ECG complexes

D J Hamilton1, D C Thomson, W A Sandham

  • 1Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, UK.

Medical & Biological Engineering & Computing
|November 1, 1995
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

Beta-blockers and mechanical dyssynchrony in heart failure assessed by radionuclide ventriculography.

Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology·2022
Same author

Radionuclide ventriculography phase analysis for risk stratification of patients undergoing cardiotoxic cancer therapy.

Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology·2020
Same author

Discussion on the Pathology of Phthisis Pulmonalis.

Glasgow medical journal·2018
Same author

On Reflex Paralysis and Urinary Paraplegia.

The British and foreign medico-chirurgical review·2018
Same author

Notes on Two Cases of Stricture of the Œsophagus.

Edinburgh medical journal·2018
Same author

On Tubercle in the Human Lung.

Edinburgh medical journal·2018

This study introduces an auto-associative neural network for compressing electrocardiogram (ECG) signals, improving performance with DC level removal. The algorithm offers a novel approach to ECG data compression.

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence
  • Signal Processing

Background:

  • Electrocardiogram (ECG) signal compression is crucial for efficient data storage and transmission in healthcare.
  • Traditional compression methods may not fully capture the complexities of ECG data.
  • Auto-associative neural networks offer a promising avenue for advanced signal processing tasks.

Purpose of the Study:

  • To present a novel compression algorithm for electrocardiogram signals utilizing an auto-associative neural network.
  • To evaluate the impact of different network sizes and coding strategies on compression performance.
  • To demonstrate performance enhancements through DC level removal and compare with existing techniques.

Main Methods:

  • Development of a compression algorithm based on an auto-associative neural network architecture.

Related Experiment Videos

  • Investigation of weight and activation coding techniques within the neural network.
  • Systematic comparison of compression performance across various network configurations.
  • Implementation and evaluation of DC level removal as a preprocessing step.

    • Main Results:

    • The auto-associative neural network effectively compresses electrocardiogram signals.
    • Performance varies with network size and coding methods, with optimal configurations identified.
    • DC level removal significantly improves compression performance.
    • The proposed algorithm demonstrates competitive or superior performance compared to existing compression techniques.

    Conclusions:

    • Auto-associative neural networks provide an effective framework for ECG signal compression.
    • DC level removal is a valuable technique for enhancing compression efficiency.
    • The presented algorithm offers a viable and improved alternative for ECG data compression.