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

Modelling ECG signals with hidden Markov models

A Koski1

  • 1Department of Computer Science, University of Turku, Finland. akoski@cs.utu.fi

Artificial Intelligence in Medicine
|October 1, 1996
PubMed
Summary

Continuous probability density function hidden Markov models (HMMs) are effective for electrocardiogram (ECG) signal analysis. This study demonstrates their suitability for accurate ECG recognition and modeling of segmented signals.

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

First Report of Brown Stripe of Saltgrass Caused by Bipolaris heveae in Colorado.

Plant disease·2019
Same author

First Report of Rapid Blight Caused by Labyrinthula terrestris on Poa annua in Colorado.

Plant disease·2019
Same author

In vivo magnetic resonance imaging and spectroscopy identifies oncolytic adenovirus responders.

International journal of cancer·2013
Same author

Oncolytic adenovirus based on serotype 3.

Cancer gene therapy·2010
Same author

Very rapid dissolution is not needed to guarantee bioequivalence for biopharmaceutics classification system (BCS) I drugs.

Journal of pharmaceutical sciences·2009
Same author

Depletion of resident alveolar macrophages does not prevent Fas-mediated lung injury in mice.

American journal of physiology. Lung cellular and molecular physiology·2008

Area of Science:

  • Biomedical Signal Processing
  • Machine Learning
  • Cardiology

Background:

  • Previous research utilized syntactic pattern recognition for signal processing.
  • Hidden Markov Models (HMMs) are probabilistic finite state machines with applications in speech and DNA analysis.
  • ECG signal analysis presents challenges in accurate pattern recognition.

Purpose of the Study:

  • To investigate the application of continuous probability density function hidden Markov models for ECG signal analysis.
  • To evaluate the efficacy of HMMs in ECG recognition and segmented signal modeling.

Main Methods:

  • Utilized continuous probability density function hidden Markov models.
  • Applied HMMs to segmented electrocardiogram (ECG) signals.
  • Leveraged the probabilistic and finite state machine properties of HMMs.

Main Results:

  • Hidden Markov models demonstrated high suitability for ECG recognition tasks.
  • The models accurately captured and represented segmented ECG signal characteristics.
  • HMMs proved effective in analyzing complex ECG patterns.

Conclusions:

  • Continuous probability density function hidden Markov models are a powerful tool for ECG analysis.
  • HMMs offer a robust approach for accurate ECG recognition and modeling.
  • This methodology advances the field of biomedical signal processing for cardiac diagnostics.

Related Experiment Videos