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

Semi-supervised learning of probabilistic models for ECG segmentation.

Nicholas P Hughes1, Stephen J Roberts, Lionel Tarassenko

  • 1Dept. of Eng. Sci., Oxford Univ., UK. nph@robots.ox.ac.uk

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|February 3, 2007
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

Clinical Evaluation of a Real-Time Wearable System for Monitoring In-Hospital Ambulatory Patients With COVID-19: Retrospective Data Study.

JMIR medical informatics·2026
Same author

Publisher Correction: Reliability of LLMs as medical assistants for the general public: a randomized preregistered study.

Nature medicine·2026
Same author

Southern Ocean seabird population shifts over the Holocene revealed by peat sequestration of mercury from guano.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Hybrid physics-machine learning models for quantitative electron diffraction refinements.

Nature communications·2026
Same author

Training instabilities favor flatter solutions in gradient descent.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Longitudinal cardiorespiratory wearable sleep staging in the home.

Frontiers in neuroscience·2026

We developed a new semi-supervised learning algorithm for probabilistic models using subjectively labeled data. This method accurately measures the QT interval in electrocardiograms (ECG) and improves ECG segmentation.

Area of Science:

  • Machine Learning
  • Biomedical Signal Processing

Background:

  • Subjectively labeled data presents challenges for traditional machine learning.
  • Accurate electrocardiogram (ECG) segmentation is crucial for clinical diagnostics, particularly for measuring the QT interval.

Purpose of the Study:

  • To introduce a novel semi-supervised learning algorithm for probabilistic models using subjectively labeled data.
  • To apply this algorithm to automated ECG segmentation, focusing on precise QT interval measurement.

Main Methods:

  • Utilized the Expectation-Maximization (EM) algorithm for maximum likelihood estimation.
  • Employed wavelet methods for ECG signal representation.
  • Incorporated advanced duration modeling techniques for Hidden Markov Models (HMMs) in ECG segmentation.

Related Experiment Videos

Main Results:

  • Demonstrated the effectiveness of the semi-supervised algorithm on automated ECG segmentation.
  • Achieved accurate measurement of the QT interval using the proposed method.
  • Showcased the utility of wavelet and HMM techniques in ECG analysis.

Conclusions:

  • The novel semi-supervised learning approach effectively handles subjectively labeled data for probabilistic model learning.
  • The algorithm provides accurate QT interval measurements and enhances ECG segmentation.
  • Wavelet methods and advanced HMM duration modeling are valuable tools for ECG signal processing.