Heartbeat Classification Using Gaussian Mixture Models

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F06%3A03125303" target="_blank" >RIV/68407700:21230/06:03125303 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Heartbeat Classification Using Gaussian Mixture Models
Original language description
Automatic analysis of long term electrocardiographic registers is an issue of great importance since these records are used to diagnose difficult to observe heart diseases and their duration makes human inspection time consuming and error prone. That wepropose in this paper is a supervised procedure for heartbeat classification based on a probabilistic method successfully applied to many pattern recognition tasks, Gaussian Mixture Models (GMM). So, we will use a mixture composed by bidimensional Gaussian probability density functions (pdf) to modelate a concrete heartbeat morphology. The parameters of these Gaussian pdfs are estimated using the Expectation-Maximization (EM) algorithm, and at that point, thresholds can be obtained to separate the objects into the component classes. Experiments are carried out using registers of the MIT ECG database.
Czech name
Není k dispozici
Czech description
Není k dispozici

Publication year
2006
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Analysis of Biomedical Signals and Images - Proceedings of Biosignal 2006
ISBN
80-214-3152-0
ISSN
—
e-ISSN
—
Number of pages
3
Pages from-to
3-5
Publisher name
VUTIUM Press
Place of publication
Brno
Event location
Brno
Event date
Jun 28, 2006
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)