ARAN - Access to Research at NUI Galway

Bayesian ANN Classifier for ECG Arrhythmia Diagnostic System: A Comparison Study

ARAN - Access to Research at NUI Galway

Show simple item record

dc.contributor.author Lyons, Gerard en
dc.contributor.author Chambers, Des en
dc.contributor.author Madden, Michael G. en
dc.contributor.author Gao, Dayong en
dc.date.accessioned 2009-05-13T09:56:58Z en
dc.date.available 2009-05-13T09:56:58Z en
dc.date.issued 2005 en
dc.identifier.citation "Bayesian ANN Classifier for ECG Arrhythmia Diagnostic System: A Comparison Study" , Dayong Gao, Michael G. Madden, Des Chambers, and Gerard Lyons, Proc. International Joint Conference on Neural Networks, Montreal, July 2005. en
dc.identifier.uri http://hdl.handle.net/10379/186 en
dc.description.abstract Abstract¿This paper outlines a system for detection of cardiac arrhythmias within ECG signals, based on a Bayesian Artificial Neural Network (ANN) classifier. The Bayesian (or Probabilistic) ANN Classifier is built by the use of a logistic regression model and the back propagation algorithm based on a Bayesian framework. Its performance for this task is evaluated by comparison with other classifiers including Naive Bayes, Decision Trees, Logistic Regression, and RBF Networks. A paired t-test is employed in comparing classifiers to select the optimum model. The system is evaluated using noisy ECG data, to simulate a real-world environment. It is hoped that the system can be further developed and fine-tuned for practical application. en
dc.language.iso en en
dc.subject Arrhythmia en
dc.subject ECG signals en
dc.subject Bayesian artificial neural network (ANN) classifier en
dc.subject Decision trees en
dc.subject Logistic regression en
dc.subject.lcsh Arrhythmia en
dc.subject.lcsh Electrocardiography en
dc.subject.lcsh Bayesian field theory en
dc.subject.lcsh Decision trees en
dc.subject.lcsh Logistic regression analysis en
dc.title Bayesian ANN Classifier for ECG Arrhythmia Diagnostic System: A Comparison Study en
dc.type Conference Paper en

Files in this item

This item appears in the following Collection(s)

Show simple item record