Edinburgh Research Explorer

Automatic classification of arrhythmic beats using Gaussian Processes

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationComputers in Cardiology, 2008
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages4
ISBN (Print)978-1-4244-3706-1
Publication statusPublished - Sep 2008
Event2008 35th Annual Computers in Cardiology Conference - Bologna, Italy, United Kingdom
Duration: 14 Sep 200817 Sep 2008


Conference2008 35th Annual Computers in Cardiology Conference
CountryUnited Kingdom


We propose a novel approach to the automated discrimination of normal and ventricular arrhythmic beats. The method employs Gaussian Processes, a non-parametric Bayesian technique which is equivalent to a neural network with infinite hidden nodes. The method is shown to perform competitively with other approaches on the MIT-BIH Arrhythmia Database. Furthermore, its probabilistic nature allows to obtain confidence levels on the predictions, which can be very useful to practitioners.


2008 35th Annual Computers in Cardiology Conference


United Kingdom

Event: Conference

ID: 22994847