By Topic

Multi-component based neural network beat detection in electrocardiogram analysis

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
T. Last ; Faculty of Engineering, University of Ulster at Jordanstown, Northern Ireland ; C. D. Nugent ; F. J. Owens

Electrocardiogram (ECG) classification systems have the potential to benefit from the inclusion of automated measurement capabilities. The first stage in the computerized processing of the ECG is Beat Detection. The accuracy of the beat detector is very important for the overall system performance hence there is benefit in improving its accuracy. In the present study we introduce the concept of a multi-component based approach to beat detection based on neural networks (NNs). A database containing in excess of approximately 3000 cardiac cycles was used to evaluate the techniques developed. Results showed the enhanced capability of the multi- component based approaches to detect up to 2988 beats in comparison to 2848 beats achieved by standard benchmarking techniques of non-syntactic and cross- correlation methods. These results have subsequently demonstrated the improvements which can be achieved through utilization of the proposed approach.

Published in:

2006 Computers in Cardiology

Date of Conference:

17-20 Sept. 2006