Classification of bundle branch blocks using multilayered perceptron network

Development of automated and accurate techniques for ECG recognition is important for diagnosis of heart diseases. Arrhythmic signals occur due to the disturbances to the rate, regularity, nodes and conduction path of the electrical impulses. Bundle branch block arises from defects of the conduction...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE International Conference on Control System, Computing and Engineering pp. 531 - 535
Main Authors Megat Ali, M. S. A., Jahidin, A. H., Norali, A. N., Mat Som, M. H.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2011
Subjects
Accuracy
bundle branch blocks
Classification algorithms
Electrocardiography
Feature extraction
multilayered perceptron network
Network topology
performance metrics
Training
training algorithms
Vectors
Online AccessGet full text

Cover

More Information
Summary:Development of automated and accurate techniques for ECG recognition is important for diagnosis of heart diseases. Arrhythmic signals occur due to the disturbances to the rate, regularity, nodes and conduction path of the electrical impulses. Bundle branch block arises from defects of the conduction pathways involving blockage of electrical impulses through the bundle branches. This paper investigates MLP network for classification of bundle branch block arrhythmias. Trainings were conducted for varying network topologies with different training algorithms. A 98.2% overall detection accuracy was achieved over 90 beat samples. Results show that the Levenberg-Marquardt algorithm managed to achieve 100% recognition accuracy for all network topologies.
ISBN:9781457716409
1457716402
DOI:10.1109/ICCSCE.2011.6190583