DocumentCode :
1940790
Title :
Classification of bundle branch blocks using multilayered perceptron network
Author :
Ali, M. S A Megat ; Jahidin, A.H. ; Norali, A.N. ; Som, M. H Mat
Author_Institution :
Fac. of Electr. Eng., Univ. Teknol. MARA, Shah Alam, Malaysia
fYear :
2011
fDate :
25-27 Nov. 2011
Firstpage :
531
Lastpage :
535
Abstract :
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.
Keywords :
diseases; electrocardiography; medical diagnostic computing; multilayer perceptrons; ECG recognition; Levenberg-Marquardt algorithm; MLP network; arrhythmic signals; bundle branch blocks; classification; conduction pathways; diagnosis; electrical impulses; heart diseases; multilayered perceptron network; Accuracy; Classification algorithms; Electrocardiography; Feature extraction; Network topology; Training; Vectors; bundle branch blocks; multilayered perceptron network; performance metrics; training algorithms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control System, Computing and Engineering (ICCSCE), 2011 IEEE International Conference on
Conference_Location :
Penang
Print_ISBN :
978-1-4577-1640-9
Type :
conf
DOI :
10.1109/ICCSCE.2011.6190583
Filename :
6190583
Link To Document :
بازگشت