Fault Tolerant Neural Network for ECG Signal Classification Systems

Advances in Electrical and Computer Engineering. 2011;11(3):17-24 DOI 10.4316/AECE.2011.03003

 

Journal Homepage

Journal Title: Advances in Electrical and Computer Engineering

ISSN: 1582-7445 (Print); 1844-7600 (Online)

Publisher: Stefan cel Mare University of Suceava

LCC Subject Category: Technology: Electrical engineering. Electronics. Nuclear engineering: Electronics: Computer engineering. Computer hardware

Country of publisher: Romania

Language of fulltext: English

Full-text formats available: PDF

 

AUTHORS

MERAH, M.
OUAMRI, A.
NAIT-ALI, A.
KECHE, M.

EDITORIAL INFORMATION

Double blind peer review

Editorial Board

Instructions for authors

Time From Submission to Publication: 20 weeks

 

Abstract | Full Text

The aim of this paper is to apply a new robust hardware Artificial Neural Network (ANN) for ECG classification systems. This ANN includes a penalization criterion which makes the performances in terms of robustness. Specifically, in this method, the ANN weights are normalized using the auto-prune method. Simulations performed on the MIT ? BIH ECG signals, have shown that significant robustness improvements are obtained regarding potential hardware artificial neuron failures. Moreover, we show that the proposed design achieves better generalization performances, compared to the standard back-propagation algorithm.