By Topic

Comparison of neuro-fuzzy approaches with artificial neural networks for the detection of Ischemia in ECG signals

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

4 Author(s)
Hoda Tonekabonipour ; Mechatronics Department, Qazvin Islamic Azad University, Iran ; Ali Emam ; Mohamad Teshnelab ; Mehdi Aliyari Shoorehdeli

This paper compares different classification methods of ECG signals including their accuracies. First of all , Preprocessing for ECG signal is necessary in order to detect QRS complex. Then, with the intention of extract influential features in Ischemia disease, baseline wandering and noise suppression is done. Following to above mentioned target, two neuro-fuzzy classification algorithms incorporated with two artificial neural networks classifiers selected. They put under test to investigate their ability to recognize Ischemic Heart Disease (IHD) from ECG signals. Adaptive Neuro Fuzzy Inference System (ANFIS) and Locally Linear Model Tree (LOLIMOT), are two neuro-fuzzy networks used in the test. They have good capability of learning. Also Multi layer Perceptron (MLP) and Probabilistic Neural Networks (PNN) used as well in test. These are four structures totally used in this paper. The ECG sampled signals are taken from MIT-BIH database. They are used to train neural networks enabling them to classify Ischemia. All neuro-structures have been tested by using experimental ECG records of individuals. The results suggest that neuro-fuzzy classifiers perform better than the other types of classifiers.

Published in:

Systems Man and Cybernetics (SMC), 2010 IEEE International Conference on

Date of Conference:

10-13 Oct. 2010