Click for new scientific resources and news about Corona[COVID-19]

Paper Information

Journal:   COMPUTATIONAL INTELLIGENCE IN ELECTRICAL ENGINEERING (INTELLIGENT SYSTEMS IN ELECTRICAL ENGINEERING)   SPRING 2011 , Volume 2 , Number 1; Page(s) 1 To 16.
 
Paper: 

USING MIXTURE STRUCTURES OF NEURAL NETWORKS IN ORDER TO DETECT CARDIAC ARRHYTHMIAS USING FUSION OF TEMPORAL AND WAVELET FEATURES

 
 
Author(s):  MOKHLESSI O., MEHRSHAD N., RAZAVI M.
 
* 
 
Abstract: 

In recent years the use of intelligent systems in science and engineering, especially in the diagnosis of disease, is increasingly growing. In this paper a smart way to diagnose heart disease (cardiac arrhythmias) is presented. This method is based on a combination of structures using neural networks for classification of normal operation and four abnormal heart functions. In the combination of these structures, some neural networks as a mediator, and some of them have been used as a specialist. In the proposed method firstly for removing noise from ECG signal, preprocessing was performed. The various time features (including fifteen properties) and wavelet features (includes fifteen feature) are extracted from the noise free signal and given the large number of selected features, principal components analysis is used for feature reduction to eight features. The proposed structures of MLP neural networks and RBF neural networks are appropriately trained for classification of arrhythmias and their performance has been evaluated. The results of the implementation of the proposed method on MIT / BIH database show the better performance in the diagnosis of cardiac arrhythmias compared to previous approaches.

 
Keyword(s): ELECTROCARDIOGRAPHY, CARDIAC ARRHYTHMIAS, MIXTURE STRUCTURES, NEURAL ETWORKS, TEMPORAL AND WAVELET FEATURES
 
References: 
  • ندارد
 
  Persian Abstract Yearly Visit 63
 
Latest on Blog
Enter SID Blog