Classification of ECG signals using Hermite functions and MLP neural networks

Mohsen Ahmadi ,Ataollah Ebrahimzadeh ,M Safarnejad

doi:10.5829/idosi.jaidm.2016.04.01.07

Abstract

Classification of heart arrhythmia is an important step in developing devices for monitoring the health of individuals. This paper proposes a three module system for classification of electrocardiogram (ECG) beats. These modules are: denoising module, feature extraction module and a classification module. In the first module the stationary wavelet transform (SWF) is used for noise reduction of the ECG signals. The feature extraction module extracts a balanced combination of the Hermit features and three timing interval feature. Then a number of multi-layer perceptron (MLP) neural networks with different number of layers and eight training algorithms are designed. Seven files from the MIT/BIH arrhythmia database are selected as test data and the performances of the networks, for speed of convergence and accuracy classifications, are evaluated. Generally all of the proposed algorisms have good training time, however, the resilient back propagation (RP) algorithm illustrated the best overall training time among the different training algorithms. The Conjugate gradient back propagation (CGP) algorithm shows the best recognition accuracy about 98.02% using a little amount of features.

Highlights

Development of accurate and quick methods for automatic ECG classification is vital for clinical diagnosis of heart disease [1]
multilayer perceptron (MLP) neural network architectures and training algorithms Various network architectures were evaluated to find an optimum solution for ECG signal diagnosis problem
We have compared the performance of MLP NN with PNN neural network

Summary

Introduction

Development of accurate and quick methods for automatic ECG classification is vital for clinical diagnosis of heart disease [1]. In [3], the authors used the discrete wavelet transform as the feature extractor and linear discriminants as the classifier for PVC beat classification and achieved the recognition accuracy (RA) about 95.6%. In [5] the authors used a feed forward neural network as classifier They derived five features including the QRS width and offset, amplitude of R segment, the T segment slope and the R-R interval duration for PVC beat classification. In [8], the authors used morphological information as the features and a neural network classifier for differentiating the ECG beats including PVC beats. The method presented in [15] is based on a hybrid fuzzy neural network that consists of a fuzzy self-organizing sub-network

Methods

Results

Conclusion