DWT and ANN Based Heart Arrhythmia Disease Diagnosis from MIT-BIH ECG Signal Data

Abstract

Diagnosis of heart disease is complex. ECG plays an important role for analysis and diagnosis of heart disease. Normally ECG signals are affected by different noises. These noises pollute the ECG signal. For quality diagnosis it is necessary to de noise the ECG signal. After de noising ECG signals, a pure signal is used to detect ECG parameters. Detection of ECG parameters takes an important role in the analysis of ECG signal. The Feature extracted ECG signal applied to ANN for classification to detect cardiac arrhythmia. This paper introduces the Electrocardiogram (ECG) pattern recognition method based on wavelet transform and neural network technique with error back propagation method has been used to classify two different types of arrhythmias, namely, Left bundle branch block (LBBB), Right bundle Branch block (RBBB) with normal ECG signal. The MIT-BIH arrhythmias ECG Database has been used for training and testing our neural network based classifier. The simulation results shown at the end.
DOI: 10.17762/ijritcc2321-8169.150156