ROBUST METHOD FOR THE CLASSIFICATION OF THE ARRHYTHMIA WITH DNN CLASSIFIER IN THE DIVERSE ECG SIGNAL

Electrocardiography (ECG) signals are classified into two classes in order to find abnormality of the signal. The ECG can be obtained by placing the electrode on the skin of the body and record the ECG signal. This signal is used in the medical to identify the condition of the patients and report his/her health. In this method, the four features have been extracted from the ECG signal to classify the signal. The ECG signal is obtained from the MIT-BHE arrhythmia database, which consists of the large number of signals including the label of normal and arrhythmia signal. The Deep Neural Network (DNN) is used to classify the signal into arrhythmia and sinus rhythm. The experiment is also conducted with the other classifiers in order to compare the value with the DNN. The performance of the classifier measured and compared with one another, the result showed that the DNN provides higher classification than other classifiers.