Automatic Classification of ECG signal for Heart Disease Diagnosis based on Probabilistic Neural Network and Self Organising Maps

Abstract

Electrocardiogram is one of the traditional methods used as a diagnosis mechanism for cardiac diseases which records the electrical activities of the heart. The intention of this work is to classify the ECG signal into normal and abnormal (Arrhythmia) category in an automated manner. The proposed work demonstrates an automatic classification system using the morphological features extracted from the ECG signal, and classified using effective techniques such as the Probabilistic Neural Network (PNN) and Self Organising Map (SOM) Model. MIT-BIH (Massachusetts Institute of Technology – Boston’s Beth Israel Hospital) dataset of both normal and arrhythmia patients has been used to substantiate the algorithms. The experimental results demonstrate the efficacy of the proposed method. A comparison is made for the experimental results obtained using both PNN and SOM model and the performance is studied. The SOM model has given a better performance of 97\% than PNN model during testing and both the normal and Arrhythmia categories are classified accurately.

A12.Automatic Classification of ECG signal for Heart Disease Diagnosis based on pdf.ms

Leave a Reply

Your email address will not be published. Required fields are marked *