Open AccessClassification of Heart Arrhythmia in ECG Signals using PCA and SVM
Author(s) -
Sumanta Kuila,
Namrata Dhanda,
Subhankar Joardar
Publication year - 2020
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.j7481.0891020
Subject(s) - support vector machine , cardiac arrhythmia , artificial intelligence , pattern recognition (psychology) , computer science , principal component analysis , classifier (uml) , electrocardiography , medicine , atrial fibrillation
Electro cardiogram (ECG) signals records the vital information about the condition of heart of an individual. In this paper, we are aiming at preparing a model for classification of different types of heart arrhythmia. The MIT-BIH public database for heart arrhythmia has been used in the case of study. There are basically thirteen types of heart arrhythmia. The Principal Component Analysis (PCA) algorithm has been used to collect various important features of heart beats from an ECG signal. Then these features are trained and tested under Support Vector Machine (SVM) algorithm to classify the thirteen classes of heart arrhythmia. In the paper the proposed algorithm has been discussed and the outcome results have been validated. The result shows that the accuracy of our classifier in our research work is more than 91% in most of the cases.