Automated Classification of Cardiac Arrhythmias

Abstract

Early detection of cardiac arrhythmia is of great importance both for the patients and the cardiologist for proper treatment. The detection is achieved through an extensive analysis of the electrocardiogram (ECG) signals, feature extraction method and machine learning techniques. The extracted features are used for the classification of the different types of arrhythmias. This research presents sequential feature selection (SFS) method whereas, the extracted features are fed into the classifiers; the Fuzzy Neural Network (FNN), Naïve Bayes (NB) and Radial Basis Function Network (RBFN) for classification. Observations from the results demonstrated that FNN gained the highest accuracy of 99% as compared with the other two machine learning techniques; NB and RBFN.