A Machine Learning Approach for the Classification of Cardiac Arrhythmia

Rapid advancements in technology have facilitated early diagnosis of diseases in the medical sector. One of the most prevalent medical conditions that demands early diagnosis is cardiac arrhythmia. ECG signals can be used to classify and detect the type of cardiac arrhythmia. This paper introduces a novel approach to classify the ECG data into one of the sixteen types of arrhythmia using Machine Learning. The proposed method uses the UCI Machine Learning Repository [1] dataset of cardiac arrhythmia to train the system on 279 different attributes. In order to increase the accuracy, the method uses Principal Component Analysis for dimensionality reduction, Bag of Visual Words approach for clustering and compares different classification algorithms like Support Vector Machine, Random Forest, Logistic Regression and K-Nearest Neighbor algorithms, thus choosing the most accurate algorithm, Support Vector Machine.