Classification of ECG Signal during Atrial Fibrillation Using Autoregressive Modeling

Abstract

Atrial fibrillation (AF) is a common type of arrhythmia that causes death in the adults .The Auto regressive (AR) coefficients characterize the features of AF. The AR coefficients are measured for every 15 second duration of the ECG and the features are extracted using Burg's method. These features are classified using the different statistical classifiers such as kernel Support Vector Machine (KSVM) and K- Nearest Neighbor (KNN). The performance of these classifiers is evaluated on signals obtained from MIT-BIH Atrial Fibrillation Database.The effect of AR model order and data length is tested on the classification results.