Classification of Electrocardiogram (ECG) signals for Diagnosis of Heart diseases

Abstract

The Electrocardiogram (ECG) has been introduced for decades as a powerful tool for diagnosing heart diseases. Hence, the automation of analyzing a rich source of information like ECG for diagnostic purposes is very crucial, since it helps 24-hour monitoring and instant discovering of cardiac disorders which need rapid medical aid in clinical situations. Cardiac arrhythmias mean abnormal activities in the heart upon certain conditions and mainly consist of two types. One of them is life threatening and can cause death. On the other hand, the other type is cardiac arrhythmia which is our interest in this study. It needs attention to avoid deterioration, but it is not critical as life threatening as the first one. Thus, ECG heartbeats should be continuously examined and classified. This thesis proposes an automatic reliable two-stage hybrid hierarchical method for ECG heartbeat classification. The heartbeats are segmented dynamically to avoid the consequences of the heart rate variability. Discrete Wavelet Transform (DWT) is utilized to extract morphological features that describe the segmented heartbeat. The extracted features are then reduced by using Principal Component Analysis (PCA). Subsequently, the resulted features along with four RR features are fed into