A real time approach for classification of ECG beats using repetition-based pattern detection and cardiac profiling scheme

Abstract

ECG beats is the most significant waveform within the electrocardiogram (ECG). QRS provides the basis for all ECG classification methods. We proposed a novel method for classification of ECG beats using repetition based packet processing and ECG waveform profiling. We first developed a real-time QRS detection technique using two-phase hashing to find exact QRS points. Then we proposed a classifier for profiling an ECG of normal patient. Our proposed technique depends much on the series of data corresponding to particular feature. The proposed method can accurately classify and differentiate normal (NORM) and abnormal heartbeats. Abnormal heartbeats include left bundle branch block (LBBB), right bundle branch block (RBBB), ventricular premature contractions (VPC) and atrial premature contractions (APC). Parameters of the algorithm adjust with the changes in ECG signals.