Heart Beat Classification of ECGs Using Morphology and Beat Intervals

The paper presents an automated approach to beat recognition of four different beat types in ECG´s, namely Normal beats, Ventricular ectopic beats, Supra-ventricular ectopic beats and Fusion beats. The feature vector used to differentiate between the different beats contains morphological features and beat intervals for each beat. The features include parameters like the pre- RR interval, post-RR interval, the peaks of the Q, R, S, T points, as well as the time duration between different fiducial points. The feature vector is then fed to a neuro fuzzy classifier which determines the type of heart beat.