Cardiac arrhythmia diagnosis method using hybrid network with feature analysis on ECG signals

This paper describes hybrid classification to classify ECG signals to recognize heart arrhythmia. Suggested method can categorize normal and abnormal heart beats from each other. Heart abnormal beats consist of left bundle branch block (LBBB), right bundle branch block (RBBB), ventricular premature contractions (VPC) and atrial premature contractions (APC). ECG signal processing includes ۳ layers: QRS waves detection, features extraction, classification and recognition. ECG signals in MIT-BIH databases were tested to evaluate the suggested method. Results of the presented method show that the correct diagnosis values for APC, VPC, LBBB, RBBB and NORM are all ۱۰۰%.

Keywords:

SVM , Hopfield , hybrid network and cardiac arrhythmia