Classification of Arrhythmia Using Parallel Channels and Different Features

Application of artificial intelligence methods (AI) has become an important area in electrocardiography (ECG) for recognition and classification of various types of arrhythmias. Arrhythmia refers to any disturbance in the regular rhythmic activity of the heart (amplitude, duration and QRS complex). From a diagnostic point of view, most information about arrhythmia is contained in the QRS complex and the RR intervals. In this study, a powerful neural network technique was devised for classifying heart beats based on a feature matrix. The proposed method achieved the following metrics: 0.972 – precision, 0.97 – recall and 0.972 – f1 measure.