New representation of heart rate and evaluation of extracted geometric features

In this paper, a novel method for representation of heart rate has been introduced which is obtaining by using RR interval time series signal to plot the Triangle mapping consist of all the ordered pairs: (RRi, abs (RR̅ – RRi), i = 1, …, N where RR̅ is the mean of RR intervals. We obtained a triangle from the distribution of these points and by analyzing it, we could extracted some geometric features which were evaluated in distinguishing four groups of subjects (Arrhythmia, Congestive Heart Failure (CHF), Atrial Fibrillation (AF) and Normal Sinus Rhythm (NSR)) obtained of Physionet database. The results show that these features discriminate arrhythmia from NSR subjects by p<3E-4; CHF from NSR by p<8E-4; AF from NSR by p<8E-4; CHF from arrhythmia by p<2E-2; CHF from AF by p<8E-4; and arrhythmia from AF by p<7E-4.