CLASSIFYING HEARTRATE BY CHANGE DETECTION AND WAVELET METHODS FOR EMERGENCY PHYSICIANS ∗

Abstract. Heart Rate Variability (HRV) carries a wealth of information about the physiological state and the behaviour of a living subject. Indeed, the heart rate variation is intrinsically linked to the autonomic nervous system: the Parasympathetic and Sympathetic systems. Thus, any imbalance in these two opposite systems results in a variation of the cardiac frequency modulation. It is also recognized that this alternation between equilibrium and disequilibrium (frequency variability) is an indicator of well being and good health. In other words, decreased heart rate variability is always linked to stress, fatigue and decreased physical performances. The aim of this work is to exploit the heart rate signals to detect situations of stress in different populations: emergency physicians, sportsmen, animal behaviours, etc... This paper introduces a methodological framework for the detection of stress and eventually well being. Our contribution is based on first extracting high and low frequencies energies which are linked to the Parasympathetic and Sympathetic systems. We then detect change points on these energies using the Filtered Derivative with p-value (FDpV) method. Finally, we develop a typology of cardiac activity by distinguishing homogeneous groups or state profiles having a characteristic similarity. We apply our methodology on a real dataset corresponding to an emergency doctor