Biomedical Signal Processing and Control 42 (2018) 145–157 Contents lists available at ScienceDirect Biomedical Signal Processing and Control journal homepage: www.elsevier.com/locate/bspc Heart rate variability analysis using neural network models for automatic detection of lifestyle activities Sarah Christina Matta a , Ziad Sankari b , Sandy Rihana a,∗ a Faculty of Biomedical Engineering, The Holy Spirit University of Kaslik, USEK, Kaslik Campus, Jounieh, Mount Lebanon, Lebanon b CardioDiagnostics SAL, R&D Medical Company, Dbayeh, Lebanon a r t i c l e i n f o Article history: Received 20 April 2017 Received in revised form 6 January 2018 Accepted 27 January 2018 Keywords: Heart rate variability Artificial neural network Activity recognition Classification ROC Confusion matrix a b s t r a c t The quality of life and individual well-being are crucial factors in disease prevention. Particularly, healthy lifestyle lessens the risk and occurrence of main diseases, such as cardiovascular diseases and metabolic disorders. Since a patient has an active role in being a co-producer of his/her health, innovative devices and technologies have been devoted to helping folks in self-evaluation and expected to play a key role to maintain their well-being. In this work, we present a very promising assessment tool for health, Heart Rate Variability (HRV). HRV is the difference in time between one heartbeat and the next. HRV measurement is simple and non-invasive, it is derived from recording of electrocardiogram (ECG) on free-moving subjects. The main aim of this work is to investigate the dynamics in the autonomic regulation of the heart rate by using frequency and temporal analysis to correlate between the HRV and these physiological patterns. In addition to the applied frequency and temporal analyses, pattern recognition is also accomplished using Neural Networks which are further implemented and explored in this work. In the first place, the detection of the sleep/awake states is achieved. Next, a multiclassification of different types of activities such as sleeping, walking, exercising and eating is performed. © 2018 Elsevier Ltd. All rights reserved. 1. Introduction “Health should be defined as a state of complete physical, men- tal and social well-being, and not merely as the absence of disease and infirmity”, according to the World Health Organization. This is even marked by the role of lifestyle in illness risk. For instance, the risk of developing non-communicable diseases (NCD) which are leading causes of morbidity and mortality can be reduced by act- ing on lifestyle activities such as diet, physical activity and sleep. Thus, lifestyle interventions become a core factor in disease pre- vention. Furthermore, the development of innovative technologies for individual self-assessment is a very promising path towards the implementation of modern and effective solutions in disease prevention [1]. In this work, we focus on Heart Rate Variability (HRV). HRV pri- marily depends on the extrinsic regulation of the heart rate and so is believed to reveal the heart’s ability to detect and rapidly adjust to promptly varying stimuli. HRV mirrors the autonomic stability between the sympathetic and parasympathetic nervous systems ∗ Corresponding author at: Department of Biomedical Engineering, Faculty of Engineering, Holy Spirit University of Kaslik, Kaslik Campus, Jounieh, Lebanon. E-mail address: sandyrihana@usek.edu.lb (S. Rihana). [2]. In fact, the Autonomic Nervous System (ANS) is a part of the nervous system that non-voluntarily controls all organs and sys- tems in the body [3]. The ANS is composed of two subsystems of distinct neural pathways: the Sympathetic Nervous System (SNS) and the Parasympathetic Nervous System (PNS) [4]. Although some internal organs are innervated by only one type of subsystems, either parasympathetic or sympathetic pathways, the heart is characterized by being dually innervated by both sub- systems [5]. In fact, the main initiator of the electrical impulses is the Sinoatrial node (SA node) which is referred to as the pacemaker of the heart. The beat generated from the SA node is called the sinus beat [6]. In contrast, disturbances due to the abnormal impulse gen- eration or abnormal impulse conduction result in non-sinus beats [7]. The SA node generates impulses about 100–120 times at rest. Nevertheless, in healthy subjects resting heart rate is not commonly that high. This is due to the continuous control of the ANS over the output of SA node activity [3]. The SA node receives the neural impulses from the ANS [5]. Therefore, SA node is regulated by the ANS (both SNS and PNS), and consequently the heart’s electrical activity is the result of the PNS and SNS regulation. Assessments of autonomic function reflects the ability of this system to stimulate the SA node [7]. https://doi.org/10.1016/j.bspc.2018.01.016 1746-8094/© 2018 Elsevier Ltd. All rights reserved.