Accessibility navigation

Stress level classification using heart rate variability

Tlija, A., Istrate, D., Badii, A., Gattoufi, S., Bennani, A.-e. and Wegrzyn-Wolska, K. (2019) Stress level classification using heart rate variability. Advances in Science, Technology and Engineering Systems Journal, 4 (3). pp. 38-46. ISSN 2415-6698

[img] Text - Accepted Version
· Restricted to Repository staff only
· The Copyright of this document has not been checked yet. This may affect its availability.


It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.25046/aj040306


The research programme reported in this paper is set within the framework of our research under the theme of ICT support for Active Healthy Ageing (AHA). This longitudinal empirical research is focused on the study of the impact on the management of cardio-vascular disease if supported by sustained health monitoring using wearable connected devices. One of the key objectives is stress monitoring and its classification during the daily routine of life thus enabling psycho-physiological monitoring to study the correlation between emotional states including variable stress levels and the evolution and prognosis of cardiovascular disease. In this paper, the calibration phase will be studied in order to distinguish between two emotional states: i) meditation and ii) stress condition. For this, the Heart Rate Variability (HRV) features are used as extracted from the RR interval and a support vectors machine (SVM) classifier deployed which resulted in 74% and 87% recognition accuracy based on HRV data for the recognition of the two emotional states, namely meditative, and, stressed, respectively. The main objective is to prevent Cardio-Vascular Disease (CVD) in healthy people and to treat those who already suffer from it. Creating a reference database was our first step in this research project. The sensor choice was made based on doctors’ recommendations. The work methodology was as follows: first validate the « objective data » issuing from the calibration state. Second, set up the automatic algorithm and detect automatically the patient’s emotional states during the experimentation period (subjective data). Third analyse the physical activities correlated to the blood pressure and emotions. This study has involved the challenge of distinguishing the influence of stress versus relaxation on the Cardio-Vascular function and in particular on the risk of exacerbation of pre-existing Cardio-Vascular Disease.

Item Type:Article
Divisions:Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
ID Code:88159
Publisher:Society of Polish Mechanical Engineers and Technicians

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation