Issue 2 (188), article 2

Posted on

by admin

DOI:https://doi.org/10.15407/kvt188.02.036

Kibern. vyčisl. teh., 2017, Issue 2 (188), pp.

Khorozov O.A., Ph.D (Phys-Math), Leading Researcher
e-mail: oleh753@hotmail.com
Institute of Telecommunications and Global Information Space of the National Academy of Sciences of Ukraine,
Chokolovskiy ave., 13, Kiev 04186, Ukraine

APPLICATION OF FUZZY LOGIC FOR TELEMEDICINE SYSTEMS

Introduction. The telemonitoring system of patient’s vital signs for primary diagnosis and detection of abnormal values biophysical indicators is described. Expert estimates inherent in fuzzy logic rules are compared with the measured values of the vital signs for disease risk counting. The system is implemented at the Arduino with code for fuzzy logic controller. The structure of distributed management of the warning system is represented.

The purpose of the article is to develop an expert system based on fuzzy logic rules to calculate the risk level of the patient and use feedback control in decision-making.

Method. Expert estimates inherent in fuzzy logic rules are compared with the measured values of the vital signs for disease risk estimation.

Results. Expert system was considered for determination of patient’s health risk level. The fuzzy logic rules was formed for determination of belonging variables to risk groups and used for reflect the input to the decision making process. The application detects anomalous values of monitoring data, generates a medical report and sends it to the server for decision-making. The system includes monitors vital signs of the patients, warning services based on Fuzzy Logic techniques with the objective of reducing the risk from the slow provision of health care. The architecture of the integrated mHealth platform with functional models was proposed.

Conclusions. Telemedicine system was designed for primary diagnosis and monitoring of patients on the basis of fuzzy logic. The method based on expert knowledge, which are incorporated in the rules of fuzzy logic to compare the values of the input parameters of patients and disease risk prediction was used. The technique is common in detecting abnormal values biophysical indicators for disease risk assessment.

Download full text (ua)!

REFERENCE

  1. S.Dutta, A.Maeder, J.Basilakis, Using Fuzzy Logic for Decision Support in Vital Signs Monitoring Jjint Workshop Proceedings, 26th Australasian Joint Conference on Artificial Intelligence, 2013, p. 29–33.
  2. M. Mayilvaganan, K. Rajeswari, Risk Factor Analysis to Patient Based on Fuzzy Logic Control System. International Journal of Engineering Research and General Science. 2014. Vol. 2. Issue 5. P. 185–190.
  3. M.K. Choudhury, N. Baruah, A Fuzzy Logic Based Expert System for Denermination of Health Risk Level of Patient. International Journal of research in Engineering and Technology. 2015. Vol. 4. Issue 5. P.261–267.
  4. A.Povoroznjuk, E.Kharchenko, The use of fuzzy logic in computer systems medical diagnostics. Vestnik National Technical University. 2015. № 33. P. 125–133.
  5. Aj O. Alves URL: https://github.com/zerokol/eFLL.
  6. S. Sriparasa. JavaScript and JSON Essentials, 2013. URL: https://books.google.co.in/books?id=MZOkAQAAQBAJ

Recieved 09.03.2017