UDC 004.622
SOFTWARE AND ALGORITHMIC SUPPORT TO ASSESS HUMAN HEALTH BY GAS PIE-ZOSENSOR SIGNALS
T. A. Kuchmenko, Dr. Sc. (Chem.), Professor of the Russian Academy of Sciences, Head of the Department of Physical and Analytical Chemistry, VSUET, Voronezh, Russia;
orcid.org/0000-0001-7812-9195, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
L. A. Korobova, Ph.D. (Tech.), Associate Professor of the Department of ITMC VSUET, Voronezh, Russia;
orcid.org/0000-0003-1349-732X, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
I. A. Matytsina, Ph.D. (Tech.), Associate Professor of the Department of MISiT Voronezh branch «GUMRF named after Admiral S.O. Makarov», Voronezh, Russia;
orcid.org/0000-0001-9236-9654, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
I. A. Murakhovsky, post-graduate student, Department of ITMC, VSUET, Voronezh, Russia;
orcid.org/0000-0000-0000-000X, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
D. A. Menzhulina, lecturer at VSMU named after. N.N. Burdenko, Voronezh, Russia;
orcid.org/0000-0003-3342-2659, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The issues of using a bioscanner device for medical research are considered. An algorithm is proposed, according to which, on the basis of chronofrequencyogram obtained as a result of the work of non-invasive diagnostics, health indicators are calculated, which describe the general state of human health. The aim of the work is to study the possibility of obtaining information about human health by analyzing a section of sorption curve using classification and dimensionality reduction methods. On the example of the analysis of human skin smell, the possibilities of the developed software are demonstrated. Algorithms are presented for calculating the rate of change in volatile substances molecules mass on the sensor to determine the marks of person's state. The software includes the calculation of characteristics and visualization of their sets for easy perception by untrained users. The software allows you to quickly process the data from the device, to present the possible reasons for state deviation from average statistical norm. Untrained users easily perceive information without complex processing of multidimensional data.
Key words: : sensors, sorption, output signals, information transformation, application, identification intervals, metrics, human condition, database, visualization