The purpose of research is development of a concept for building an automated system for the control and management of highly organized insects, namely bee colonies, based on unstructured physically heterogeneous data using artificial neural networks.

Methods. When conducting research and developing a method for constructing an intelligent system for monitoring and managing the life of bee colonies, the methods of multi-criteria analysis and the infological approach were used.

Results. The concept of synthesis of an intelligent information and telecommunication system for monitoring and managing the life of bee colonies with maximum integration into existing regional specialized structural units is proposed, which differs from the existing ones by the possibility of forming an ontology according to specified thematic requests, automated centralized control and management.

Conclusion. The scientific article describes the construction of an intelligent information and telecommunication system based on the tasks necessary for automating technological processes in order to increase the efficiency of performing the functions of beekeeping activities, potential consumers of services provided by the synthesized System.

The purpose of research is to meet the needs of legal entities and individuals in reliable information about the state of the environment in the region by creating an automated system for information support of environmental protection activities.

Methods. Considering the practice of using software in environmental protection, the following main groups can be distinguished: information and legal systems; programs for assessing the negative impact on the environment; software products for processing data from analytical laboratories performing environmental control; software for automating the process of preparing statistical reports in the field of environmental protection; territorial software complexes; electronic maps of environmental orientation. Automated information systems, as a rule, include a set of some of the software products listed above. The process of collecting and accumulating information in the system being developed should be based on a single standard reference information converted to work with it in electronic form. The operation of the database of the system in question is carried out according to the client-server scheme.

Results. The automated system being developed for environmental information support consists of six modules: waste; air; water; soil; plants; animals. All modules, in turn, are divided into certain blocks: reference and information block; reports; monitoring. The reference and information block contains general information about the object under consideration, statistical data and other reference information. The reports block includes standard forms of reporting documentation for a specific module, as well as recommendations for filling out the forms of the reports under consideration. The monitoring block contains information obtained through a system of constant monitoring of phenomena and processes occurring in the environment with the object in question.

Conclusion. The information accumulated in the system under development can be used to carry out operational environmental control, assess the anthropogenic load on the territory, as well as make management decisions in the field of environmental protection, the introduction of low-waste and environmentally friendly technologies.

The purpose of research is the development of an Internet platform of car service aggregators, or a trading platform, or a marketplace in order to eliminate the contradiction in which the consumer cannot find the required product or service, the company finds it difficult to find customers.

Methods. When creating a software implementation of the platform of autoservice aggregators, the PHP language was used, the interface was created using HTML, CSS. The Lareval 9.2 CSS framework was used, the following libraries were used when designing the interface: SticSlider - library for the slider, Wow J5 - animation library, React.js in the Redux bundle.

Results. A Web resource allows you to aggregate information scattered over the network and eliminate difficulties for customers in finding goods and services, for customers in finding contractors for work, and for companies in finding their customers and customers. Provides the ability to create a single database of contacts and interactions with customers through the main communication channels, which makes it possible to analyze and improve the strategy for promoting goods and services of car services.

Conclusion. In the course of the project, the software for the Internet platform of car service aggregators was developed and implemented. The test results showed that the software system fully meets the functional requirements and is ready for use.

Purpose of research is development of a recurrent algorithm for optimizing Voight models of biomaterial, which allows obtaining sets of descriptors for classifiers of the functional state of living systems in intelligent decision support systems for predicting and diagnosing socially significant diseases.

Methods. The essence of the proposed method lies in the use of a recurrent procedure for comparing the biomaterial impedance model obtained on the basis of series-connected Voigt links and the results of experimental studies. In the process of optimizing the Voigt model of the biomaterial, according to the proposed method, frequency pools are formed, at which, according to the results of the recurrent procedure, the optimal Voigt models are found by the number of links in the model. Then, according to the results of the integral error, the optimal number of model links is selected, corresponding to this number, the optimal pool of frequencies. The parameters of the Voight model make it possible to form descriptors for multimodal classifiers of the functional state of living systems and parameters of model links.

Results. ^s an example for testing the operation of the classifier built on the basis of the Voight model optimization algorithm, a group of patients with pneumonia with a clear diagnosis was taken. To obtain raw bioimpedance analysis data, an electrode belt was put on the chest of patients and impedance diagrams were determined corresponding to a certain combination of electrodes. The quality indicators of various classifier models reached 0,78% and did not fall below 0,62%

Conclusion. It is shown that the capabilities of multi-frequency probing and neural network models of multimodal classifiers make it possible to obtain new decision rules for diagnosing pathological conditions of the body (cardiovascular, infectious and oncological diseases).

The purpose of research is development of a method for processing and graphical display of multichannel medical signals in quasi-real time.

Methods. The method assumes segmentation of the program into easily used class modules, which are combined into a common hierarchy using object-oriented inheritance principles. It allows building medical signal registration systems of wide complexity. The method is based on the division of the general computational process into certain stages, called steps. A separate part of the hardware is allocated for each stage, and the process of transferring input-output data is organized between the stages. The set of steps is a pipeline for data processing. The proposed architecture of the medical signal processing system allows pipelined multi-threaded processing of multichannel medical signals, which increases the efficiency of using multi-core computing platforms.

Results. Based on the proposed method, a modular structure of medical signal processing software for a multichannel data acquisition system was developed. Data processing in pipeline processing stages includes such typical operations as writing data to a hard disk or to a separate memory buffer, signal filtering - removing a constant component or suppressing a certain frequency spectrum, calculating signal diagnostic indicators, analyzing the obtained indicators, making decisions, and etc. According to the proposed modular structure, software for processing multichannel medical signals in real time has been developed.

Conclusion. In the course of the study, software for processing multichannel medical signals in real time was developed. A method has been developed that allows the program to be segmented into easily used class modules, which are combined into a common hierarchy using object-oriented inheritance principles.

The purpose of research is to improve the accuracy in assessing the level of blood oxygen saturation in an aircraft pilot when conducting non-invasive spectrophotometric measurements in transmitted light under the influence of dynamic flight factors.

Methods are based on the basic concepts of the interaction of optical radiation with biological tissue and blood, the theory of pulse oximetry, probability theory, mathematical statistics, signal theory. When developing mathematical models of photoplethysmographic signals, aircraft noise, vibration, as well as for their representation in the frequency domain, the MATLAB 2019b program with a graphical user interface with a built-in Symbolic Math Toolbox package of mathematical functions was used as a tool.

Results. Mathematical models have been developed to assess the level of functional and fractional blood saturation. Model studies of the influence of dynamic flight factors, such as broadband quasi-harmonic vibration and aircraft noise, on the accuracy of estimating the pilot's blood saturation level have been carried out. It has been shown that to assess functional saturation, it is sufficient to use two sources of optical radiation, while for fractional saturation, their minimum number should be equal to four and is determined by the number of hemoglobin fractions taken into account in the blood. The use of four sources of optical radiation of a given spectral composition (660 nm, 805 nm, 880 nm and 940 nm) when performing non-invasive spectrophotometric measurements to assess the level of blood oxygen saturation compared to two sources (660 nm and 940 nm) allows to reduce the absolute error: in under the influence of broadband quasi-harmonic vibration - 3.64 times; under the influence of aircraft noise (70 dB) and (30 dB) - by 7.64 and 2.5 times, respectively; under the influence of the combined effects of vibration and aircraft noise (30 dB) - by 2.22 times.

Conclusion. For an adequate assessment of the pilot's functional state according to the values of his physiological parameters, in particular, the level of blood oxygen saturation, it is necessary to use diagnostic tools based on multiwave pulse oximetry, which allow estimating the level of fractional saturation.

The purpose of research is focused on factors affecting the detection and differentiation of circulatory disorders using broadband measurements of electrical impedance parameters.

Methods. The measurements were conducted using an anatomically realistic head phantom consisting that contained three major components simulating the scalp, skull and the brain. The pathological foci were simulated by injection of sodium chloride dissolved in distilled water. A purpose made measuring setup that provides wideband electrical impedance measurements in the frequency range from 10 kHz to 1 MHz and a basic error of no more than 1% was used.

Results. Early diagnosis of brain stroke is a necessary condition for successful treatment and subsequent rehabilitation. Computed tomography has the most advanced diagnostic capabilities, but it can used only in hospitals. Electrical impedance spectroscopy, a method to measure the electrical parameters of biological tissues, can potentially be used for early diagnosis at the pre-hospital stage. The article presents the results of numerical and phantom modeling aimed to study the ability of electrical impedance spectroscopy to detect and differentiate ischemic and hemorrhagic types of brain stroke.

Conclusion. Wideband electrical impedance spectroscopy can be considered as a promising cerebrovascular screening method. However, it has some limitations that should be addressed to develop biotechnical systems for clinical applications. In particular, the minimum size of a detected ischemic lesion depends on the resolution and dynamic range of the system. To detect foci with a volume of no more than 5 ml, located close to the electrodes, a dynamic range of the system must be at least 60 dB. Systems with typical dynamic range of 40 dB the minimal detectable volume increases up to 30 ml.

The purpose of research is to develop a method that allows predicting the severity of ischemia of the affected organ on the basis of metabolic disorders (PION) based on the use of such indicators as: base deficiency (DO), blood glucose (GC), potassium (K), sodium (Na), blood bicarbonate (BCC), partial CO2 voltage (PNUG), blood pH, aldosterone.

Methods. In the course of the work, an exploratory analysis was carried out using the method of group accounting of arguments (MGUA) and the theory of latent variables with the Rush model was used. As a basic mathematical apparatus, the methodology of synthesis of hybrid fuzzy decision rules was used, which proved itself well when solving problems with a fuzzy description of the classes under study.

Results. During the research, mathematical models for predicting the severity of ischemic disorders were synthesized and appropriate membership functions were obtained to assess the severity of ischemia of the affected organ for each of the signs. Expert evaluation and mathematical modeling have shown that confidence in the correct decision-making on the prognosis of the severity of ischemia of the affected organ exceeds 0.9.

Conclusion. The developed algorithm made it possible in 90% of cases to avoid the development of cardiovascular complications in the form of myocardial infarction, acute cerebrovascular accident and gangrene of the lower extremities, which makes it possible to recommend its use in clinical practice of cardiologists and cardiovascular surgeons.

The purpose of research is to improving the quality of diagnosis of obstructive pathology of extrahepatic bile ducts based on the analysis of reference schemes of reference endosonograms through the use of hybrid fuzzy mathematical models.

Methods. The main diagnostic method is endoscopic ultrasonography in combination with the methodology of synthesis of hybrid fuzzy decision rules developed at Southwestern State University.

Results. The number of patients with cancer of the extrahepatic bile ducts and the papilla duodeni major is steadily growing and has increased 1,5-2 times over the past 20 years. The differential diagnosis of benign and malignant stenoses is particularly difficult due to the similarity of their echosemiotics. Based on expert assessments of endosonograms displaying the pathology of extrahepatic bile ducts using the methodology of synthesis of hybrid fuzzy decision rules, a fuzzy hybrid model of differential diagnosis of the pathology under study was obtained. Based on the results of mathematical modeling and statistical tests on representative control samples, it was shown that the obtained model of differential diagnosis using reference images of reference endosonograms provides confidence in the desired diagnosis at the level of 0,93.

Conclusions. The obtained model of differential diagnosis of obstructive pathology of extrahepatic bile ducts provides confidence in decision-making at the level of 0,93, which is an acceptable quality indicator in clinical practice, providing "work" in conditions of insufficient statistics with a poorly formalized data structure.