Purpose of the research. The purpose of this work is to develop an algorithm and a software system that allows to perform in a distributed mode the extraction of information from news sites using big data technologies.

Methods. Extracting the key concepts of news sites content helps artificial intelligent algorithms to investigate economic, political, and social phenomena in different contexts. This task is close to the text summarization problem which is being studied actively in modern research papers. But significantly less of the works touch on the big data algorithms for text summarization. We propose a new algorithm for effective text meaning extraction from a large count of news sites based on big data framework Apache Spark. The meaning of news is analyzed with Google BERT - the modern neural network architecture for natural language processing. Different groups of news are separated from each other with the k-means clusterization algorithm. The number of clusters is determined automatically using the gap statistic method. The content of sites scrapes by chrome browsers driven Selenium WebDriver in the distributed regime.

Results. The article presented detailed algorithms for the implemented software system, such as a mathematical model, architecture of a software distributed system.

Conclusion. The evaluation of our algorithm using the ROUGE metric demonstrates satisfactory summarization quality of news texts.

The purpose of research is development of an information system for assessing occupational risks, which allows to automate the processes of the labor protection management system using the example of an educational organization.

Methods. Today, there is a wide range of methods for assessing and managing occupational risks, but there is no unified method and approach to assessing occupational risks. Due to the fact that the user needs to process huge volumes of incoming information, an automated information system is needed, which will reduce the time period from identifying hazards to making management decisions aimed at eliminating identified hazards.

Results. The author reviewed the existing methods of assessing occupational risks and selected the optimal method based on the given criteria. Existing information systems have been analyzed to automate the risk assessment process. Based on the specified criteria, the most effective environment capable of realizing the set goals was selected. The database, which is a component of the information system for assessing occupational risks, was designed and the developed database was tested in the real conditions of the educational organization.

Conclusion. During the study, an information system for assessing occupational risks was developed, which includes forms for introducing and adjusting the list of professions and positions, forms for quickly changing and refining the list of occupational risks and the possibility of calculating the level of risk when the working environment changes, as well as the possibility of creating risk assessment maps. This system made it possible to automate the process of identification and assessment of occupational risks, which contributes to the prompt adoption of decisions aimed at reducing the likelihood of occupational diseases and occupational injuries in an educational organization. The developed procedure is implemented and used in practical activities by the labor protection service of the university.

Purpose of research. The article discusses a method for increasing the reliability of authentication of data sources in distributed information systems using communication channels with low bandwidth. Such systems are characterized by a small size of authentication codes contained in individual messages, which leads to a significant frequency of authentication errors.

Methods. The article presents an algorithm for correcting authentication errors performed for chains of information blocks. Due to the analysis of the time of receipt of blocks to the receiver, a numerical metric is formed for each message chain, which is recognized by the receiver as a chain formed by the target source. The chain is selected based on the minimum value of the calculated metric.

Results. Based on the real time characteristics of network packet delivery, a simulation model was created for the formation and verification of metrics generated for message chains. It is shown that, depending on the value of the simulated parameters of network packet transmission, the use of the proposed universal metric allows with a probability of up to 80% to choose from two chains identified by the receiver as a chain of blocks of the target source the one that is actually formed by it.

Conclusion. The paper shows that the use of an algorithm for analyzing meta-information - the time of receiving a data packet - can be used as a means of increasing the reliability of the authentication procedure performed for a remote subject of information exchange in conditions when the use of conventional cryptographic algorithms does not provide the required reliability. The proposed algorithm has low computational complexity, is easily implemented in hardware and reduces the number of errors when processing information data packets.

Purpose of research. Tooth surface treatment is an integral part of the dentist's job. Every day, specialists of a dental office are faced with clinical cases that involve the preparation or grinding of the tooth surface, the processing of filling material or a crown. In the process of cutting, abrasive tools are subjected to periodic and continuous power, thermal and physical-chemical influences, as a result of which their working surfaces wear out. This can be due to various reasons.

According to the literature data, the morphology of the working part of the tool, the inter-diamond space, and the high temperature during friction during the cutting process, to a greater extent affect the salting of the tool. The purpose of the work is to provide analytical proof of the effectiveness of a method for manufacturing a rotating abrasive cutting tool (VR) with a modified metal bond, which makes it possible to reduce the filling density of its working section and increase the inter-diamond space, which will lead to minimization of salting. This will ensure an increase in the VRI resource and the quality of preparation.

Methods. The article discusses a method for reducing the salinity of a galvanic diamond tool due to the additional introduction of diamond powder into the metal bunch of burs, the size of which is 30-50% of the size of the working diamond, i.e. creating a hybrid dental rotary instrument. In the course of the study, a comparative analysis of the salinization of standard and hybrid burs by the method of cutting - 2mm thick plates made of fiberglass of the SF-1-50 brand (microhardness 62HV) was carried out. The salinity Ams was determined as the difference in mass between the mass of the tool after cutting and the final mass. The test was carried out on a stand, which allows simulating the real conditions of loading and wear of the VRI, by drilling the plates with a radial feed of bora with a bur speed of 5000 rpm with a force of 4 N. The surface relief of the working part was determined microscopically. The assessment of the chemical composition of the VRI working section before and after tribological tests was carried out using an OXFORD energy dispersive microanalysis attachment of the TM3030 microscope.

Results. The positive effect of the proposed method is experimentally confirmed by the results of comparative tests for determining the salinity and cutting temperature of a standard and modified diamond dental rotating instrument.

Conclusion. An analytical evaluation of the modified tool showed a significant performance advantage over a standard bur due to minimization of the contamination of the working part of the tool.

Purpose of research. In this paper, we propose a block diagram of a laser cytometry system designed for non-invasive hematological tests. The relevance of this work lies in the growing interest in one's own health, as well as the need to monitor changes in the patient's condition. The aim of this work is to develop a portable laser cytometry system, which is a diagnostic complex and based on an optoacoustic effect - the conversion of optical radiation into thermo-acoustic waves in a medium at a laser wavelength A = 1064 nm. This effect will allow you to obtain information about the state, shape and size of uniform blood cells, to determine the degree of aggregation of erythrocytes and the level of saturation. Flow cytometry is a technology for the rapid measurement of cell parameters and processes occurring in it. The flow cytometry technique consists in identifying the processes of absorption and scattering of light from a laser beam when cells pass through it in a fluid flow.

Methods. The main tasks of this study are to substantiate the structural diagram of the laser cytometry system, determine the constituent parts of the device being developed and identify the connections between them. In the developed block diagram, two measurement channels can be distinguished: optoacoustic and additional, based on Doppler. The signal coming from the additional measuring channel provides information about the blood velocity, which will make it possible to make corrections to the signal received from the optoacoustic channel.

Results. In the proposed system, it is necessary to take into account the corrections for the blood velocity. In the course of this work, a structural diagram of a laser cytometry system was proposed for non-invasive blood analysis. The block diagram of the system was implemented in the computer-aided design system KOMPAS-3D. An analysis carried out using a laser cytometry system can provide information about various diseases and pathological changes in the composition of the blood.

Conclusion. The developed laser cytometry system is distinguished from other hemoanalyzers by its non- invasiveness, which can serve as an excellent advantage in conditions where invasive intervention is impossible or is fraught with certain difficulties

The purpose of research is timely detection of a fire center in the stage of its development can reduce both material and human losses. Therefore, the development of models, methods and algorithms for managing the monitoring system of fire and medical and environmental safety, ensuring an increase in its efficiency through the analysis of video data from unmanned aerial vehicles, is an urgent task.

Methods. The method of classifying aerial photographs of a video sequence when monitoring a fire situation in an autonomous territorial unit assumes their segmentation into identical rectangular segments of a given size and assigning them to one of three classes: smoke, flame, indifferent class. The “strong" and “weak" classifiers are used to classify the segments. The Walsh-Hadamard transform was used to form descriptors for "weak" classifiers. Descriptors are calculated for three "weak" classifiers. First, the Walsh-Hadamard transform is calculated for the window of the entire segment and its spectral coefficients are used for the first "weak" classifier. Then descriptors are calculated for two windows, the sizes of which are two and four times smaller than the sizes of the original window.

Results. Timely detection of a fire in the stage of its development can reduce both material and human losses. Therefore, the development of models, methods and algorithms for managing the fire and medical-environmental safety monitoring system, providing an increase in its efficiency through the analysis of video data from unmanned aerial vehicles, is an urgent task. The classifier consists of three independently trained neural networks - "weak" classifiers. To combine the outputs of neural networks, a simple ensemble averaging block is used. Software for classifying aerial images has been developed, which makes it possible to form a database of segments of "smoke" and "flame" classes, determine the twodimensional Walsh-Hadamard spectrum of aerial image segments, train fully connected neural networks and conduct exploratory analysis to study the relevance of two-dimensional spectral coefficients.

Conclusion. When conducting experimental studies on video sequences containing flame and smoke, the average value of smoke detection accuracy was 86%, flame - 89.5%. False positives for smoke detection averaged 13% and for flame detection 4.5%. To configure and validate the classifiers, we used real data from CCTV cameras in open spaces

The purpose of research is to find optimal methods for preparing an image with the aim of a more stable course of execution of the algorithm for detecting symbolic information.

Methods. The paper uses methods to improve the quality of images by increasing low intensity parameters, digitizing and correcting a digital image, removing noise pixels, methods of image restoration, methods of reducing chromatic aberrations.

Results. The analysis of methods for improving the quality and restoration of images is carried out; the weight parameters are found using the Gaussian filter. A method for correcting the angle of inclination of the original image is presented; a table of the probability of detecting and recognizing symbolic information after applying the methods of improving the selected area of the image for high-speed processing of symbolic information is presented.

Conclusion. In the course of the work, it was revealed that with a sufficient image resolution, the use of methods for improving the selected area allows with a probability of up to 95% to detect and recognize symbolic information at a speed acceptable for a high-speed device (up to 280 ms), depending on the quality of the original image and the number of detected areas containing symbolic information

The purpose of research is to conduct a comparative analysis of several methods for prioritizing test suites described in the literature to select the most promising method for regression testing of software systems.

Methods. Regression testing being performed to check a previously tested software product after the next modification to eliminate detected defects is associated with a significant investment of time and money. Methods for prioritizing test cases are aimed at determining the optimal (from the point of view of early detection of defects) and efficient (from the point of view of the number of executed test cases) order of their execution. Several such methods are known, and the software development team faces the problem of choosing the most effective one. In this paper, the following prioritization methods are considered: a method based on the analysis of the similarity of texts of software requirements, a method based on a joint analysis of risk factors and the importance of requirements, a method based on identifying a critical component in the source code, a method based on the use of additional coverage of functions and a method based on the analysis of the system of artifacts of the life cycle of software product development.

Results. Based on a comparative analysis of the considered prioritization methods, it was concluded that among the considered alternatives, the method based on the analysis of the artifact system of the software product development life cycle seems to be the most effective.

Conclusion. The prioritization method based on the analysis of the system of artifacts of the life cycle of software product development is most fully consistent with the basic ones for modern software engineering methodology. principles of systems analysis and can be used to solve the problems of ensuring the quality of programs.

The purpose of the research is to use the potential didactic possibilities of discussion as a pedagogical technology for the development of soft skills of future IT specialists.

Methods. The research methods is based on the competence-based, contextual and integrative approach in education. We used traditional methods for theoretical and applied research - analysis, synthesis, pedagogical observation, systematization of facts. The material of this research is scientific works that explore practical issues of training future IT specialists in universities, as well as our own experience in organizing and conducting discussions on the results of practices provided for in the educational program of the "Software Engineering" direction.

Results. The relevance of the study is determined by the need to improve the educational process based on the widespread use of interactive technologies in higher professional education for training specialists of a qualitatively new level in the context of the development of the digital economy. These specialists must be competitive and in demand in the labor market, be able to solve problems in a rapidly changing situation. The experience of organizing and conducting discussions based on the results of practical training has proved that the discussion has great opportunities for professional training and development of soft skills of future IT specialists, since it creates situations and conditions for the discussion participant to form, develop and consolidate personal qualities, ensures the manifestation of individuality and active involvement of students in the search and proof of truth.

Conclusions. Discussion is possible only in the implementation of preliminary theoretical and practical training of students on the problem under consideration. As a pedagogical technology of interactive learning, it will ensure success only when analyzing problems for which there is no unambiguous solution, which require active joint discussion, have a personally and professionally significant character for the participant. A significant success factor is the willingness of the practice manager, experts and students to discuss, who are obliged to responsibly accept the rules of interaction before the discussion and observe them by each participant during the discussion, to have a culture of dispute management, adequate self-esteem, openness of thinking, breadth of creative imagination, tolerance.

The purpose of research is to improve the quality of predicting and diagnosing diseases caused by the action of external pathogenic factors through the use of the estimated characteristics of the level of the body's defense.

Methods. It is known that the body's defense system has a highly complex, rather poorly studied, structure of a dynamic type, which does not allow obtaining reliable models for a quantitative assessment of the body's defense level with the subsequent selection of adequate preventive and therapeutic regimens. This work examines the issues of using indicators characterizing the oxidative status of an organism for a quantitative assessment of the level of the body's defense against the effects of many exogenous factors. The methodology for the synthesis of hybrid fuzzy decision rules is used as a basic mathematical apparatus.

Results. It is shown in the work that the indicators of lipid peroxidation and antioxidant activity can be used to quantitatively assess the level of the body's defense against external risk factors. For these indicators, functions of the level of protection and a generalized indicator of the level of protection of the body in the form of a fuzzy decision rule were obtained. The mechanism of embedding this indicator into prognostic and diagnostic decision rules is shown. As a result of expert assessment and mathematical modeling, it was found that the quality of decision making using the proposed models increases by 10 - 20%, depending on the type of problems being solved, compared to models that do not take into account the level of body defense.

Conclusion. In the course of the studies carried out, it was revealed that to improve the quality of predicting and diagnosing diseases caused by the action of external pathogenic factors, quantitative assessments of the level of the body's defense, determined by its oxidative status, can be used. It was found that the quality of decision-making using the proposed models increases by 10 - 20% depending on the type of tasks being solved in comparison with models that do not use indicators of the level of the body's defense.

The purpose of the research is to improve the indicators of the quality of predicting and diagnosing diseases caused by the action of external pathogenic factors through the use of indicators characterizing adaptation mechanisms to assess the level of body defense.

Methods. It is known that the body's defense system has a complex, hierarchically organized rather poorly studied structure of a non-stationary, dynamic type, which does not allow obtaining reliable models for a quantitative assessment of the body's defense level with subsequent selection of adequate preventive and therapeutic schemes. This work examines the issues of using indicators characterizing the adaptive mechanisms of the body for a quantitative assessment of the level of the body's defense against multiple exogenous factors. The methodology for the synthesis of hybrid fuzzy decision rules is used as a basic mathematical apparatus.

Results. The work shows that for a quantitative assessment of the level of protection of the body from external risk factors, indicators of adaptive potential, energy imbalance of BAP, adaptive compliance and a number of immunological indicators can be used. For these indicators, functions of the level of protection and a generalized indicator of the level of protection of the body in the form of a fuzzy decision rule were obtained. The mechanism of embedding this indicator into prognostic and diagnostic decision rules is shown. As a result of expert assessment and mathematical modeling, it was shown that the quality of decision-making using the proposed models increases by 10 -15%, depending on the type of problems being solved, in comparison with models that do not use indicators of the level of protection of the body.

Conclusion. In the course of the studies, it was shown that to improve the indicators of the quality of predicting and diagnosing diseases caused by the action of external pathogenic factors, indicators of the level of the body's defense determined by its adaptation mechanisms can be used. It was found that the quality of decision-making using the proposed models increases by 10 -15% depending on the type of tasks being solved in comparison with models that do not use indicators of the level of the body's defense

The purpose of research is to analyze and propose a method for synthesizing an infological system in the tasks of information and analytical support of beekeeping activities, in terms of identifying the disease of bee colonies with varroatosis using unstructured data obtained from geographically distributed beekeeping farms.

Methods. When conducting research and developing a method for identifying the disease of bee colonies with varaosis, methods of theories were used: algorithms, probabilities and mathematical statistics, calculations, graphs.

Results. Methods of identification of bee colonies affected by varroatosis, as well as ways to assess the degree of infection are considered. During the analysis, it was revealed that the existing methods have disadvantages: there is no systematic physically heterogeneous identification of the disease; different methods of assessing the degree of infection give an error of up to 48%; there is no assessment of the disease with the use of technical vision in the visible and infrared ranges. Taking into account the shortcomings obtained during the critical analysis, a logical model of the infological system is proposed, which allows analyzing unstructured physically heterogeneous data depending on the type of request by an expert. The most effective algorithms for processing acoustic signals and images in the visible range are presented, and an algorithm for processing data at the associative-ontological level of the infological model is proposed in order to develop the most optimal solution about the degree of infection.

Conclusion. The method of identifying the disease of bee colonies with varroatosis, put into the infological system of information and analytical management of beekeeping farms, allows you to generate data on the state of colonies of highly organized insects in the region, the country for departmental institutions for the control and prevention of viral and infectious diseases, as well as for peasant (farm) farms. The results of processing by the infological system can later be used to form the control effects on the means of biological treatment.

The purpose of research is to improve the tuning of fuzzy inference in medical information systems based on knowledge.

Methods. The leading approach to the study of this problem is the adjustment of the rules of fuzzy inference systems based on the principles of the proportional-integral controller.

Results. The relevance of the study is due to the need to improve medical information systems by introducing artificial intelligence technologies. The key element of such systems is the decision inference mechanism, which implements logical inference from a pre-built base of facts and rules in accordance with the laws of formal logic. The efficiency of the decision inference mechanism essentially depends on the quality of its configuration. The article presents an algorithm for tuning Sugeno-type fuzzy inference systems, which allows adjusting the rules of fuzzy inference systems with minimizing the adjustment time and overshoot time, as well as the results of studying the dependence of the error and overshoot on the values of the integral and proportional components.

Conclusion. Development of an algorithm for tuning fuzzy logical inference in medical information systems based on knowledge, which minimizes the time of tuning decision rules and the time of their overshoot. The materials of the article are of practical value for improving knowledge-based information systems. The priorities for further research are the study of the dependence of the rate of adjustment of the decision rules on the form of the membership functions of the input variables and the value of the limiting factor of the integral component.

The purpose of research development of method and architecture of a mobile application that allows remote monitoring of the current state of a person (patient) using high-tech phone sensors, smart watches or fitness bracelets.

Methods. Yearly, the number of people (patients) who need regular care and monitoring of their current state of health increases exponentially. Nowadays, methods and systems of remote monitoring of a patient in pandemic times have become widely in demand along with classical (traditional) methods used in medical institutions. Thanks to the development of such methods and modern technologies, doctors can provide medical services any time and in any place in the mode as close to real time as possible. This article provides an analysis of existing methods of remote monitoring of patients and suggests a new method that allows you to track the current state of the patient on the basis of the VSP, such as: activities, body temperature, pulse, blood pressure, oxygen level in blood, stress level, sleep- extracted using phone, smartwatch or fitness bracelet sensors. The developed general architecture of the Android-based mobile application is also presented. Medical methods of remote monitoring of patients were used to solve the goal set for us, while writing the article. Methods of mathematical modelling, system analysis, software engineering, object-oriented programming and human- machine interaction design technologies were used to develop the overall architecture of the mobile application.

Results. The analysis of existing methods of remote monitoring of patients was carried out, reflecting their main advantages and disadvantages; a new way of tracking the current state of patients is presented; the general architecture of the mobile application has been developed.

Conclusion. Based on the work done, we can conclude that the proposed method is no less effective and accessible to patients (people) in comparison with other proposed methods. It allows improvement of the interaction between patient and doctor. It will give a possibility to doctors, as well as relatives, to respond promptly to any changes in the patient's state of health.