The purpose of research. Radiation diagnostics is central to the detection of malignant neoplasms. Recently, the implementation of screening programs has faced a number of obstacles, including staff shortages and limited funding. The introduction of artificial intelligence (AI)-based systems capable of absolutely accurate sorting of research into two categories - "normal" and "not normal", seems to be a promising solution to these problems. However, before they are widely used, it is critically important to verify their ability to guarantee the safety and high quality of the screening process. The aim of the study is to evaluate the possibility of using autonomous sorting of mammographic examination results in real clinical conditions.  

Methods. The study was carried out in 2 stages. At the first stage, 25,892 mammographic studies processed by the AI service were retrospectively analyzed. A ROC analysis of these results was carried out in order to assess the possibility of configuring the AI service for 100% sensitivity. At the prospective stage, the results of 82,372 mammograms were analyzed. All studies were processed by AI services configured for 100% sensitivity. The tasks of the AI services included the sorting of mammography results into the categories "normal" and "not normal". Next, the decisions of AI services and radiologists on categorization were compared. 

Results. According to the results of a retrospective study, when configuring the AI service for 100% sensitivity, the specificity was 39%. In the course of a prospective study, the proportion of defects (false attribution of research results to the "norm" category) was 0.08%, the specific weight of clinically significant defects in AI services was 0.02%, which is significantly lower than that of a radiologist. 

Conclusion. The use of autonomous sorting of mammographic research results in clinical practice is possible in order to optimize the diagnostic process during preventive measures, as well as under the condition of monitoring the quality of artificial intelligence technologies. Keywords: artificial intelligence, mammography, preventive examinations, radiation diagnostics. Conflict of interest: The author declares the absence of obvious and potential conflicts of interest related to the publication of this article. 

The purpose of research. The goal of the research is to develop an intellectual processing algorithm for classifying text information. As the amount of information grows every day, it is necessary to quickly and efficiently separate significant from unimportant content. Therefore, the development of an intellectual processing algorithm for classifying text information is an urgent task.

Methods. A method is proposed for classifying text information presented in one or more natural languages. It is based on 5 key stages: entering a task, accumulating a queue of tasks, processing the task, generating the result of processing the task, outputting the result. The input task is presented in the form of an http request, the body of which contains a file object. If the intensity of the input stream is greater than the processing speed, then an accumulation of tasks occurs. After selecting the active task (using the FIFO principle), it is processed. As a result of the transformations, the received data is decoded into a string using UTF-8 encoding. Processing refers to the process of categorization, when a search for patterns occurs in a line. Upon completion of rubrication, the result for the selected task is generated. From the accumulated result, a response to the original http request is formed, the body of which contains a list of found categories.

Results. A method and algorithm for processing text data has been developed to determine the topics that are present in the input data set. The algorithm, implemented in software, allows you to work with text data in various languages.

Conclusion. The software development of the text data classification algorithm was carried out in the C++ programming language using the Qt libraries version 5.11. This implementation showed a throughput of 1-5 MB per second (on a homogeneous input text data set). The algorithm allows you to correctly process damaged file formats.

The purpose of the research is to form a comprehensive understanding of how mathematical models are used to interpret complex dynamics related to the distribution, metabolism and excretion of drugs in the human body. The use of mathematical models to predict the required dose of drug prescriptions and establish its effectiveness means a paradigm shift in the field of pharmacology.

Methods. The methodology used in this study was aimed at identifying and analytically reviewing articles that correspond to the objectives of the study. The publications included in the analysis were analyzed and data extracted, focusing on key information such as the mathematical modeling methodology used, the exact predicted treatment effects, the populations studied, long-term prognostic effects, and the assessment of the use of various drug dosing regimens.

Results. In total, 12 publications were analyzed, which used four different methodologies: models with the effects of several different conditions, models that take into account the occurrence of various discrete events, models based on the effects of informative signs taking into account the physiology of individuals, as well as survival models and generalized linear models.

Conclusion. The conducted study of the current state of mathematical modeling in medical research for the purpose of comparative effectiveness is intended for practicing scientists and doctors in conducting further research and introducing innovations. Despite the challenges, the potential impact of these models aimed at bridging the gap between the controlled clinical environment and the real health context is undeniable. The use of mathematical modeling methods to predict the dosage of medicines will improve the quality and effectiveness of personalized medical appointments in the coming years.

The purpose of research.The actual problem in voting systems is not the prevention of fraud and the failure to ensure the integrity of elections. Therefore, the task of building a system of safe and transparent voting is urgent.

The purpose of the research is design and develop an information and computing system based on smart contacts for online voting.

Methods. The presented system has the form of a decentralized system that can overcome a number of limitations, such as the likelihood of human error, falsification of voting results and problems with accessibility, using blockchain technology, which provides protection against unauthorized access and transparent record keeping.

The use of smart contract technology also ensures that the voting process will be automated, transparent and secure. Thanks to the ability to execute self-executing contracts based on predefined rules, smart contracts can eliminate the need for intermediaries, reduce the likelihood of errors and ensure a high degree of accountability.

Results. In order to evaluate the effectiveness of the developed system, testing was carried out, after which a comparative analysis was made with other similar systems.

The system can ensure that votes are counted accurately and cannot be manipulated, thereby increasing confidence in the results of the voting process. In addition, the system can potentially reduce the costs associated with traditional voting methods and improve accessibility for voters, since it can be accessed remotely via a web interface.

In general, the system will be of interest to various organizations and individuals seeking to conduct safe and transparent voting processes.

Conclusion. The use of this software product will provide security and convenience when participating in various online voting, reliable storage of votes and the provision of detailed statistics on the conducted voting.

The purpose of the research is development of a method for determining the influence of destabilizing factors, such as the unevenness of the amplitude-frequency response (AFC) and the nonlinearity of the phase-frequency response (FFC), in non-recursive digital frequency selection filters on the target function of multicriteria structural-parametric synthesis of radio communications from the payload of aviation robotic devices.

Methods. In conducting scientific research, probability theory, mathematical statistics, statistical radio engineering and computational mathematics were used. The study obtained mathematical expressions of the dependence of the probability of error per bit (BER) on the average signal-to-noise ratio when signals pass through symmetrical non-recursive digital filters with quadrature amplitude modulation with a positivity of no more than 4096, signal constellation irregularities of no more than 5, which are the basis for the energy balance of radio lines with aviation robotic devices. The expressions obtained are one of the "foundations" for the implementation of a multi-criteria synthesis of radio systems adaptive to a cognitively formed flight task. In this paper, all the results of the probability of reliability of the received data by means of communication are reflected for the case of rigid decision-making (Gray coding).

Results. In the course of the conducted research: 1) a mathematical model of the structural-parametric synthesis of radio communications with aviation robotic devices is demonstrated, which is based on the criteria for minimizing: electronic computing resources with a given noise immunity; radiation outside the operating frequency band; peak factor signals; the effects of narrowband, broadband and structural interference in the radio channel at a given bandwidth; the use of structural and functional nodes specific to the existing information and communication environment; 2) the analytical dependence of the influence of the parameters of one of several structural and functional nodes - digital filters of frequency selection, on the criteria for the synthesis of communication means has been revealed. The paper considers the most common approximating functions - Kaiser, Tukey, Barlett-Khan, Chebyshev, and also shows the influence of the filter order on the equivalent of energy loss in information communication lines of aviation robotic devices.

Conclusion. The scientific article presents a method for determining the effect of the uneven frequency response of a symmetrical non-recursive digital filter in devices for receiving and processing radio signals of multicriteria means of communication with the payload of aviation robotic devices. The proposed approach increases the reliability of determining the values of criteria for minimizing electronic computing resources for a given noise immunity, radiation outside the operating frequency band, as well as the use of structural and functional nodes characteristic of the existing information and communication environment.

The purpose of the research is assessment of the joint and separate influence of linear and angular deviations of the UAV from the trajectory of rectilinear horizontal flight on the change in parallax images of the underlying surface. Methods. Quantitative estimates are based on a study of the sensitivity of a model describing the functional relationship between the parameters of UAV deviations from a given trajectory and changes in the longitudinal and transverse parallaxes of overlapping images of the underlying surface caused by these deviations.

Results. The difference of longitudinal parallaxes in the absence of linear deviations of the UAV, regardless of the sign of the ordinate of the point in the overlap zone, is always positive and increases with an increase in the level of angular deviations, and transverse deviations are negative and decrease, and the value of the first is three times greater than the second. The difference of the transverse parallaxes in the absence of angular deviations of the UAV at a positive ordinate point in the overlap zone is positive, and the longitudinal parallaxes are negative, and at a negative ordinate, on the contrary. At the same time, regardless of the sign of the ordinate of the point in the overlap zone, with an increase in the level of linear deviations of the UAV, the first increases, the second decreases, and the value of the first is four times greater than the secon.

Conclusion. The magnitude of the parallax differences depends on the levels of linear and angular deviations of the UAV that occurred at the time of registration of the inclined image, and the sign depends on the sign of the ordinate of the corresponding point in the overlap zone of the second pair of images. In this case, the difference of longitudinal parallaxes is always directly proportional to the level of angular deviations and inversely proportional to the level of linear deviations, and transverse parallaxes is directly proportional to the level of angular deviations at negative values of the ordinate of the point and inversely proportional at its positive values.

The purpose of the research  is to analyze the efficiency of the U-net neural network architecture in decision support systems for glioma diagnostics and segmentation of brain areas affected by it on MRI images.

Methods. To conduct experimental studies, a training dataset was generated and the data was normalized. A software implementation of the U-Net neural network architecture was performed using the Keras framework in the Python programming language. The neural network model was trained.

Results. A series of experiments were conducted, during which error and classification matrices were obtained, the efficiency of classification of the trained neural network model for the "Tumor" and "No tumor" classes was assessed using metrics such as Recall, Precision and F1-measure, and the quality of segmentation of glioma-affected areas on the test data set was assessed. The quality of segmentation was assessed using the IoU metric, which reflects the ratio of the areas of the bounding boxes and is used to assess the accuracy of the spatial correspondence of the predicted segmented areas highlighted on the masks. Based on the results of testing the neural network model in solving the problem of segmenting brain areas affected by glioma, the average value of the IoU metric was 0.812, which is an acceptable result.

Conclusion. The testing results showed that the neural network model based on the U-net architecture is able to effectively diagnose the presence of glioma with acceptable values of the classification and segmentation quality metrics, which indicates the possibility of using this neural network model in medical decision support systems for glioma diagnostics, as well as its segmentation on MRI images. However, it is advisable to refine this neural network model to reduce the number of false negative classification results, which is critically important in medical diagnostics.

The purpose of the research. The aim of the study is Russian and foreign studies have shown that malignant breast tumors have significantly different impedance from normal tissues. However, bioimpedance analysis has limitations in resolution, as well as in the imperfection of bioimpedance models required to generate input vectors for machine learning systems.

Methods. The presented study proposes a multimodal classifier, the raw data for which are obtained through an electrode matrix. It also has three channels for processing the results of bioimpedance analysis, with subsequent aggregation of their solutions. An impedance model of biomaterial is proposed, which allows forming descriptors for medical risk classifiers.

Results. Hardware and software for bioimpedance studies have been developed, which include a data collection device for bioimpedance spectroscopy based on an electrode matrix, a device for communication with the object of study, and a device for bioimpedance spectroscopy using an electrode matrix. The software includes interface windows for setting up the bioimpedance research program and training and testing fully connected neural networks. An experimental study of the multimodal classifier on a physical model was conducted using inclusions of higher conductivity (tumor imitation) of various types and sizes in the conductivity range from 1.1 to 1.9 of the background. Based on the obtained images in the two-level neural network of the first channel, the integral risk of breast cancer was determined for all pixels of the image. Statistical studies (ROC analysis) showed sufficient sensitivity and specificity for the screening method - > 0.75. 

Conclusion. Thus, a new model of intelligent support for medical decision-making has been created, integrating the capabilities of bioimpedance spectroscopy, convolutional neural networks and expert assessment of images generated by bioimpedance mapping. However, current data confirming the possibility of separating benign and malignant breast tumors using bioimpedancemetry methods are very limited, which requires further research in this direction.

The purpose of the research. UAVs are widely used in such fields as military, intelligence, and research. As a result, the issue of their use in electronic warfare conditions and the presence of various interference, both man-made and natural, is acute. Thus, the need for UAV navigation using visual data increases.

The purpose is study of the main negative factors affecting the quality of aerial photography images and methods for eliminating them to construct a correct orthomosaic for UAV visual navigation.

Methods. Mathematical methods are proposed to eliminate negative distortions in UAV camera images using various image transformation approaches. After applying these methods to the original images, corrected versions are obtained, which are used to construct the tile covering. Tiled coverage created from processed images provides continuous and uniform coverage of the area collected during the UAV’s flight. This allows you to obtain exact coordinates of images and objects on them.

Results. An analysis of the main methods for eliminating negative factors that distort images during aerial photography for the visual navigation of UAVs, as well as a brief overview of the visual navigation methods themselves.

Conclusion. To successfully implement visual navigation of a UAV, it is necessary to apply a number of methods for converting aerial photography images, as well as the use of certain algorithms for visual navigation. It is concluded that in addition to the use of mathematical and software algorithms, it will also be necessary to analyze and study the necessary computing power for the use of the entire hardware and software complex on board the UAV, taking into account its weight-dimensional properties.

The purpose of the research is development of scientific and technical ways to reduce the quantitative indicators of false alarms when operating an on-board radar station against the background of the underlying surface (earth) against the background of passive interference.

Methods. When conducting scientific research, methods of probability theory, mathematical statistics, statistical radio engineering and computational mathematics were used. The study identified a number of methods and technical solutions based on them that make it possible to increase the efficiency of the functioning of airborne radar stations against the background of passive interference. The paper proposes a method for expanding the signal spectrum to 1 GHz by reducing the resolved volume of airborne radar stations. Physically, this is determined by the fact that with a decrease in the resolved volume, the size of the underlying surface area from which the signal is reflected decreases. In order to improve the quality of detection of objects against the background of the underlying surface, a method of using polarization modes is proposed.

Results. In the course of the research: a technical solution was proposed based on the method of expanding the signal spectrum to 1 GHz by reducing the resolution volume of airborne radar stations designed to convert radio frequency signals into digital form, using a mixed signal receiver with direct digitization at radio frequency, such as the AD6688 ; a design of a low-baseline radar system has been developed, consisting of two positions, the antennas of which are located within the average width of the lobe of the backscattering diagram of the irradiated object; a feature of the antenna is the ability to receive and emit signals of the same linear polarization, but orthogonal to the polarization of the first position (including . horizontal and vertical polarization signals); an important relation was obtained for a lowbaseline polarization measuring system (MPIS) when the distance between two partial antennas can be much less than the distance to the measured object. 

Conclusion. The scientific article proposes methods and technical solutions based on these methods to reduce the quantitative indicators of false alarms when operating an on-board radar station against the background of the underlying surface (ground) against the background of passive interference. The proposed approach allows us to move on to the synthesis of a low-baseline polarization measuring system.

The purpose of research. The main goal of assessing reliability is to quantitatively substantiate the measure of confidence in a particular process. The article discusses the methodological and practical aspects of assessing the reliability of sociological research conducted on the Internet. Emphasis is placed on analyzing the specific problems encountered when using online surveys and other digital data collection methods. Issues of sample representativeness and a number of other quantitative indicators that affect the reliability of the assessment of sociological research are discussed.

Methods. The article is devoted to methodological and practical aspects of assessing the reliability of sociological research conducted on the Internet. Issues of sample representativeness, weighting coefficients, data analysis, testing for systematic errors, and calculation of Cronbach’s alpha coefficient are discussed.

Results. The main steps for calculating the reliability of sociological research conducted on the Internet are presented. Key steps include proper sample selection and adjustment, use of weights, performing statistical analysis, and estimating confidence intervals. These methods help minimize errors and increase the reliability of the data obtained.

Conclusion. The proposed methods for assessing the reliability of the Internet will help improve the quality of data and the reliability of the results, namely, Online surveys can be subject to various types of biases, including self-selection of participants, when only certain groups of people decide to participate in the survey. Credibility assessment will promote fair and transparent research, which strengthens the trust of respondents and the public in research projects.

The purpose of the research analysis of known invasive and non-invasive examination methods, determination of the necessary criteria for assessing the degree of fatigue of submariners, a survey of Navy personnel involved in service on submarine ships was conducted, on the basis of which a justification of research directions was carried out for the subsequent development of a system for collecting, evaluating and analyzing the physiological state and factors affecting the fatigue of military personnel.

Methods: the use of an experimental non-invasive research method to determine the degree of fatigue and physiological condition of submariners based on three criteria during the month, the analysis of the results obtained, the establishment of a comparative analysis method during the development, a structural analysis of the system based on previously known devices and sensors.

Results. The dependence of the studied indicators on the time of watch keeping and their connection with the increase in fatigue were found. It has been established that in order to develop a system for monitoring the fatigue of submariners, a systematic analysis and objective assessment should be carried out, including: determination of methods for monitoring the condition of military personnel; application of knowledge from medicine, physiology, biophysics, biomechanics, bioengineering, electronics, circuitry and programming, to develop effective methods for monitoring physical condition and fatigue. Based on the analysis of domestic and foreign techniques and devices, a proprietary method for implementing a system for collecting assessments, analyzing the physiological state and factors affecting the fatigue of military personnel is proposed.

Conclusion. It is concluded that it is necessary to conduct non-invasive studies of the degree of fatigue, before proposing the development and proposal of its own device and methodology for assessing the degree of fatigue, capable of implementing individual features of the system for operational monitoring in order to improve combat readiness, situational awareness, health, safety, mobility of submariners.

The development of such monitoring systems and devices is necessary in the modern world to prevent or prevent disasters without reducing the efficiency of submariners.

The purpose of the research is a multidimensional analysis of the "quality of life" of patients before and after dental prosthetics. It is necessary to assess the quality of life of patients after prosthetics, depending on the type of prostheses, gender, and age of patients and give recommendations on the choice of prosthetics method. 

Methods. Dental prosthetics was performed at the clinic of the Moscow State Medical University named after A. I. Evdokimov, four types of prostheses were tested - the classic traditional prosthesis (TR) and three types of digital prostheses (D1, D2, D3). Based on the developed OHIP-20 DG questionnaire, the quality of life of patients was assessed before prosthetics, immediately after prosthetics and six months later. The quality of life of patients after prosthetics was determined within the framework of the theory of latent variables. Using a four-factor analysis of variance, the impact on the quality of life of the type of prostheses, the duration of adaptation after prosthetics, gender and age of patients was assessed. 

Results. Within the framework of the theory of latent variables, it is shown that the developed questionnaire can be used as a measuring tool to analyze the influence of the studied factors on the quality of life of patients after prosthetics. Due to the use of four-factor analysis of variance, the accuracy of statistical analysis has been improved and the statistical significance of four sources of variance has been revealed. Based on the results of statistical analysis, recommendations on the choice of prosthetics method have been developed. 

Conclusion. A multidimensional analysis of the studied factors affecting the quality of life of patients after dental prosthetics was carried out. The quality of life of patients increases statistically significantly after prosthetics. Due to the use of a four-factor model of variance analysis, the precision of assessments of the quality of life of patients has been improved. The prosthetics method (D1) is recommended for women, the prosthetics method (D3) is recommended for men. The obtained results are recommended to be used in practice.

The purpose of the research is to develop a conceptual model of an object oriented system and implement it using a functional language with metaprogramming support. 

Methods. A conceptual model of an object oriented system was developed based on a dynamic object system with message passing and dynamic dispatch. The developed object oriented system includes functions for creating and deleting classes, creating and deleting object instances of a class, functions for working with object properties, functions for adding methods to a class and passing messages. Inheritance is also possible, when a child class will have the properties of the parent class and its own properties. 

Results. The object oriented system was implemented using a set of macros and helper functions. The basic data structure was a hash table with key access capabilities, which was also implemented using macros. When a class is created, an instance constructor is automatically generated, setting the initial values of the object’s fields. Inheritance is implemented as the inclusion of fields of a parent class in a child object. Polymorphism is implemented as dynamic dispatch: when processing a message, a handler method is searched. The resulting object oriented system, together with the hash table module, occupies 97 lines. 

Conclusion. As a result of the work, a conceptual model of an object oriented system was created and implemented, which includes the main functions of the object oriented programming paradigm. It has been shown that macros can be used to create a compact object oriented system without the need to add any new functions or capabilities to the functional language interpreter.