Работая с нашим сайтом, вы даете свое согласие на использование файлов cookie. Это необходимо для нормального функционирования сайта, показа целевой рекламы и анализа трафика. Статистика использования сайта отправляется в «Яндекс» и «Google»

Понятно

Научный журнал Моделирование, оптимизация и информационные технологииThe scientific journal Modeling, Optimization and Information Technology

Online media
issn 2310-6018

submit
a manuscript

metadata of articles for the last 2 years

Approaches to processing big spatiotemporal uncertain data in GLONASS+112

2023. T.11. № 1. id 1307

Anikin I.V. Petrov G.E.

DOI: 10.26102/2310-6018/2023.40.1.026

The paper examines some approaches to processing big spatiotemporal uncertain data in GLONASS+112. This system is used for managing interaction between operational services in the Republic of Tatarstan and collecting and processing data characterizing various incidents, based on calls received by a common emergency number "112". The performance and scalability of several basic operations for managing big data (query with threshold, JOIN, k-nearest neighbors algorithm) were studied; they were adapted for operating data under spatial and temporal uncertainty. New approaches to clustering and associative rules mining for uncertain data are suggested. Modernization of ST-DBSCAN algorithm for clustering spatiotemporal data is proposed. This algorithm is integrated into the association rules mining process. The program complex for forming the associative rules for spatiotemporal data under uncertainty has been developed. The complex is applied to analyze GLONASS+112 data as well as the information about weather conditions obtained from external sources. The associative rules being formed can be used by various units in operating services for decision-making and resource-planning. This would help to increase the efficiency of managing the emergencies and undesired incidents.

Keywords: data mining, spatiotemporal data, uncertainty, clustering, associative rules, emergency management

Optimization of passenger transportation management under the conditions of unstable seasonable passenger traffic

2023. T.11. № 2. id 1306

Shtepa A.A. Belokurov V.P. Korablev R.A. Busarin E.N.

DOI: 10.26102/2310-6018/2023.41.2.010

Passenger public transport is very important for the social-economic development of any territory, and that is why consideration of the issues of sustainable functioning and optimization of the transportation management is relevant, which underlies the authors' research. Owing to this, the article addresses the problem of passenger transportation management optimization under the conditions of unstable seasonable passenger traffic in cities. The leading method to study this transport problem is dynamic programming, which is based on the package of recurrence relations. The article presents an optimization criterion in the situational task to manage passenger traffic, demonstrates the objective function that allows optimal additional distribution of passenger vehicles along each city route depending on the time of year, identifies the optimal number of passenger vehicles and substantiates the method of dynamic programming in solving a transportation problem. As the result of the study, an algorithm that determines the required number of rolling stock on the route of public transport by dynamic programming has been developed and the results of calculations depending on the period of instability of seasonal passenger traffic have been provided. The materials of the article are of practical value for applied researchers in the auto transport complex.

Keywords: dynamic programming, task, criterion, modeling, optimization, transportation, seasonality, transport

Mathematical modeling of microclimate indicator influence on the intensification of agricultural production on the example of broiler farming

2023. T.11. № 1. id 1305

Belykh T.I. Burdukovskaya A.V. Ivonina O.Y. Rodionov A.V.

DOI: 10.26102/2310-6018/2023.40.1.018

The article deals with the regression mathematical models that describe the influence of mechanical and automatic microclimate control systems on the growth and development of Arbor Acres cross broiler chickens in Sayansky Broiler agro-industrial complex with outdoor maintenance. The paper regards the influence of such parameters as microclimate, temperature, humidity and illumination. To test the statistical hypothesis of homogeneity of the two considered samples, the Cramer-Welch and Wilcoxon tests are employed. Chou's test is presented concerning the possibility of constructing two different mathematical models of the same type that illustrate the patterns of the modeled indicators development. Statistical estimates of the significance of the constructed models and the factors included in the models are calculated. An interpretation of the results of regression analysis in relation to the subject area under study is given. In addition, a graphical visualization of the analysis of the initial and output data of the constructed models was performed. The ranking of factors is carried out according to the degree of their impact on the resulting indicator using elasticity coefficients and the shares of their influence. The main production indicators are calculated based on the results of livestock rearing: average daily gain, absolute gain, relative growth rate, safety. The article calculates the economic effect for one full cycle of farming broiler chickens.

Keywords: mathematical modeling, regression model, determination coefficient, statistical significance of the model, arbor Acres cross broilers, microclimate

Face reconstruction as a technique for enhancing accuracy of human recognition in a video frame

2023. T.11. № 1. id 1303

Prichko I.O. Afanasyev A.D.

DOI: 10.26102/2310-6018/2023.40.1.019

The article considers an approach aimed at enhancing the accuracy of human identification by facial image in video surveillance systems, using the reconstruction method based on generative-adversarial networks. During the investigation of offenses, one often encounters video recordings of people of interest for the investigation with a low resolution or containing visual disturbances of different genesis, which limits the implementation of techniques for identifying the person by means of deep learning neural networks. This causes two problems: one pertaining to face detection of a certain person in the video data and another regarding the search for a selected person in the frame contained in the database. The reconstruction of a face using generative adversarial networks is known to significantly improve low-quality face images, but this method is demanding of the content of the original image as any occlusions and disturbances are multiply amplified. The paper presents an approach composed of image preprocessing on the basis of the known property of video recordings – the presence of object image versioning. The proposed algorithm helps to correct much of the visual noise and subsequently reconstruct the face image with high quality. During the experiments, we have also found a method of facial elements restoration which enables the increase in the recognizability of an unknown face by a person, which can be important during the identification by witnesses.

Keywords: face recognition, face restoration, video analytics, superresolution image, generative and adversarial networks, computer vision

Automated system for classifying pancreatic ultrasound images based on the segment-by-segment spectral analysis method

2023. T.11. № 1. id 1302

Kondrashov D.S. Sukhomlinov A.Y. Shulga L.V. Al-Darraji C.H. Belozerov V.A. Filist S.A.

DOI: 10.26102/2310-6018/2023.40.1.021

Classification of ultrasound images is the prevailing tool in the diagnosis of many pancreas diseases. It takes years of experience and training for a doctor to interpret an ultrasound image. Therefore, the development of models, methods and algorithms for improving the reliability and quality of interpretation of ultrasound images through the use of specialized software tools that reduce the risk of diagnostic errors is a relevant issue. The proposed method involves the segmentation of ultrasound images into segments of prescribed size of a rectangular shape and their correlation to one of three classes: oncology, pancreatitis, indifferent class. Classification is carried out by means of "strong" and "weak" classifiers. For "weak" classifiers, the Walsh-Hadamard transform is employed in the formation of descriptors. Descriptors are calculated for three "weak" classifiers. For the first "weak" classifier, the spectral coefficients of the Walsh-Hadamard transform are used, calculated for the window of the entire segment. After that, the descriptors are calculated for other "weak" classifiers, which are windows with sizes that are two and four times smaller than the sizes of the original window. The classifier consists of three independently trained neural networks – "weak" classifiers. To combine the output data of neural networks, an averaging block over the ensemble is used. Software has been developed for classifying ultrasound images which helps to create a database for the "oncology" and "pancreatitis" class segments, determine the two-dimensional Walsh-Hadamard spectrum of ultrasound image segments, train fully connected neural networks and conduct exploratory analysis to study the relevance of two-dimensional spectral coefficients. Experimental studies on the classification of ultrasound images containing oncology and pancreatitis showed an average accuracy of oncology detection – 88.4 %, and pancreatitis – 85.7 %. Errors of the second type averaged 10.2 % when pancreatitis was detected and 5.2 % when oncology was detected. To set up and test the classifiers, real data from pancreatic ultrasound were used.

Keywords: ultrasound, pancreas, oncology, pancreatitis, disease detection, segmentation of ultrasound images, neural network, classification of ultrasound images

Application of machine learning for adjective ordering in English sentences

2023. T.11. № 1. id 1301

Terekhova A.D. Terekhov G.V. Sychev O.A.

DOI: 10.26102/2310-6018/2023.40.1.028

The article presents a methodology for solving the adjective ordering problem in English sentences by determining their hypernyms. The determining of a hypernym can be represented as a classification task; therefore, the most popular machine-learning classification methods were compared, they include the following: nearest neighbors method, logistic regression, decision classifier, support vector machine and naive Bayes method. The models were trained on a sample that contained adjectives and their hypernyms. For each adjective, similar adjectives from the training sample were selected; the most semantically appropriate hypernym was determined based on them. The use of information about word similarity from GloVe embeddings is proposed. The optimal values of hyperparameters for the K-Nearest Neighbors method were selected by means of the gridsearch technique. The quality of data classification was evaluated applying the metrics of precision, recall, and F1-measure for each of the methods. Since there were no ready-made datasets of classified adjectives, 300 adjectives were classified manually to create necessary samples.

Keywords: adjective ordering, natural language processing, word vector representation, gloVe, classification methods, hypernyms

Prediction of coiled tubing material residual life based on the kinetic theory of fatigue

2023. T.11. № 1. id 1300

Ivzhenko S.P. Vdovin A.S. Pechenkin V.V. Rakcheev V.L.

DOI: 10.26102/2310-6018/2023.40.1.017

Coiled tubing technologies are actively used in the process of well drilling and well intervention. During the operation of a coiled tubing unit, it is necessary to obtain a real-time assessment of the residual life of the installation equipment, in particular, the residual life of the coiled tubing. The main damaging factors of a flexible pipe include bending loads, internal pressure effects, axial impacts, exposure to aggressive media. The most important task of predicting the state of a coiled tubing is the construction of a mathematical model that allows the most accurate description of the process of fatigue damage accumulation under low-cycle loads. An analysis of the literature sources available for study showed that nowadays it is essential to develop methods and algorithms that enable assessing the knee fatigue of the flexible tubing material on a complex trajectory of movement where the pipe is subjected to bending loads with different intensities. The solution to this problem substantiates the development of a mathematical model that relates the calculation of damage in the area of low-cycle deformations, taking into account damage that has been previously kneeled. The purpose of this research is to develop methods and algorithms for constructing a predictive model of the current state of the coiled tubing material considering the accumulated damage based on semi-empirical models as part of the kinetic theory of fatigue. By means of the methods for constructing algorithms for processing data from low-cycle tests as part of the kinetic theory of fatigue and mathematical models for estimating the residual life of the test sample, the article proposes a solution that helps to calculate the damage parameter of the sample in the event of damage accumulation in various sections of the coiled tubing trajectory. The materials of the article are of practical value for researchers dealing with the problems of calculating the residual life of flexible pipes under the conditions of their cyclic deformation.

Keywords: coiled tubing, low-cycle fatigue, damage accumulation, cyclic stresses, kinetic theory of mechanical fatigue, equivalent stresses

Process optimization algorithm for forming the production schedule of custom production enterprises

2023. T.11. № 1. id 1299

Kuznetsova Y.A. Kharsekin I.R. Knyazeva I.O.

DOI: 10.26102/2310-6018/2023.40.1.008

This article deals with the problem of downtime in production enterprises with time-based wages. Irrational allocation of resources leads to losses. This problem can be solved through the automation of production schedule process formation. In the presented paper, the authors use the terminology of schedule theory. As a research result, an algorithm that is a solution to the problem was developed. The algorithm assumes a random selection of an operation based on the criteria; the resource availability in a given time period is checked and then assigned to the appropriate operation. The algorithm is executed cyclically until all operations or resources are involved for a given time period. The construction of the algorithm is based on a calculated record, the excess of which leads to the termination of algorithm implementation and its re-launch. The described algorithm, after the expiration of the number of iterations specified by the user, visualizes the solution through the Gantt chart to ensure dispatching of production processes. The results obtained by the authors will make it possible to form a system for the intelligent formation of a production schedule and introduce it into the existing management system of a manufacturing enterprise engaged in the production of products from polymer composite materials.

Keywords: schedule theory, combinatorial optimization, heuristic algorithms, discrete programming

The methodology for unmanned aerial vehicle trajectory forming for the autonomous gathering of visual data on electric powerline defects in infrared and ultraviolet spectra

2023. T.11. № 1. id 1297

Astapova M.A. Lebedev I.V. Uzdiaev M.Y.

DOI: 10.26102/2310-6018/2023.40.1.003

Powerline element heat and corona discharge occurring in current conducting elements are significant problems that may cause serious faults in energetic systems. These defects require special equipment that makes it possible to obtain images in infrared (IR) and ultraviolet (UV) spectra for heat and corona discharge detection, respectively. The use of autonomous unmanned aerial vehicles (UAV) equipped with the appropriate cameras provide automation of such defect detection. Concurrently, the trajectory of the autonomous UAV should be formed according to the spatio-geometric features of the inspected power lines and the requirements for the image sample obtained during the inspection of the damaged powerline. However, the issues related to forming UAV trajectory consistent with the specified requirements have not been properly explored. As part of this research, a new method for UAV trajectory forming is presented. The method is characterized by forming the trajectory according to the spatio-geometric features of the inspected powerlines with its key components and the requirements for the collected data (the presence of damage in the image, object representativeness, unification of the represented objects). The method was tested in the Blender 3D modeling environment by simulation of the autonomous wire heating and corona discharge inspection in three powerline types. As a result, a sample of IR and UV spectra images was collected. The sample consists of 1300 images, which represents 1376 unique angles of 17 cases of simulated damage, which indicates the viability of this technique for constructing UAV autonomous flight trajectories in order to collect representative sample data on powerline damage in UV and IR spectra.

Keywords: autonomous UAVs, trajectory construction, automatic monitoring, aerial survey algorithms, data collection

Consensus management and multi-agent reinforcement learning in the problems of structuring project networks

2022. T.10. № 4. id 1296

Razinkin K.A. Sokolova E.S.

DOI: 10.26102/2310-6018/2022.39.4.017

An approach to the construction of technological platforms (project networks) designed to enable self-organization of participants with key competencies into a team to carry out activities with initially set goals, the achievement of which determines the completion of the project, is considered. At the initial stage, the project network is in ‘the sleep mode’, i.e. the usual for a social network information exchange between potential project team members takes place on the network and, consequently, ‘traditional agents’ or actors interact on the network. A two-level scheme is proposed for organizing the process of interaction between agents of the project network in work teams: intra-cluster and inter-cluster. The effectiveness of the first interaction is estimated as the result of consensus modeling in asynchronous multi-agent systems with discrete and continuous time. At the same time, if consensus is reached, then the cluster at the second level of the hierarchy can be considered as a single agent node participating in the next cycle of interaction – inter-cluster. At this level, the solutions being formed are considered as Markov decision-making processes. Accordingly, as a mathematical apparatus for modeling this type of interaction, it is planned to use one of the machine learning methods – reinforcement learning when solving the problem of optimal resource allocation between processes within a single project.

Keywords: project network, consensus, multi-agent management, reinforcement learning, intra-cluster interaction of agents, inter-cluster interaction of agents

Neuro-predictive control system for a mobile nonholonomic three-wheeled robot in an environment with static obstacles

2023. T.11. № 1. id 1295

Berezina V.A. Mezentseva O.S. Mezentsev D.V.

DOI: 10.26102/2310-6018/2023.40.1.024

This article proposes to track and predict the trajectory of an autonomous nonholonomic three-wheeled mobile robot in an environment with static obstacles using a neuro-predictive control system. This system consists of a modified Elman neural network (to track the position and orientation of the robot), a neural network model of an obstacle (to determine the point cloud of an obstacle) and cubic spline curve interpolation methods and a PSO algorithm (to smooth the obstacle avoidance curve and ensure the shortest distance). A new trajectory for avoiding an obstacle is built on three points (before the obstacle, the center of the obstacle, after the obstacle). The proposed control system improves the efficiency of mobile robot control and provides the smallest deviation from the movement trajectory, in general, and in the place where the obstacle is bypassed, in particular. The neuro-predictive control system is compared with the classical PSO algorithm, and, within the system itself, methods for smoothing the obstacle avoidance curve (cubic spline interpolation and PSO algorithm) are compared. Algorithms are compared according to such criteria as the average distance of the robot from the obstacle when rebuilding the trajectory, the speed of movement, the time it takes to bypass the obstacle. In addition, the deviation from the given trajectory of movement is checked: movements along the lemniscate and along the square. The simulation results showed that the neuro-predictive system is more efficient (by 28.1 % on average) in avoiding an obstacle (provides the shortest distance) and performs this maneuver faster (by 17.2 % on average) than the classical PSO algorithm. Also, within the system itself, the PSO-algorithm works more efficiently to construct an obstacle avoidance curve (3.3 % closer to the obstacle and, on average, 88.2 % less root-mean-square error) than cubic spline interpolation. At the same time, the neuro-predictive control system copes much better with following the desired trajectory than the classical PSO algorithm.

Keywords: neuro-predictive control system, elman recurrent neural network, nonholonomic three-wheeled robot, motion trajectory prediction, obstacle avoidance

System analysis and corporate organization management based on the ESG-approach

2023. T.11. № 1. id 1292

Stoianova A.D. Trofimets V.Y. Kalach A.V.

DOI: 10.26102/2310-6018/2023.40.1.011

The issues of strategic management of fuel and energy complex enterprises in accordance with the ESG approach are considered. The existing variants of measures used by Russian and foreign companies in the field of ESG policy are investigated. The analysis of existing methods has been carried out, unresolved scientific problems and prospects for further research have been identified. It is concluded that attracting new investors is one of the main reasons why companies pursue an active ESG policy. It is shown that a successful ESG policy helps to reduce the risk of a company's value falling in the market, which makes it more attractive to investors and shareholders. The features of the application of the ESG approach for fuel and energy companies are revealed. The features of ESG ratings are noted. It is demonstrated that an active policy in the field of ESG leads not only to an increase in financial indicators, but also to the adjustment of the company's market value. It is concluded that in order to integrate all ESG directions into a single platform solution based on ESG principles, joint actions of the state, rating agencies, companies, specialists in the field of sustainable development as well as investors are necessary. Moreover, the implementation of a simplified version of such solutions directly on the basis of companies brings low efficiency and will not allow achieving a comprehensive effect.

Keywords: strategic management of enterprises, ESG approach, criteria for evaluating the effectiveness of management, ESG rating, ESG principles, fuel and energy complex

Neural network model of robotic complex control during emergency rescue operations under the conditions of the Far North

2023. T.11. № 1. id 1291

Tsarkova E.G. Kalach A.V. Bobrov V.N.

DOI: 10.26102/2310-6018/2023.40.1.010

The geopolitical situation and the increase in criminal and terrorist threats dictate the need to develop new territories, including the North of Russia. The article presents the results of a study of an artificial neural network mathematical model that takes into account delays designed to control an autopiloted ground-based robotic complex employed for transportation during emergency rescue operations under difficult natural and climatic conditions of the Arctic region. The universal nature of the proposed method is shown. An approach to finding a solution to the optimization problem using the necessary optimality conditions in the form of the Pontryagin maximum principle and the method of rapid automatic differentiation is described. A problem-oriented software product has been created, which is based on the developed computational algorithm for constructing approximate optimal control. The results obtained from numerical experiments confirm the effectiveness of the developed algorithm in finding an approximate optimal solution to the problem under consideration. The created software tool can be used to train an ANN with dynamics described by a system of differential equations with consideration to delays. The proposed mathematical model of ANN is suitable to solving a wide range of applied robotics tasks, including those aimed at developing technical means for emergency rescue operations under difficult natural and climatic conditions of the Arctic region. The flexibility, stability and adaptability of the selected model to changes in input parameters determine the prospects of using the developed computational algorithm to solve control problems in complex technical systems.

Keywords: robotics, emergency rescue operations, optimal control problem, maximum principle, artificial neural network training, safety

Indicator-free information and measurement method for determining flow structure parameters in heat and mass exchangers

2023. T.11. № 1. id 1290

Persidskiy A.V. Topilin M.V. Merentsov N.A. Golovanchikov A.B.

DOI: 10.26102/2310-6018/2023.40.1.014

The article proposes a method for determining differential and integral response curves and their dispersion ‒ the central moment of the second order according to the velocity profile, as well as the dependence of the velocity head or the height of the manometric liquid column in the Pitot-Prandtl tube on the radius of the apparatus. Calculated dependencies for determination of flow structure parameters are given on the basis of experimental data for distillation column by vapor phase and boiling solution, as well as equations of their conversion into C- and F- response curves, dispersions. Indicator methods for determining flow structure parameters are considered drawing on pulsed or stepped input of indicators into the flow with subsequent recording of changes in the concentration of "labeled" particles, molecules and ions over time. The indicator method of measuring parameters of the flow structure of liquid-phase mass exchange products is regarded using the input of a tracer, the electrical conductivity of which differs from the electrical conductivity of the carrier stream with subsequent registration of the signal at the output by a conductometric cell. Indicator methods for determining parameters of gas-phase carrier flows structure based on input of smoke particles, radioactive isotopes, as well as ionization of gas flow at the inlet to the engine displacement of the apparatus with subsequent recording of signals and recognition of model parameters are presented for comparison. The advantages of the proposed (information and measured) method of calculating the parameters mentioned above compared to the indicator method are shown related to the choice of the indicator, its accurate supply in the form of a pulse or step signal at the inlet of the object and registration at the outlet, as well as data on the densities of the liquid, gas or vapor phase in the object and the density of the manometric liquid in the Pitot-Prandtl tube.

Keywords: flow structure, hydrodynamics, gas dynamics, flow rate, velocity profile, mass exchange, heat and mass exchange, rectification, absorption, adsorption

Ensuring the integrity of telemetric information on the state of a complex technical object

2023. T.11. № 1. id 1289

Frid A.I. Vulfin A.M. Guzairov M.B. Berkholts V.V.

DOI: 10.26102/2310-6018/2023.40.1.002

The relevance of the study is due to the need to improve the security of telemetry information transmitted to the manufacturer, which allows analyzing the state of on-board subsystems, failures and malfunctions, as well as detecting possible intruder impacts. On the basis of algorithms for predictive analytics of telemetric information, malfunctions and pre-failure states of on-board subsystems, and automatic control systems for the gas turbine engine of an aircraft can be detected. Efficient collection and analysis of telemetry helps specialists of ground technical services to plan repair and preventive measures. Telemetry accumulated over a long period makes it possible to continuously adapt digital models of aircraft subsystems, blocks and modules, which can be used to provide significant decision support in the event of a technical failure. In this regard, the purpose of the research is to increase the probability of detecting unauthorized modification of the transmitted telemetry data on the state of a complex technical object – a gas turbine engine automatic control system. The main method for studying this problem is the intellectual analysis of multidimensional time series of parameters characterizing the state of the onboard systems of the aircraft. The article develops the structure of the system for monitoring the integrity of telemetric information transmitted from the aircraft based on the analysis of the consistency of multidimensional time series. A comparison is made between telemetry from the aircraft and the outputs of a digital model of a complex technical product. At the output of the system, the probability estimate of integrity violation of the data transmitted to the manufacturer is formed. The materials of the article are of practical value for increasing the level of information protection when it is being transmitted from the aircraft to the manufacturer.

Keywords: telemetry information, intellectual analysis, multidimensional time series, ensemble of neural network classifiers, time series consistency parameters

The forecast of cancer prevalence in the regions and municipalities of Russia based on a multivariate model

2023. T.11. № 1. id 1286

Stepanov V.S.

DOI: 10.26102/2310-6018/2023.40.1.022

The article considers the issue of the relationship between the cancer prevalence in some Russian regions and age composition along with a set of environmental and hygienic variables. The presence of the relationship between the prevalence of this pathology in the territory and the lag values of the variables are shown. The complex of factor explanatory variables contains an indicator of atmospheric air pollution in the settlements of the territory, a qualitative variable according to the degree of its technogenic pollution, the specific volume of polluted wastewater discharge, the concentration of benzo(a)pyrene, and the age composition. On this basis, an econometric model has been built that has a high statistical quality: the coefficient of determination is above 95 %, the approximation error is less than 3%. One of the factors was of the ordinal type; therefore, the result was a linear regression model with a variable structure containing two dummy variables. The model parameters were estimated by the least squares method using panel data with Russian regions for 2017-18. These data included observations on the populations of people with oncologic pathologies in the regions and factor variables. The presence of lags in the latter makes it possible to predict the number of people suffering from tumors of any localization with a planning horizon of 1 year. Such forecasts were carried out both at the level of regions and in the context of municipalities. Based on the resulting equation, one can make evidence-based managerial decisions aimed at canсer prevention in specific regions of Russia as well as to build agent-type simulation models.

Keywords: regression model, atmospheric air pollution, sewage pollution, benz(a)pyrene, technogenic pollution of the territory, smoking, malignant neoplasm, region, municipality

Investigation of the influence of aggressive behavior of minors on their deviant activities based on the Buss-Durkee method by constructing a fuzzy logic production system

2023. T.11. № 1. id 1284

Gish A.Z. Kovalenko A.V.

DOI: 10.26102/2310-6018/2023.40.1.009

The problem of deviant behavior prevention in minors is particularly relevant at present since this age group belongs to the most socially vulnerable category. In order to identify the deviation in adolescents, it is necessary to analyze and identify manifestations of their aggressive behavior. This study is based on the identification of predisposition to the development of aggressive behavior based on the Buss-Durkee method. 10 factors identified by the authors of this technique have been considered. A five-level classifier for input and output factors of a fuzzy logic production system is proposed. The membership functions are selected by applying the method of expert assessments reflecting the competent opinion of a specialist regarding the affiliation of the elements with the term set. Fuzzy logic rules have been defined, in the capacity of which the data on the test results obtained by minors aged 14-15 years have been entered and supplemented with a view to ensuring the completeness of the system. To reduce the number of fuzzy logic rules and enable consistency in it, a hierarchical structure of input factors has been formed. As a result, an intelligent system, namely a fuzzy logic production model of deviant behavior of minors "Deviance level BD", has been created, which can be used to prevent deviant behavior in minors, as well as to analyze and identify manifestations of their aggressive behavior to prevent them from committing criminal acts.

Keywords: fuzzy logic production system, fuzzy logic model, deviant behavior, buss-Durkee method, five-level classifier, term-set, membership function, fuzzy logic rules

Smoke recognition model in an open area using a convolutional and recurrent neural network

2023. T.11. № 1. id 1282

Shestakov D.A. Shagrova G.V. Strukova V.G. Doronin V.A.

DOI: 10.26102/2310-6018/2023.40.1.027

Timely detection of the source of ignition is an important issue of protecting people, animals and vast territories from fires. The relevance of this study is due to the fact that the existing visual smoke detection systems have a number of disadvantages that do not allow them to be effectively applied in practice. The surveillance system must rely on visual characteristics and often mistakenly identifies fog and clouds as smoke. The aim of this study is to increase the efficiency of smoke detection by using an advanced smoke detector model based on the "You-Only-Look-Once" neural network and a classifier with long-term short-term memory (LSTM). The main objectives of the study are structural description of the proposed smoke detection model, mathematical description of the trained model and comparative analysis with existing neural network models. By changing the structure of the LSTM, a reduction in the number of layers and cells is achieved, and the performance of the original LSTM is maintained. The proposed method provides a reduction in the number of parameters by several times and a faster processing time on the data set used. The article presents the results of the performance of artificial intelligence systems for a comparative analysis of neural network candidates in the smoke recognition model.

Keywords: smoke detection, fire detection, object classification, neural networks, image processing

Situation-oriented databases: verifying electronic signatures of heterogeneous documents in a RESTful web service

2022. T.10. № 4. id 1281

Gusarenko A.S.

DOI: 10.26102/2310-6018/2022.39.4.019

When focusing on modern conditions in the field of processing heterogeneous data based on a situation-oriented approach, the task of using information systems with implemented cryptographic technologies during operation arises. One of the examples of such implementation are services and microservices available via the Internet. They provide opportunities to employ their capabilities to verify the authenticity of document enhanced digital signature by means of the published API. Situation-oriented databases (SODB) do not have their own certification authority and encryption-related functionality, but there are opportunities to work with RESTful services by establishing a network connection, thus, there is a research interest in model-oriented processing of heterogeneous documents in cryptographic services and obtaining results from it. To use cryptographic web services in model states, it will be necessary to develop and modify the hierarchical situational model of the SODB in order to enhance it with the ability to work with such services, where authentication of authorization tokens and operating several entry points at the same time are required. The model should also be structured by using specialized elements and methods. The involvement of such services can solve the problem of checking heterogeneous documents: whether they were signed with an enhanced qualified electronic digital signature, the result will be a verification report, the so-called protocol, which is then saved in the database. Such a research objective has not previously been considered from a scientific and technical point of view as part of the SODB project. At the moment, there are opportunities to create tools and methods of the model to solve this problem; the current course design information system based on SODB also exists. By developing the proposed SODB tools, it becomes possible to create applications with the capability to verify heterogeneous documents in cryptographic web services and at the same time avoid laboriousness when creating such applications.

Keywords: situation-oriented database, built-in dynamic model, heterogeneous data sources, JSON, electronic digital signature, verification, RESTful-services

Automation of growing crops in a stationary compact greenhouse complex with a controlled microclimate based on a hydroponic system

2023. T.11. № 1. id 1280

Levonevskiy D.K. Ryabinov A.V. Zhukova N.A. Kovalevsky V.E.

DOI: 10.26102/2310-6018/2023.40.1.029

Automation processes are currently being implemented in agriculture. Solutions in the field of agricultural automation and smart agriculture can reduce time expenditure and cost of crop production and lessen the impact of the human factor, i.e. mistakes that can lead to the death of crops and cause significant damage to the enterprise. This article deals with the issue of automation and modeling of technological processes of growing crops in stationary compact greenhouse complexes with a controlled microclimate based on a hydroponic system. A diagram and a model of the behavior of such complex is presented in the article. The complex helps to perform cyclic cultivation by periodic irrigation with a nutrient solution cleaned with a biofilter. To model the behavior of a mini-greenhouse, UML state diagrams were used. The problem of evaluating the performance of such modules and recording disruptions of cultivation process drawing on the collected data was considered. Machine learning methods were employed to estimate and predict climatic parameters in the greenhouse. The application of these methods allows performing proactive control of technological processes in the greenhouse, ensure strict adherence to production regulations and rational use of resources. Further research involves creating a method for proactive control of compliance with technological processes based on the formal models of these processes.

Keywords: smart agriculture, cyber-physical systems, smart greenhouse, behavior modeling, automated process control systems

Modeling and visualization of thermohydraulic processes under the influence of external dynamic forces

2023. T.11. № 1. id 1275

Sataev A.A. Andreev V.V.

DOI: 10.26102/2310-6018/2023.40.1.004

The article deals with the relevant issue related to accounting for the impact of external dynamic forces on thermal-hydraulic processes. These include processes of natural circulation, mixing of the coolant in the equipment of nuclear power plants, steam separation processes, operating modes of heating systems for high-viscosity media, operation of absorption refrigeration devices installed on small and large sea vessels. The principal approach to researching this problem is the experimental method which makes it possible to comprehensively consider these processes on small-scale models. For this, an experimental stand of an original design was developed. The parameters obtained during the operation were visualized and converted into graphic images, which were analyzed using the open-source computer vision library OpenCV. A new method for visualization of mixing processes of non-isothermal flows is proposed, the implementation of which resulted in the integral and local characteristics of this process. It is evident from the findings that the modes of periodic rolling and static roll have a significant effect on the mixing processes of non-isothermal coolant flows. After analyzing the obtained graphic images, areas of uneven mixing were identified, which are in direct correlation with the conditions of external dynamic influences. The techniques tested in the study of mixing processes of non-isothermal flows can be used in other applications to solve similar problems.

Keywords: visualization, thermohydraulic processes, external dynamic forces, rolling, experimental modeling, nuclear power plant, openCV, mixing

Algorithmization of the multivariate structuring process in digitalized organizational systems

2023. T.11. № 1. id 1274

Ryndin N.A.

DOI: 10.26102/2310-6018/2023.40.1.005

The relevance of the study is due to the problem of improving management efficiency in organizational systems that employ a digital environment for storing and processing information about the parameters and characteristics of such systems. The article deals with the issues of algorithmization of multivariate structuring process in digitalized organizational systems of two types: multi-object and autonomous. The main characteristics of the multivariant structuring process are given; optimization models are formulated for solving the problems of the multivariant structuring main stages. It is shown that the performance indicators of the organizational system depend on the selected implementations of the components of the developing digital environment. At the same time, the presence of extremal and boundary requirements leads to the problems of single-objective or multi-objective optimization with restrictions. Optimization models for the distribution of resource support for maintaining the functionality and development of the components of the digital environment are being built. The main algorithmic procedures for searching the optimal solutions are formulated and an assessment of the variant compatibility of the environment structures is given. The implementation sequence of the multivariant structuring stages is given in the form of a block diagram of the interaction of these stages. The specifications of using the apparatus of multivariate structuring to optimize the characteristics of digitalized systems are demonstrated through the example of the organizational system of an agro-industrial enterprise. Algorithmization of the multivariate structuring process makes it possible to implement this apparatus in the information management system and ensure the fulfillment of the specified requirements for the system.

Keywords: organizational systems, digital environment, management, multivariate structuring, optimization, agricultural enterprises

Intelligent support for detecting information security incidents

2023. T.11. № 1. id 1271

Tokarev V.L. Sychugov A.A.

DOI: 10.26102/2310-6018/2023.40.1.006

The relevance of the study is due to the need to automate the processes of detecting and identifying information security incidents for the timely launch of response processes, which, in turn, will reduce the impact of both intentional and accidental information security incidents on information security in automated systems for various purposes. The suggested solutions are based on artificial intelligence methods, and as a built-in means of intellectual support for the detection of information security incidents, a decision support system is employed. The article proposes models, mathematical dependencies and methods for solving problems of automatic detection, identification of information security incidents as well as their localization, for which, among other things, fuzzy set theory is used. Possible strategies for localizing information security incidents are considered. Procedures for responding to information security incidents as well as their elimination are formulated, which, in turn, allows building intelligent support systems for solving the problem of prompt detection of information security incidents. Examples of events are given. The materials of the article are of practical value for building systems of preventive information protection, which is currently one of the promising areas of theory and practice of ensuring information protection

Keywords: information security incidents, preventive information protection, artificial intelligence systems, mathematical logic, automated systems

Modeling the conditions of regular сompliance with recommendations for cardiological patients at the outpatient stage using decision trees

2022. T.10. № 4. id 1270

Gafanovich E.Y. Sokolov I.M. Konobeeva E.V. Kashirina I.L. Firyulina M.A.

DOI: 10.26102/2310-6018/2022.39.4.011

The paper is concerned with the use of decision trees with a view to designing the model of regular сompliance with recommendations for cardiological patients. Machine learning of feature significance in a tree-like structure was conducted based on the statistical sampling gathered after examining 69 patients that had received treatment in a cardiological department and who had been being observed for 6 months after discharge. To build a decision tree, input data was employed: age, gender, social status, reasons for hospitalization, description of previous illnesses, treatment strategy, reasons for missed doses, adherence to recommendations. As output data, regular / irregular compliance with the recommendations during 6 months after discharge was used. The decision tree that reflects the conditions influencing the compliance with medication intake after discharge has been built. Analysis of factor scaling influence at branching points will provide the means for defining the regularity of compliance with the prescribed medical treatment in the form of their conjunctions at each branch of the decision tree. Significance of the features associated with the factors of influence was evaluated according to Gini index value. This intelligent technology identified the factors that determine the outcome: providing patients with clear recommendations, missed doses due to forgetfulness, patient’s general state, social status, changes in therapy, patients’ age, duration of arterial hypertension.

Keywords: modeling, classification, decision tree, gini index, regular medication intake

Determination of the stabilization rate of the solution to one initial problem for the heat equation

2022. T.10. № 4. id 1268

Ryabenko A.S. Tran D.

DOI: 10.26102/2310-6018/2022.39.4.014

Differential equations are intensively used as models for a wide range of natural science problems. For most differential equations, it is not possible to obtain solutions in quadratures expressed in terms of elementary or special functions, and if it is possible, then the representations of these solutions are often very cumbersome, which makes their practical application difficult. Therefore, the question of finding simple formulas that describe with a sufficient degree of accuracy the qualitative behavior of solutions to differential equations on a certain interval of variation of the independent variable is very acute. Asymptotic methods are employed to determine the qualitative behavior of solutions to differential equations on a certain interval of change of the independent variable. Asymptotic methods are more preferable than numerical methods when one needs to know the behavior of the solution to a differential equation considered on an unbounded interval. This is explained by the fact that the discrepancy of the solution to a differential equation (the modulus of the difference between the true solution and the numerical solution) is usually estimated from above through a value proportional to the length of the interval on which the numerical method is applied. The paper considers the one-dimensional Cauchy problem for an inhomogeneous heat equation with a homogeneous initial condition. Using an explicit representation of the solution to the Cauchy problem, an exact uniform estimate and an exact pointwise estimate of the stabilization rate of the solution to the Cauchy problem to zero for a long time were constructed.

Keywords: heat distribution, solution stabilization, time behavior, time asymptotics, heat equation, time estimate, asymptotics at infinity

Hybrid intrusion detection system with the use of a classifiers committee

2022. T.10. № 4. id 1267

Vasilyev V.I. Vulfin A.M. Gvozdev V.E. Shamsutdinov R.R.

DOI: 10.26102/2310-6018/2022.39.4.020

The issues of detecting network attacks to Industrial Internet of Things (IIoT) systems are analyzed. Existing approaches for detecting such attacks based on the use of artificial intelligence methods are considered. The high interest to integration of machine learning and artificial intelligence methods as a part of hybrid systems is emphasized. Such integration makes it possible to compensate the shortcomings of some algorithms due to the advantages of others. The goal of this research is to improve the efficiency of network attacks detection. The paper proposes the implementation of a multi-level hybrid attack detection system on the basis of combining several classifiers in the committee including the artificial immune system, the multilayer perceptron, and the random forest algorithm. The choice of these classifiers is due to their high classification efficiency and the ability of artificial immune system to detect unknown network attacks. The decision is made on the basis of the conclusion of each expert (classifiers) with the use of voting mechanism. Such approach provides more accurate result in accordance with the Condorcet's jury theorem. To carry out computational experiments for assessing the effectiveness of the proposed system, the NSL-KDD network traffic data set was employed. The results of experiments carried out demonstrate the high efficiency of the proposed hybrid attack detection system based on use of classifiers committee.

Keywords: information security, industrial Internet of Things, intrusion detection system, network attack, NSL-KDD dataset

System analysis of a model for obtaining performance characteristics of an integrated security system

2023. T.11. № 1. id 1266

Lubentsov A.V.

DOI: 10.26102/2310-6018/2023.40.1.030

The study regards the system analysis of the issues related to the synthesis of complex security systems. The analysis of the approaches to evaluating the efficiency of security systems is presented. Main efficiency criteria and the parameters of complex system operation are discussed; their system analysis is proposed. The result of the performance specification analysis and the analysis of security system efficiency objectives are presented. The key objective functions of complex security systems are defined. The concept of technical and economic efficiency is substantiated. The functions are evaluated by the predefined parameters. System analysis of the notion of ‘efficiency’ in regulation documents is given. An argument for the optimality of using analytic hierarchy process is presented. It has been proved that analytic hierarchy process tends to be subjective, and its reduction is suggested. The original method consists of two parts: the first one is subjective (selection of the criteria and the solutions along with ranking); the second one is objective (calculation of impact parameters and matrix elements) which is not affected by the decisions of a human being. When implementing the first part, the results depend heavily on the decision-maker. The modified (cascaded) analytic hierarchy process is proposed, the calculation model is described. In this instance, three groups of experts are developed: independent experts, facility managers and users (specialists who operate the facility after its implementation). They jointly select the list of solutions (modification) and the list of criteria, but the ranking is carried out by each group individually and the matrices are built by each group at their own discretion. The rationale for the preferred use of the cascaded hierarchy analysis process is provided. The generalizations concerning the characteristics being considered are given.

Keywords: security, risk, efficiency characteristics, hierarchy analysis process, objective function of a security system

On the approach to ensuring the property transitivity in web ontologies

2022. T.10. № 4. id 1265

Shulga T.E. Sytnik A.A.

DOI: 10.26102/2310-6018/2022.39.4.009

The article focuses on the issues of knowledge representation in the form of web ontologies. The relevance of the study is due to the two factors. On the one hand, a large number of OWL ontologies and RDF datasets have been created as part of semantic web concept development in recent years. On the other hand, the OWL language has a number of limitations that do not always allow adequate representation of domain knowledge. For example, SPARQL queries that use the transitive properties of the OWL language can create some kind of "loops" and return incorrect information. This article demonstrates that in some cases it is preferable not to use the transitivity of properties in the ontology. The algorithm for traversing related entities, which enables solving the problem of “loops”, is proposed. To illustrate the issue, we use "Higher educational programs of Russian Federation" web application. This application is developed on the basis of the RDF dataset which contains information about scientific specialties, bachelor’s, master’s and postgraduate programs obtained from publicly available official documents of the Ministry of Science and Higher Education of the Russian Federation since 2001. To set up a correspondence between the fields of studies that have existed over the years in the Russian Federation, equalsTo transitive property is employed in the RDF dataset. Although the developed algorithm is formulated and used in terms of a specific domain to solve the problem of a particular application, it is quite universal and can be applied by web developers to solve the problem of transitivity in RDF datasets of other domains.

Keywords: transitivity of OWL properties, web ontology, OWL ontology, RDF dataset, semantic Web, recursive algorithm, linked fields of study

Identification of technological complementarity of enterprises based on the analysis of the patent database

2022. T.10. № 4. id 1264

Korobkin D.M. Fomenkov S.A. Kolesnikov S. Bezruchenko A.Y.

DOI: 10.26102/2310-6018/2022.39.4.010

Technological complementarity plays an increasingly important role in making strategic decisions regarding the choice of partners to work with as well as for expanding the diversity of innovation activities through the creation of alliances or mergers. Modern quantitative measurements of technology complementarity are largely based on research founded on patent classification codes. However, this approach ignores specific technologies in a particular field and, therefore, the results obtained are only general pointers. It is proposed to develop an approach to the quantitative measurement of the complementarity of enterprise technologies in reliance on statistical machine analysis of the patent array. The aim of the study is to develop a technology for clustering USPTO patent documents and identifying technological complementarity of enterprises based on the comparison of cluster information. The theoretical value lies in the following: the developed algorithms for patent parsing; clustering of the patent array based on the hLDA method; formation of "Enterprises – Clusters (Topics)" matrix; visualization of enterprise connections in a clustered patent space. The practical significance of the research lies in the developed software for identifying technological complementarity of enterprises, the effectiveness of which has been tested on a number of test examples.

Keywords: patent, USPTO, technological сomplementarity, clustering, hLDA

Solving system-problems of WEB application development by means of the MODx-concept

2023. T.11. № 1. id 1257

Gutovskii D.I. Dobrynin V.N. Minzov A.S. Podgorny S.A.

DOI: 10.26102/2310-6018/2023.40.1.013

Current CMS, regardless of their complexity and orientation, can be divided into two groups: one follows the MODx-concept, the other does not. The article describes the problems of building and development of WEB applications that are typical for standard CMS. The problems regarded in this article are relevant for all participants of WEB development. The problem of drastic changes to the interface is that it has to be constantly edited when the functionality is modified even if it is not related to this part of interface. This changing requires significant costs on the part of WEB developers and users. The problem of API continuity absence in standard systems is associated with the absence of atomic entity principle. The absence of API continuity leads to significant costs for CMS developing. The problem of connection between the different applications is due to the strong relationship between CMS components, which, in turn, does not make it possible to flexibly adjust the system to generate the content with the specific properties which are needed for joint applications. The problem of WEB application module conflicts is connected with unsystematic dependencies between CMS components. The inability to redefine the client part and the inflexible file hierarchy of standard CMS play an essential role in the problem of WEB application security. The scalability problem is primarily associated with the nonindependence of addresses on the site filesystem for standard CMS. The authors provide justifications for the application of the MODx-concept by a team of developers at the stages of WEB application design and operation to solve these problems.

Keywords: CMS, MODx, template, layout, setup, MODx-concept, site, content, WEB-site, WEB