Journal archive

Currently, a new type of information security threat is spreading – hidden mining, which uses the computing resources of users through browsers. Malicious software based on WebAssembly files unauthorizedly uses the computing resources of users of computer systems. The existing methods for detecting “hidden miners” in the browser environment are based on: dynamic analysis algorithms, however, they have a number of limitations, for example, it is required that malicious software for hidden mining work for a certain period of time, they are characterized by a large number of false positives; algorithms of browser extensions that use blacklists to prevent unauthorized access to the user’s browser environment, however, attackers often change their domain names, etc. The relevance of using special protection tools against browser-based cryptominers is beyond doubt. The purpose of this study is to increase the level of security of the browser environment of users of computer systems. Achieving this goal is possible by solving the main task - the timely automated detection of “hidden miners” in the browser environment and the prevention of unauthorized mining. The article describes software that does not depend on the browser or operating system used, is resistant to attempts to circumvent protection by intruders, will allow users to reliably recognize “hidden miners”, and increase the level of information security of a computer system. The software is based on classification algorithms implemented on the basis of a convolutional neural network. The results of the study and experimental data showed that as a result of testing the software, the recognition accuracy of “hidden miners” in the browser environment is 91.37%.

In the last decade, there has been an active digitalization of industrial production based on rapidly developing information technologies, including artificial intelligence technologies. This is largely due to the development of deep learning methods and their applications in computer vision. Since the mid 2010s convolutional neural networks demonstrate exceptional efficiency in solving problems such as the detection, classification and segmentation of various objects. As a result, computer vision methods are beginning to be actively used in the problems of quality control of raw materials and finished products. All this applies to the mining industry. However, in the Russian scientific literature there are practically no systematic reviews of computer vision applications in this area. The present study aims to fill this gap. The paper provides a systematic review of the history of development and the current state of the methods and technologies of machine vision used in the mining industry for the analysis of solid materials, demonstrates the latest achievements in this area and examples of their application in the mining industry. The authors have analyzed 29 research papers in the field of application of computer vision in the mining industry and classified the stages of technology development from the mid-1980s, when computer vision was used without the use of machine learning, and ending with modern research based on the use of deep convolutional neural networks for solving problems of classification and segmentation. The effectiveness of the methods used is compared, their advantages and disadvantages are discussed, and forecasts are made for the development of computer vision methods in the mining industry in the near future. Examples are given showing that the use of convolutional neural networks made it possible to move to a qualitatively higher level of quality in solving problems of classification and segmentation as applied to the analysis of output volume, particle size distribution, including flakiness, angularity and roughness, dust and clay content, bulk density and emptiness, etc.

The results of studies on the development of the structure of an intelligent model for managing the risks of violation of the characteristics of electromechanical devices in a multi-stage system for processing ore raw materials are presented. Such devices are involved in all cycles of the technological process, so the assessment of this risk for them is an urgent task. A method for assessing such risks is proposed, which is based on the assessment of the useful life of equipment, performed on the basis of the prediction of characteristics by a deep recurrent neural network, with further generalization of the results of such an assessment in a fuzzy inference block. Recurrent neural networks with long short-term memory were used, which are one of the most powerful tools for solving time series regression problems, including predicting their values for long intervals. The use of deep neural networks to predict the characteristics of electromechanical devices made it possible to obtain a high prediction accuracy, which made it possible to apply a relatively less accurate recurrent least squares method for the iterative process of estimating the useful life of equipment. This approach made it possible to build a computational evaluation process with its constant refinement as new results of measurements of the characteristics of electromechanical devices become available. The results of a model experiment with a software implementation of the proposed method, performed in the MatLab 2021a environment, are presented, which showed the consistency of the program modules and obtaining a risk assessment result that is consistent with the expected dynamics of its change.

Currently, at the global and regional (national) levels, the expert community, as well as statesmen, have prioritized the task of practical implementation of the Sustainable Development Goals (characterizing the dynamics of a development of various parameters of socio-ecological and economic systems). Achieving these goals requires serious analytical work based on a deep and comprehensive analysis of a processes taking place in various spheres, as well as the formation of an appropriate information platform, including a set of databases that adequately describe changes taking place in various spheres of state activity. However, today, in Russian practice, this tool is practically absent, which significantly complicates the qualitative and quantitative analysis, assessment and forecasting of the processes of adaptation of Russian regions (including the population living in them) to consequences of global climate change. The purpose of this study is to form a database of indicators characterizing process of adaptation of socio-ecological and economic systems of a northern regions of Western Siberia (The Khanty-Mansiysk Autonomous Okrug and Yamalo-Nenets Autonomous Okrug) to global climate change. The projected database should become the basis for creating an open information resource for a wide range of users when they solve analytical and predictive tasks related to a socio-economic assessment of an impact of global climate warming on permafrost. To achieve the objectives of the study, a set of methods was used: theoretical generalization and comparison, formalization, algorithmization, structuring and grouping, economic and statistical methods (including correlation and regression analysis), cartographic method, graphical modeling method. As a result, we have formed a database representing a single, periodically updated repository containing spatio-temporal data sets characterizing processes and phenomena, on the one hand, socio-ecological and economic systems, on the other – climate change. Further work with the database assumes, on the basis of available quantitative data and methods of mathematical statistics, the identification of elements of the ecological, socio-economic systems of the KhMAO and YaNAO vulnerable to global climate change, as well as forecasting the dynamics of their (systems) transformation.

One of the key factors in the country’s GDP growth is reproducible capital, which lays the foundation for the production of products, works and services. Accordingly, the study of the state, structure and dynamics of the dominant component, fixed assets, is one of the priority tasks of statistics and econometrics. This implies the purpose of the study, which is to assess the predictive capabilities of econometric models. To achieve this goal, a pool of mathematical-statistical and econometric methods was used, in particular tabular and graphic, descriptive statistics, correlation-regression, adaptive modeling. The main results include: analysis of the structure of investments did not find new or hidden patterns, so investments are directed to the modernization or renewal of capital-intensive areas – these are buildings, structures and land (about 40% of the total investment), the main industries are industry and transport; visual analysis of the dynamics of the temporary series of investments in fixed assets showed the presence of a long-term, seasonal and situational component; the construction of 6 econometric models reflecting the complex dynamics of the macro indicator in question made it possible to distinguish two adaptive models belonging to the group; thus, the best forecast opportunities for complex dynamics of investments in Russian fixed assets are observed in the three-parameter exponential smoothing model and SARIMA (1,0,0)(1,1,0) [4]. The results obtained in the course of the study will be useful for scientists involved in modeling and predicting complex-structured time series.

The article deals with an urgent problem related to organization of control of a team of intelligent mobile robots and their interaction with each other for the most effective achievement of the goal. The research is aimed at development of interrelated models of intelligent planning of robot behavior, which is based on a market approach resting on a new risk equilibrium model. The substantial and formal formulations of the task of planning of autonomous mobile robots activities are proposed. The author’s model and a set of new simulation models for calculation of the overstatement, understatement costs, as well as their risks are developed. Various calculation algorithms are proposed for various variants of robot interaction: control under conditions of a restricted limit of the most scarce resource (for example, battery energy); interaction between robots using information products (messages); robot control from the center; purchase and sale of the information product; making a decision on subordination and support of communication between robots, etc. Examples of description of robot behavior options (speed of movement, equipment with photos, videos, sampling tools, energy limit), classification of events (fire, traffic accident, violation of law and order, emergency situations, suspicious object) are offered. Examples of calculation procedures are given: robot behavior options, if it is possible to maintain speed depending on energy consumption; adjustment factors to take into account increase of the probability to detect an event due to improvement of the photo quality (wide format, high definition, frame frequency).

In the article, using MatLab dynamic simulation modeling, a study was made of the excitation systems of powerful synchronous generators of stationary diesel generator sets, which are the main sources of emergency power supply for nuclear power plants. The optimal structural complexity mathematical model of a synchronous machine in relative units and orthogonal synchronous coordinate system is used. A comprehensive simulation of diesel generator sets was carried out with the reproduction of both the dynamics of the automatic control system for excitation of a synchronous generator and the diesel engine control system. The simulation takes into account the features of starting a diesel generator to accelerate a synchronous machine, its initial excitation from a battery. Particular emphasis is placed on the study of self-excitation modes through a transformer connected to the stator circuit of the generator and a thyristor rectifier with an excitation winding as a load, as well as parallel operation with the power system. As a result, the processes of starting a diesel generator set in idle mode, effective self-excitation, autonomous operation of the generator at idle, and applying a load to the generator up to the values of permissible overload were simulated. The work of all channels of the control system is shown, including the signals of the regulators of the automatic control system and mechanical variables that are inaccessible in practice. The adequacy of the developed model is proved by comparison with a real physical experiment when testing a diesel generator at a nuclear power plant. The possibility of using the model developed in MatLab as a virtual test site for testing a diesel generator set and a computer simulator for specialized engineering personnel of a nuclear power plant is demonstrated.

An approach to assessing and forecasting indicators of the quality of life of the population in the region based on the concept of system dynamics is presented. A mathematical model has been developed, which is a system of non-linear, non- homogeneous, different-tempo differential equations, which include system variables and external factors. A digraph of causal relationships between system variables and external factors is constructed. As system variables, the model uses indicators of socio-economic development of the region: gross regional product, life expectancy at birth, population size, per capita per capita income, registered unemployment rate, birth rate, share of the population with income below the subsistence level, the weight of organizations using personal computers. The choice of external factors and functional dependencies in the developed model is substantiated. The adequacy of the developed mathematical model was checked using retrospective data and the calculation of the relative error. The interface of the author’s software application “Prognoz_2”, developed in the GUIDE MatLab environment, used to conduct computational experiments, is presented. An example of the practical implementation of the developed approach to assessing the quality of life in the Saratov and Samara regions is considered. The results of the computational experiment on the analysis and prediction of the quality of life on the time interval [2022;2026] years within the framework of the implementation of three scenarios are shown. The values of system variables in 2021 normalized relative to 2010 were used as initial conditions for the calculations. The developed software can be used to form scenarios for the socio-economic development of the region. Models and algorithms can be used as part of an information-advising system for making decisions at various levels of management.