开放存取 开放存取  受限制的访问 ##reader.subscriptionAccessGranted##  受限制的访问 订阅存取

卷 9, 编号 2 (2022)

封面

完整期次

开放存取 开放存取
受限制的访问 ##reader.subscriptionAccessGranted##
受限制的访问 订阅存取

Articles

Finding the Optimal Machine Learning Model for Flood Prediction on the Amur River

Aleksandrov N., Ermakov D., Aziz N., Kazenkov O.

摘要

Water-related natural disasters are among the most devastating and are responsible for 72% of the total economic damage caused by natural disasters, and due to climate change, their number will only increase. In Russia, river floods are the main such disaster. The purpose of this research work is to determine the best machine learning method for predicting floods on the Amur River, where they cause significant damage to the population and economy of the region. The study was undertaken with the aim of improving flood forecasting methods for the subsequent use of the study results in solving management problems in response to floods. The study considers the practical aspects of implementing a forecasting system, so the 3 most popular machine learning methods were studied: linear regression, neural network and gradient boosting, because these methods have a developed ecosystem of auxiliary solutions and are widely known in the professional community. The research methodology was aimed at achieving maximum comparability of results. Among the algorithms tested, gradient boosting over trees in the implementation of Catboost demonstrated the best quality. The results of the study are also applicable to other rivers, for which the amount of data is comparable to that of the Amur.
Computational nanotechnology. 2022;9(2):11-20
pages 11-20 views

Development and Research of Distributed Control Algorithms for Swarm Intelligence Systems

Ershov N.

摘要

The subject of this paper is the development and research of distributed algorithms for organizing collective behavior in swarm robotic systems in order to solve various applied problems with these systems. Using the example of solving the problem of collective cleaning of a given area, several swarm algorithms based on classical swarm models are constructed and studied: random walk model, Reynolds model, bacterial search algorithm, stochastic gradient method. The results of numerical experiments comparing the efficiency of the proposed methods are presented
Computational nanotechnology. 2022;9(2):21-34
pages 21-34 views

Elements of artificial intelligence in solving problems of text analysis

Katermina T., Tagirov K., Tagirov T.

摘要

Due to the ever-increasing volume of textual information on the Internet and the need to navigate it, the automation of the text analysis process has become urgent. The analysis of the subject area has shown a great demand for the identification of textual information coloring and the application of works on this problem in practice. This paper deals with the development of a neural network model for analyzing commentary tone. Recurrent neural network models with long short-term memory modules (LSTM) are used for the purpose. We have developed an information system that determines the tone of comments on posts in the communities of the social network “VKontakte”. As a result of training of the artificial neural network, the model showed good accuracy in determining the tone of the text. The information system was implemented in the marketing department of the Nizhnevartovsk Construction College Budget Institution.
Computational nanotechnology. 2022;9(2):35-44
pages 35-44 views

The Modeling of Processes of Design of Information Protection Systems in Critical Information Infrastructures

Prokushev Y., Ponomarenko S., Shishov N.

摘要

The relevance and necessity of implementations of measures of information security in CII (critical information infrastructures) is explained by several reasons. Firstly, these are the requirements of Russian legislation. Note that some CII objects, because of the nature of the information being processed, can also be attributed to GIS (state information systems) or ISPDn (personal data information systems). There are also requirements for information security measures [4; 5] for systems of this type, which largely correlate with the measures described for CII objects in [6]. Secondly, it is the objective presence of threats of various kinds that require neutralization and exist in almost all modern information systems. In order to ensure information security, the protective mechanisms used at CII facilities should take into account such factors as a significant amount of processed information, the need to ensure correct, stable and trouble-free operation, the multi-user nature of access to information resources, and ensuring the security of managed equipment. The fact that failures and errors in the operation of information systems in a number of CII of industrial enterprises can entail not only economic damage or negative social consequences, but also create a direct threat to the lives of a significant number of people, that live not so far to the place of work of these objects [11]. Modeling of the work performed at the design stage of information security systems of CII facilities is due to the complexity of this process. In present, ensuring the information security of CII facilities is one of the most important tasks currently being solved at the state level. These circumstances determine the relevance of writing the article. The purpose of writing this work is the developing of the set of models describing the features of organizational, legal and technical processes that arise at the stages of formation of requirements for ensuring information security of CII facilities. The normative legal acts of the FSTEC of Russia, which are in the public domain, are used as the methodological basis for writing the work. The methodology of functional graphical modeling IDEF0 was used to describe the ongoing work performed at the design stage of the information security system of the CII. The result of the research presented in this paper is a set of graphical and symbolic models describing the processes performed at the design stage of the information security system in critical information infrastructures.
Computational nanotechnology. 2022;9(2):45-55
pages 45-55 views

Prospects for the Application of Additive Technologies in Russia from an Industry Perspective (on the Example of the Aviation Industry)

Naim O., Ermakov D., Melnikov V., Kazenkov O.

摘要

The article devoted to the problem of introducing additive technologies into the national economy of Russia from the perspective of their adaptation to modern market conditions, when the Russian Federation is developing under international economic sanctions. The authors conclude, using the example of the Russian aviation industry, that the spread of additive technologies within the framework of Russian industrial production is difficult due to low elasticity of supply and demand, low elastic supply is especially painful for the innovative development of the industry, this conclusion is made on the basis of a linear market model. However, there are prospects for additive technologies in the aviation industry, if the pricing policy will be changed in the aspect of revising prices for civil aviation products in the direction of their increase, this is quite possible in a situation of transformation of the entire industry under the pressure of international sanctions. The authors also believe that in the future, the development of small aircraft will create conditions for additive technologies to be more in demand, but it is still difficult to make certain forecasts on this score. An important theoretical result of this scientific article is the construction of a model of market influence on the effectiveness of the introduction of additive technologies, this is useful for further research of economic issues related to additive technologies, as well as issues related to the introduction of innovations in a market economy in general.
Computational nanotechnology. 2022;9(2):56-66
pages 56-66 views

Capabilities of Polyethylene-ceramic Composite in Comparison with Polyethylene Film in Real Operation Conditions

Rakhimov R., Yermakov V., Rakhimov M., Mukhtorov D.

摘要

This article presents the results of full-scale tests of a polyethylene-ceramic composite in real conditions, at an altitude of 1100 meters above sea level. This is due to the fact that at this height the level of UV, which destroys polyethylene, is significantly higher than at sea level. In parallel, the results of testing a conventional polyethylene film were also carried out, for a comparative assessment of effectiveness.
Computational nanotechnology. 2022;9(2):67-72
pages 67-72 views

Features of the Electrical Properties of Heterojunctions n-GaAs-p-(GaAs)1 - x - у(Ge2)x(ZnSe)y

Zaynabidinov S., Boboev A., Abdurahimov D.

摘要

The optimal technological conditions for growing multicomponent epitaxial films of solid solutions (GaAs)1 - x - y(Ge2)x(ZnSe)y with specified physical properties by liquid-phase epitaxy have been determined. It has been established that the above conditions for growing thin films from a tin solution-melt at temperature intervals of 730-630, 650-550 °С with a substrate cooling rate of 1 deg/min are the most optimal. In this case, the films had a thickness of 10 μm and p-type conductivity. For ohmic contacts to such semiconductor solid solutions, Sn, Au, In, (In-Ga) and (Ge-Ag) alloys were used. It was determined that the mobility of current carriers depends on the composition, the structural perfection of the epitaxial layers and the ionization energy of the atoms of the constituent components have values of 0.19, 0.07, 0.029 eV. It has been established that in heterostructures of the n-GaAs-p-(GaAs)1 - x - y(Ge2)x(ZnSe)y type, obtained at Т = 7500 °С, the current transmission is determined by tunneling-recombination, and in the samples obtained at Т = 7300 °С, by currents limited volume charges. It was also determined that a region with a higher resistivity is formed at the heterointerface, the thickness of which, depending on the growth conditions of thin films, is from 0.2 to 0.5 μm.
Computational nanotechnology. 2022;9(2):73-79
pages 73-79 views

Technologies for Increasing Production Efficiency in Industry

Kudryavtseva S., Khaliulin R., Kakadzhanov V.

摘要

The purpose of the research. The purpose of the article is to study the long-term dynamics of changes in the main indicators of production and financial efficiency of industry in the innovation system of the Russian economy and to identify complex factors in the development of the industrial complex. Achieving the goal becomes possible thanks to the solution of scientific problems: assessing the production efficiency of industry in the Russian economy; presentation of an assessment of the financial efficiency of industry in the Russian economy; construction of combined economic and mathematical models of production and financial efficiency of the industry. Results. It has been determined that in the Russian economy there is a trend towards an increase in the production efficiency of industry, which is characterized by such indicators as the level of innovative activity, the share of high-tech products in GDP, the share of R&D costs in GDP; the exception was the labor productivity index, which showed unstable dynamics of changes in 2010-2021 and a decrease relative to the base year of comparison - 2010. In the long term, indicators of the financial efficiency of industry showed an increase, among them: the share of investments in fixed assets in GDP, the profitability of production assets and industrial products sold. The greatest volatility in terms of production and financial efficiency of the industry was characteristic of the profitability of production assets and sold industrial products, as well as for the index of changes in capital-labor ratio. A positive relationship was found between the profitability of industrial goods sold and the return on assets, as well as a negative relationship between the labor productivity index, the share of R&D costs and the share of the high-tech sector in the country’s GDP, which indirectly may indicate an increase in gross value added in the Russian economy, mainly due to the intensive use of physical capital. It is proposed to consider the level of manufacturability and science intensity of production, financial activity, innovation and physical capital as complex factors for increasing the production and financial efficiency of the industry. The conclusions and results obtained in the article can be considered as a basis for improving methodological developments for assessing the production and financial efficiency of multi-level economic systems, which is of great scientific and practical importance for the development of an innovative economy. The analytical material presented in the article and the proposed tools are logical from the standpoint of system analysis in the management of production processes, financial, economic and innovative activities in general.
Computational nanotechnology. 2022;9(2):80-91
pages 80-91 views

Application of Artificial Intelligence Methods to the Task of Diagnosing Respiratory Diseases

Katermina T., Sibagatulin A.

摘要

The article considers the problem of diagnostics of respiratory diseases. The authors have chosen as a possible direction of solution of the given problem neuronetwork convolution model, developed and showed its possible architecture. The article also shows what steps of data pre-processing must be produced for the best result of model training. The authors suggest that the diagnosis of respiratory diseases should be carried out by analyzing the characteristics of audio recordings of breathing. Such audio recordings are already being produced, making it possible for the network to use a data set that is freely available on the Internet. The paper contains a list of characteristics of audio recordings of breathing that can be used to analyze and make a preliminary diagnosis. An important part of the work is the analysis of existing modern scientific methods that allow somehow simplify the work of medical personnel and help to preserve the health of the patient. The given results of learning the neural network model show which diseases can be diagnosed with great confidence automatically, and which are more difficult to determine and require additional research.
Computational nanotechnology. 2022;9(2):92-103
pages 92-103 views
##common.cookie##