ISSN 0236-235X (P)
ISSN 2311-2735 (E)


Next issue

Publication date:
16 March 2021

Journal articles №2 2016

11. Software of information technology for solving conflict situations in multi-agent environment [№2 за 2016 год]
Authors: Semenov N.A. ( - Tver State Technical University, Ph.D; Mutovkina N.Yu. ( - Tver State Technical University, Ph.D; Klyushin A.Yu. ( - Tver State Technical University, Ph.D;
Abstract: The agents’ behavior in a dynamically changing multi-agent environment (ME) depends on both external factors and personal characteristics, agents’ qualities. The external factors include interests, preferences, opinions and beliefs of the environment, “fashion”, the possibility of realization of their own desires and needs, etc. The main personal characteristic of the agent is its psycho-behavioral type, which is influenced by external factors. The agent can provoke a conflict in ME under an adverse influence of external factors along with the negative type. It is possible to control a psycho-behavioral agent using a certain combination of influences. This is a unique combination for each type of agent. It depends on the potential strategic behavior of an agent in interaction with other agents. The reduction of deviant agent to a compromise type allows resolving a conflict in ME. The article describes the main ways of avoiding a conflict, a mathematical model of matching representations of the agents and the algorithm for solving a conflict in the ME. The presented information technology allows predicting the agent’s behavioral strategy in the system in conflict and developing a control scheme of the type of the agent. The proposed technology is based on a mathematical apparatus of the game theory, fuzzy logic, the theory of active systems, the mathematical theory of values, interests and judgments. This technology has become the basis for development of an expert system for ME conflict resolution. The best way of developing such a system is the use of so -called “shells” and special software systems, e.g., EXSYS or G2.
Keywords: artificial intelligence, behavioral strategy, expert system, multi-agent environment, conflict, information technology
Visitors: 6296

12. The analysis of activity and development trends of malicious programs “file locker-encoder” type [№2 за 2016 год]
Authors: Drobotun E.B. ( - Military Academy of the Aerospace Defense (Doctoral Student), Ph.D;
Abstract: All companies engaged in development of anti-virus software noted that since the middle of 2013 there has been a burst of malware infection of computers. These malicious programs cipher user information. Thus, they are the most dangerous type of malicious programs of Ransomware class (extortioner programs). These programs not only block access to a computer for victims, but also block users’ access to files using various enciphering algorithms. Usually such malicious programs cipher popular types of the user files, which can be of a certain value: documents, spreadsheets, database files, photos, video and audio files, etc. To encrypt files the user is offered to pay ransom by means of some Internet payment services or cryptocurrency (usually bitcoins). The first versions of such malicious programs appeared in 2006–2007. However, at that time these programs used nonresistant enciphering algorithms, a small size of enciphering keys and extremely inefficient distribution methods. Therefore, they weren't widely distributed. Modern malicious programs do not have these shortcomings. They use quite resistant enciphering algorithms (AES or RSA), rather big size of enciphering keys and effective infection methods (infected web pages and malicious spam e-mails). The paper describes the main tendencies of such programs development on the basis of the analysis of several most widespread types of malicious programs. It also offers possible ways of eliminating consequences of their activity.
Keywords: virology, computer virus, cyberextortion, cipher, malicious program
Visitors: 10158

13. An approach to data normalization in the internet of things for security analysis [№2 за 2016 год]
Authors: A.I. Pechenkin ( - Peter the Great Saint-Petersburg Polytechnic University (Associate Professor), Ph.D; M.A. Poltavtseva ( - Peter the Great Saint-Petersburg Polytechnic University (Associate Professor), Ph.D; D.S. Lavrova ( - Peter the Great Saint-Petersburg Polytechnic University;
Abstract: This paper analyzes a concept of the Internet of Things to develop a system for security incidents detection. System development requires effective methods and algorithms for preprocessing and storing high volumes of data from heterogeneous devices. The authors define a notion of a “thing”, formulate the basic information coming from the “thing” to an information system. In this paper the “thing” is considered as a data source with its own features. The authors apply the ETL (Extract Transfer Loading) technology to the Internet of Things data preprocessing. Heterogeneous devices provide a great number of different data types. To analyze this information in SIEM the system needs to show information and command messages from the Internet of Things in the event space. For this purpose it is necessary to adjust them to the same form, due to the fact that a researcher often needs to analyze various events together and one event may include various messages. This problem may be solved using metadata. The authors propose an approach that applies hierarchical directories to normalize high volumes of heterogeneous data from the Internet of Things. Hierarchical directories contain information about data source and their contents. The paper describes the basic metadata directories.
Keywords: etl, information security, etl, big data, normalization, internet of things
Visitors: 4284

14. Semantic relations in text classification based on Bag-of-words model [№2 за 2016 год]
Authors: Nugumanova А.B. ( - D. Serikbayev East Kazakhstan State Technical University (Senior Lecturer), Ph.D; Bessmertny I.A. ( - The National Research University of Information Technologies, Mechanics and Optics (Professor), Ph.D; Pecina P. ( - Charles University (Professor), Ph.D; Baiburin Е.M. ( - D. Serikbayev East Kazakhstan State Technical University (System Analyst);
Abstract: The paper contains the results of research concerning quality improvement of automatic text classification based on statistical approach. It considers Bag-of-words model as a basis model of text representation. This is the most popular and the simpliest text representation model that is used in many tasks of automated language processing. The model represents texts as sets of words ignoring their order and relations. Therefore, the semantic similarity of two texts is assessed by a number of matching pairs of words. So, the texts containing few common words are meant to be semantically far from each other. Due to ignoring semantic links, this feature of Bag-of-words model creates a serious problem in such important task of natural language processing as automatic text classification. This paper proposes to enrich Bag-of-words model by semantic links from these texts extracted based on the joint word appearance statistics. Particularly, the contribution of this work consists in a new method of building and using of a semantic links matrix that is further used to display text representations to a space of linked words. The final purpose of this work is proving that the proposed model is more efficient in binary text classification than the traditional Bag-of-words approach. In order to compare these two models the authors carried out a set of experiments based on the standard Reuters 21578 texts collection. The results of the experiments demonstrate improvement of classification quality comparing to known methods.
Keywords: svd, binary text classification, bag-of-words, semantic relations
Visitors: 10845

15. Visual analytics support system of VLSI layout design for double patterning technology [№2 за 2016 год]
Authors: Shakhnov V.A. ( - Bauman Moscow State Technical University (Corresponding Member of RAS, Professor), Ph.D; Zinchenko L.A. ( - Bauman Moscow State Technical University (Professor), Ph.D; Verstov V.A. ( - Bauman Moscow State Technical University; Makarchuk V.V. ( - Bauman Moscow State Technical University (Associate Professor), Ph.D;
Abstract: The paper discusses a software tool for visualization and analytical support of VLSI layout design process. It is noted that visualization is a very important part of the system-on-chip design process. Nowadays a VLSI design engineer has to manage big data arrays during his everyday duties. The paper notes that the main purpose of visualization is data transformation from format that is suitable for high-performance computing to format that is convenient for human perception and cognition. An analytics support tool for system-on-chip design process is based on clustering and cognitive technologies for different project solutions representation of VLSI layout during its decomposition for double or multi-patterning. VLSI layout decomposition is based on graph models, e.g. a contradiction graph. The paper proposes an approach to clustering and classification of contradictions that a design-engineer has to manage during VLSI layout decomposition for double or multi-patterning. The authors propose different project solutions according their contradiction classification. They also illustrate the approach to contradiction visualization for the double patterning technology.
Keywords: the theory of counts, visual analytics, multiple patterning, vlsi, cognitive informatics
Visitors: 6826

16. Bank clients’ solvency forecasting based on machine learning methods and Markov chains [№2 за 2016 год]
Authors: Shunina Yu.S. ( - Ulyanovsk State Technical University; Klyachkin V.N. ( - Ulyanovsk State Technical University (Professor), Ph.D;
Abstract: Customer financing is one of the banking priorities. The greater part of a banking net profit is formed due to income from credit financing. However, the commitment to profitability of these operations is always related to various types of risks, which can lead to losses. In order to prevent the losses the article proposes the system for decision-making support of credit financing, starting from granting of credit to the subsequent repayment of current loan payments. When making a decision about granting a loan the system forecasts the creditworthiness of a potential borrower using aggregated classifiers. These classifiers are the results of using several independent machine learning methods that are united by a mean value, as well as by a voting procedure. The input data are client’s records specified in the application for a loan. During the repayments of the current loan the system analyzes the dynamics of an individual borrower's repayment taking into account credit terms, information about a borrower and his credit history. The system then predicts changes in the borrower’s solvency for the next month. The article proposes using Markov chains of 1st and 2nd order, as well as machine learning methods as models. Moreover, the system provides a preliminary analysis and input data processing including non-numeric data coding, continuous data sampling, selection of the most informative features, as well as the recovery of missing data of credit history. The article includes the example showing the effectiveness of the proposed methods and algorithms.
Keywords: forecasting, markov chains, machine learning methods, solvency, creditworthiness
Visitors: 7550

17. Decision assessment principles in the automated system of engineering product quality control [№2 за 2016 год]
Authors: Burdo G.B. ( - Tver State Technical University, Ph.D; Vinogradov G.P. ( - Tver State Technical University, Ph.D; Semenov N.A. ( - Tver State Technical University, Ph.D; Sorokin A.Yu. ( - Tver State Technical University (Assistant);
Abstract: The features of multiproduct machinery production are primarily associated with a large number of different products under development and in progress simultaneously. It leads to time shortage while performing the stages of a product life cycle. In this regard, work staging at design and technological preproduction is violated; there are no clear criteria for product quality. It leads to non-predictable results (considering the quality of products). It should be noted that, as a rule, the first samples of high-tech products are created in the conditions that prolong the period of product launch due to the need of its improvement. Therefore, the importance of creating quality control automated systems becomes clear. It is known that in any situation of choice a quality of decision is determined by quality evaluation criteria of each of them. The task becomes more complicated when there are multiple stages of product evaluation. A separate aspect of product quality is assessed at each stage. However, at the same time these aspects (parameters) have a qualitative and quantitative influence on each other. Therefore, the article pays much attention to quality criteria. The paper presents the results of the research in the field of quality control automated systems in multiproduct machinery production. It also considers the principles of choice of product quality evaluation criteria, provides a set of quality evaluation criteria developed on the basis of these principles. The paper shows a decision-making mechanism in the system on the basis of production models and Petri nets.
Keywords: fuzzy petri nets, production model, quality criteria, a control system of quality, product life cycle, multiproduct machinery production
Visitors: 6814

18. Fuzzy logic in a sensorless valve electric drive [№2 за 2016 год]
Authors: Lgotchikov V.V. ( - Smolensk Branch of the Moscow Power Engineering Institute (Associate Professor), Ph.D; Gorchakov D.V. ( - Smolensk Branch of the Moscow Power Engineering Institute;
Abstract: The paper considers a 6-step algorithm of valve electric drive sensorless control. The analysis of transient processes in electric drive power circuit showed the decrease of overall performance of a valve electric drive in dynamic modes of operation when the drive is controlled by a sensorless algorithm for determinination of the switching moment using a counterelectromotive force signal integral. In some cases the whole system can become unstable. It's necessary to compensate the increase of current and magnetic circuit saturation by dynamical changing control system parameters, so that the system could operate in a stable condition. To achieve this purpose the article proposes using a fuzzy logic controller. Such controller adjusts the commutation moment of drive phases using the database of fuzzy rules. Fuzzy logic control system uses normalized values of motor current and a rate of rotation as input parameters. Fuzzy logic controller used in electric drive control system will increase a control performance in dynamic modes, such as applying the load or velocity signal changes. Simulink tests show that the designed system with fuzzy logic control allows high quality level of motor control in a wide range of motor speed. The proposed control system also increases load-carrying capability of the whole system.
Keywords: modeling, fuzzy controller, fuzzy logic, back-emf, sensorless control, electric drive
Visitors: 8869

19. Simulator programs for temperature fields in flat form products [№2 за 2016 год]
Authors: Margolis B.I. ( - Tver State Technical University, Ph.D;
Abstract: The article considers a model of a temperature field in the flat shape product at asymmetric convecti ve-radiant heat transfer of product surfaces to the environment and protecting surfaces (heating elements) of production equipment. The paper presents equations for calculating product temperature distribution using numerical finite-difference methods. There is a calculation example of convective-radiant cooling of a glass plate. The article shows that the calculation results are in a good agreement with published sources. It also states possible solutions for the problem in Matlab. The standard function pdepe in MatLab has become a basis for development of a program that allows simulating a product temperature field according to specified thermal and physical characteristics of a material (thermal conductivity, temperature conductivity) and convectiveradiant heat transfer parameters (a convective heat transfer coefficient and emissivity factors). The paper considers program development features related to setting functions such as differential equations, initial and boundary conditions. There are program codes of functions, of the main program and calculation results of the temperature distribution. A comparative analysis of problem solution in Matlab and the results obtained using the finite-difference relations demonstrates their good agreement. The paper shows the prospects of using standard Matlab functions to solve the identification problems of heat transfer conditions and optimization of product thermal treatment in various technological processes.
Keywords: heat treatment optimization, identification of heat transfer conditions, differential equation, initial and boundary conditions, modeling, finite difference methods, convective-radiant heat transfer, flat shape product, a tempering
Visitors: 8022

20. The software of technological process of soldering spacecrafts’ waveguides [№2 за 2016 год]
Authors: Tynchenko V.S. ( - Academician M.F. Reshetnev Siberian State Aerospace University (Associate Professor), Ph.D; Bocharov А.N. ( - Academician M.F. Reshetnev Siberian State Aerospace University (Associate Professor), Ph.D; Laptenok V.D. ( - Academician M.F. Reshetnev Siberian State Aerospace University (Professor), Ph.D; Seregin Yu.N. ( - Academician M.F. Reshetnev Siberian State Aerospace University (Associate Professor), Ph.D; Zlobin S.K. ( - JSC “Academician M.F. Reshetnev “Information Satellite Systems” (Process Engineer);
Abstract: The paper solves the problem of automated control of soldering space vehicles waveguides using induction heating. The authors analyze the peculiarities of the induction soldering process and identifie a necessity of information-control system automation. The developed automated system controls a product heating process by varying the power of the ind uctor on the basis of information about the soldering zone temperature, and stabilizing temperatures in a narrow range above the solder melting point but below the waveguide melting point. This allows automating the soldering process, improving the quality of waveguides and eliminating burn-throughs. The software product is a Windows-based application that works in Windows XP/7/8/8.1/10. It is developed in C++ language in the programming system Borland C++ Builder 6.0 using the object-oriented approach. The article shows a block diagram of a software system consisting of five modules and describes the main algorithm of its work. There is also a description of the waveguide automated soldering system operation that explains basic functions and limitations of the system. The developed software product allows setting measurement equipment, setting and changing soldering parameters, as well as looking through temperature graphs recorded by the system. Furthermore, it is possible to monitor and edit process database. The system has an advanced human-machine interface and does not require additional skills from users. Moreover, it offers flexible scalability features. There article presents the results of experimental studies that show high quality of soldering process control and system applicability to automation tasks.
Keywords: software product, induction soldering, waveguide, automated management, an automated system issue
Visitors: 7511

← Preview | 1 | 2 | 3 | Next →