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

Journal influence

Higher Attestation Commission (VAK) - К1 quartile
Russian Science Citation Index (RSCI)

Bookmark

Next issue

2
Publication date:
17 June 2024

Articles of journal № 1 at 2021 year.

Order result by:
Public date | Title | Authors

1. Approach to designing software for artificial entity management systems [№1 за 2021 год]
Authors: Vinogradov G.P., Konukhov I.А., Shepelev G.А.
Visitors: 3860
The problems of intelligent control of artificial entities (including robotic complexes (RC)) are closely associated with the problem of decision-making. The formal decision theory was developed by abstracting from subjective fac-tors. This led to the development of a normative theory of decision - making by the "ideal" subject. Analysis of ap-proaches to the construction of RC control systems has shown that they do not have the property of independent de-cision-making. In practice, developers entertain possible behaviors of such systems, and the corresponding algo-rithms are embedded in the RС control system. As a result, such an object doesn’t have a self-sufficient behavior that guarantees the fulfillment of some mission, especially as part of a human-machine system. The demand for be-havior intellectualization forces us to reconsider the logical and mathematical abstractions underlying the construc-tion of their onboard control systems. The work objective is to substantiate the approach to software development of intelligent RC control systems based on the pattern theory. It is necessary to develop an approach that ensures the transfer of effective experience to the RC management system, the compatibility of the theological approach, and the causal approach, which is im-portant when integrating the RC and the personnel of the units. Show that the patterns of the subject's departure from the ideal rational choice to the subjectively rational are associated with the peculiarities of identification and under-standing of the state of the external environment and the properties of their interests. External factors are related to the obligations that the agent assumes. Internal factors reflect the interests of the subject, induced by his needs and the ethical system that he sticks to. The paper uses the methods of the theory of reflexive games and the theory of information management of sys-tems with will and intelligence. It is shown that the choice in conditions of severe time deficit is made based on behavior patterns that reflect ef-fective experience. Patterns form both the information structure of representations and the set of possible variants of representations. Assessments of contentment with the current situation of choice by the subject lead to a change in the structure of interests of the subject, and he can choose it. A formal model of the behavior pattern is developed. An approach to solving the problem of identification and construction of pattern models is proposed. For these pur-poses, four positions of information processing were used, and a method of logical inference on patterns was devel-oped. The results of software solutions for identifying the behavior pattern when using a new generation of training systems are presented.

2. Mental models in designing the behavior of artificial objects [№1 за 2021 год]
Author: Vinogradov G.P.
Visitors: 3401
The authors relate the immediacy of the problem considered in this paper to the need to design artifi-cial systems to perform a certain mission like a person and when interacting with him. The analysis of approaches to the construction of artificial objects has shown that developers often give artificial objects their own patterns of behavior because of the specifics of the concepts and con-cepts they use. As a result, there are gaps between the formal models of patterns offered by developers and the expectations of users. The aim of the authors is to justify an approach to the development of software for intelligent sys-tems for managing the behavior of artificial entities based on the theory of patterns and to propose an approach that provides the development of digital products based on the patterns of behavior of the subject-leader for artificial entity management systems that automate the implementation of mission problems. The work uses the methods of the theories of reflexive games and information management of sys-tems with willpower and intelligence. There are ten constituent elements based on a formal model of the behavior pattern. The work shows that these elements form what can be called an intelligent digital machine designed to automate the execution of a mission in the interests of the host subject. These components are present when a person performs a mission, including all participants in the project to develop an artificial entity. The authors show that the ideas adjustment about the architecture of an ar-tificial entity through the exchange of information during the discussion allows us to determine the most effective model of the behavior pattern and all its components for implementation in an artificial entity. The authors proposed to conduct matching as a game by conducting experiments using the TOTHE method (a set of input data  impact  result), using spatial and visual logic to interpret the results. The possible logic of interpretation is justified. The authors briefly considered the models of the constituent elements of the behavior pattern for an artificial entity. An example of the approach im-plementation is considered. The authors show that in conditions of severe time scarcity; the choice based on behavior patterns makes it possible to implement effective behavior that does not require sig-nificant computational resources.

3. Algorithms for smart node patterns in a wireless sensor network [№1 за 2021 год]
Authors: Vinogradov G.P., Emtsev А.S., Fedotov I.S.
Visitors: 3676
One of the trends in the development of modern weapons is the "linking" of individual samples with a certain degree of autonomy into a complex using, as a rule, wireless sensor networks. The scope of such complexes is uncertain and poorly formalized environments. It is possible to achieve their desired efficiency mainly by improving the intellectual component of the management system of the complex as a whole and the individual node in particular. However, it should be noted that the vast majority of research in this area remains only at the theoretical level. There is a gap be-tween the primitive models of artificial entities’ behavior, for example, in swarm robotics, models of their interaction, and expectations from the practice. The situation is aggravated by the secrecy re-quirements, miniaturization, and low energy con- sumption. This paper presents an approach to the development of software for intelligent control systems for a separate network node that has a given degree of autonomy when performing problems. To offer rela-tively simple algorithms in the conditions of restrictions on power consumption and speed for giving the network node the properties of intelligent behavior, to provide the ability to study the situation and decide both independently, considering the data received from other network devices, and as part of a group. There are methods of the fuzzy sets theory, the theory of building fuzzy models and networks, and approaches and algorithms for building on-board intelligent control systems in this work. The work shows that the class identification of typical situations and successful action methods in actual conditions contribute to the development of the required algorithms. On this basis, it becomes possible to develop formal behavior models (patterns) for implementation in the node management system. The authors propose a two-level structure of an intelligent network management system. The upper level, implemented by the operator, corresponds to such properties as survival, safety, the fulfillment of mission obligations, accumulation, and adjustment of the knowledge base as effective behavior pat-terns. The object of control for it is the network, considered as a functional system. It calculates the current indicators of specific value based on the results and effectiveness at time t, calculates and im-plements the method of action (behavior) at time t according to a given behavior pattern, and monitors the results of implementing the behavior pattern.

4. Application of the purposeful behavior principle in the cognitive control system of a radar station [№1 за 2021 год]
Author: A.A. Nepryaev
Visitors: 3226
The application of cognitive technologies in radar is a rapidly developing area with many opportunities for innovation. A significant obstruction in this discipline is the lack of a common understanding of how the architecture of a multi-function radar control system should be designed to include multiple feedback loops that enable the manifestation of cognition. In the radar community, there is still no pre-cise definition of what distinguishes an adaptive system from a cognitive one. This work is intended to expand and substantiate the list of elements and qualitative characteristics that must be present in a radar system in order for it to be classified as cognitive. The author suggests the use of a metacognitive approach to developing a model of purposeful behavior that selects the most profitable strategy and controls the cognitive processes involved in learning. The action selection based on the perception of the environment is the fundamental characteristic of the cognitive system. Finally, the choosing process leads to the optimization problem, when it is de-sirable to choose the action with the maximum reward. This is determined by the degree of similarity of the current internal and external states with the target one. This is based on the principle that radar sys-tems should not be classified as cognitive or non-cognitive, but should be evaluated by the degree of severity of cognitive functions. The author suggests a gradation of cognitive systems based on the prin-ciple of purposeful behavior of control system elements. The article substantiates the need to consider the ability of the system to function in actual time and computing power as a sign that determines the degree of expression of its cognitive abilities.

5. Automation of day-to-day tasks as a modernization of a marine rescue operation automation suite [№1 за 2021 год]
Authors: Karpov A.V., А.А. Sakharov
Visitors: 3483
The Armed Forces of the Russian Federation have phased in a marine rescue operation automation suite (MROAS) in August 2014. The suite is designed to automate the activities of specialists of the Navy search and rescue service during their daily activities, as well as when making decisions on search and rescue operations for emergency situations on Navy ships and vessels. The paper presents modern approaches to automating day-to-day tasks solved by specialists of the Navy search and rescue service: a hybrid method for developing special software, methods of forming functional requirements for a modernized MROAS, a generalized list of information that the suite ac-cumulates and keeps up to date, the basic principles of organizing information interaction between the suites distributed among the Navy command and control bodies at different levels.

6. Method of testing the training models for the adequacy [№1 за 2021 год]
Authors: Ilin V.А., Kiryushow N.P.
Visitors: 3545
The paper substantiates the necessity of assessing the quality of simulated models of trainer systems and their adequacy to actual systems and describes a method for evaluating the adequacy of simulation models. The simulated model must provide the required accuracy and reliability of the process simulation. The simulation validity assumes that the model meets some specific requirements that allow us to test its quality. The model quality analysis involves testing for compliance with the modeling goals. In general, the evaluation of the model properties includes the model adequacy assessment, the simulation results’ ac-curacy (simulation error), the stability of the simulation results of the studied processes, and the study of the model sensitivity. The model adequacy assessment reflects its compliance degree with the actual system. The algo-rithm for the model adequacy checking comprises comparing the outputs (responses) of the model and the actual system with the same input values. Here, statistical methods are used to test hypotheses, for example, by the t-Student criterion. The path of determining the estimates of the mathematical expectation and variance of the deviation of the components of the response vector tests the accuracy of the simulation. The variance of the flow values tests the stability of the simulation results. The simulated model sensitivity refers to the degree to which the model's output parameters or re-sponses change depending on the input characteristics. Methods of assessing the adequacy of the models include the steps of selection criterion of the va-lidity of the simulation model to the subject of the study, the production of measurements of the re-sponse values of the real system and the simulation model, the computational stage with the assessment of the adequacy of the simulation model to real systems, the determination of the adequacy of the simulation model. The evaluation method for assessing the models' adequacy includes the selecting stages the criteri-on for the adequacy of the simulation model to the subject of research, making measurements of the re-sponse values of the real system and the simulation model, the computational stage with the assessment of the adequacy of the simulation model to actual systems, determining the adequacy of the simulation model.

7. The quality control of training equipment [№1 за 2021 год]
Authors: Ilin V.А., Pakhomov E.S.
Visitors: 3828
Using training tools requires an assessment of their effectiveness to achieve the goals of training and training. The effectiveness of training equipment can be determined only in the process of their intend-ed use, which is not always possible; we can only talk about the effectiveness of training using training equipment. The authors of the paper propose to test the effectiveness of simulators and training complexes through a system of indicators of their qualities. The quality criteria of training equipment can be their ability to implement training and training programs. In accordance with the content and structure of the educational process, the type of autonomous simulators and simulators as part of training complexes, the stages of their life cycle, and operating conditions, the paper proposes four groups of quality indi-cators: didactic, functional, technical, and economic, and establishes their relationships and evaluation methods. Through the indicators of didactic qualities, it is possible to assess the compliance of educational and training tools with the requirements of the educational process, its structure, and content. Indica-tors of functional qualities allow us to evaluate the capabilities of training tools for implementing the didactic requirements of educational programs. Indicators of technical qualities evaluate the character-istics of training tools that ensure their use in the educational process. Economic indicators allow us to estimate the costs at the primary stages of the life cycle of training equipment. Economic indicators allow us to estimate the costs at the primary stages of the life cycle of training equipment. The proposed system of qualities of training equipment, along with a system for evaluating the effectiveness of training with their use, allows us to justify the feasibility of creating training equipment, optimize their structure depending on the requirements and problems of training.

8. The performance evaluation of simulator training by the method of target management [№1 за 2021 год]
Authors: Ilin V.А., Savvateev A.S.
Visitors: 5003
The extensive use of educational processes of educational institutions and in the system of combat training determines the relevance of the development of methods for justifying training equipment, evaluating their effectiveness and the effectiveness of training provides. One of these methods may be the target management method, proposed in this paper and not previously used in this subject area. The method of targeted training management involves determining the goals of training and the re-quirements for its means, the structure, and content of training, and testing the results of training. The paper justifies the choice of different categories of students of different simulators and meth-ods for evaluating the effectiveness of training for different students’ categories. Based on the func-tions of the students' activities, the authors propose and justify the activity classification of the trained operators and their division into three categories, three levels. Under the accepted classification, the authors define the requirements for training equipment and the organization of training equipment. Methods of forming assignments for students under the objectives of training and evaluation of its re-sults, including automation of training assessment, are fundamental in the organization of simulator training based on the method of target management. The paper suggests the following procedure for the development of mathematical software automate the assessment of the preparation: the choice of control parameters and the objective function devel-opment, the parameters and rating scales exercises development, the drafting of the algorithm and pro-vide recommendations. The target management method for evaluating the effectiveness of simulator training is developed because of over ten years of experience in using simulators in the educational process and the authors’ personal participation in their creation and use.

9. Using the entropy characteristics of network traffic to determine its abnormality [№1 за 2021 год]
Author: Efimov A.Yu.
Visitors: 3395
The number and scale of network computer attacks (intrusions) are constantly growing, which makes the problem of their prompt detection highly relevant. For this, network-level intrusion detection sys-tems are used, based on two approaches – abuse detection and anomaly detection, and the second ap-proach is more promising in the face of the constant appearance of new and modified types of intru-sions. The main objects of application of anomaly detection techniques are mass attacks (DoS- and DDoS attacks, scanning, spreading of worm viruses, etc.), which are difficult to detect by other (for ex-ample, signature-based) methods, since they are often based on regular network interactions. The entropy analysis method for detecting network traffic anomalies, compared to many other methods, is characterized by sufficient simplicity of implementation and speed of operation. The appli-cation of the method is based on the general assumption that abnormal traffic is more ordered or struc-tured than normal traffic in some parameters and more chaotic in others, which manifests itself as a de-crease or increase in the entropy of these parameters. This paper is devoted to determining the nature of the impact of attacks on the entropy of such traf-fic parameters as the source and destination IP addresses, as well as the destination port, considering several types of DoS- and DDoS attacks as objects. The author describes an approach to determining entropy (using Shannon entropy). The paper presents the results of the author's model, which reveal the ambiguity of the impact of attacks on entropy characteristics. The results show a clear dependence of such inpact (decrease or increase) depends on factors such as the source, target, attack power, and dis-tribution of normal traffic. Conclusions are made about the possibility of effective detection of anomalies corresponding to DoS and DDoS attacks by analyzing the entropy of network traffic parameters, but only if this analysis is carried out taking into account the distribution of normal traffic and the volumetric characteristics of normal and total traffic.

10. Network anomalies detection by deep learning [№1 за 2021 год]
Author: V.N. Zuev
Visitors: 5259
The paper discusses the machine learning application for detecting anomalies in network traffic. Artifi-cial neural networks of deep learning are used as a tool. In this paper, the NSL-KDD data set is ana-lyzed and used to study the effectiveness of deep learning neural networks in detecting anomalies in network traffic patterns. The most important aspects of this dataset are the imbalanced class distribu-tion. The paper describes the method of effective usage of objective functions backpropagation algo-rithms in order to train the neural network on imbalanced samples. Using the backpropagation algo-rithm is connected with many difficulties. The major problem is the ability to generalize the neural network. The ability to generalize is the most important characteristic of a neural network. It is mean that trained on studying data neural network is capable to produce output value by using unknown da-ta. However, using for training noisy data decreases the ability to generalize the neural network. The proposed method makes it possible to more efficiently calculate the value of the aim function, which is the basis of the error back-propagation algorithm. The method is well fit for the heterogeneous sample and can use priority information about the sample’s significance. The pepper described an algo-rithm of the method. Using this method will improve the accuracy of the neural network for classifica-tion and regression problems. The experimental result shows that it well suits the designed method for network anomaly detec-tions.

| 1 | 2 | 3 | Next →