Category Archives: Issue # 2(21)

APPLICATION OF A NEURO NETWORK APPROACH TO LOGICAL DATA PROBLEMS AND BUILDING INTELLIGENT DECISION-MAKING SYSTEMS

UDC 519.71

D.P. Dimitrichenko, R.A. Zhilov


The need to reduce the dimensionality of large data sets while maintaining the logical structure, as well as the detection of hidden patterns and the removal of information noise and redundancy in the description of diagnostic (recognition) objects leads to the need to construct an effective method for classifying objects in weakly formalized areas of knowledge. Logical functions that describe objects using variable-valued predicates allow us to reveal hidden regularities and eliminate redundancy in the description of objects. Ordered by means of variable-valued logical functions, object classes are the basis for the formation of the structure of cognitive maps. The purpose of this study is to create an algorithm for constructing a logical neural network based on the variable-valued logic function and justifying the possibility of applying the results obtained in the construction of cognitive maps. The theoretical possibility and algorithms allowing to make the transition from variable-valued logic functions to cognitive maps using the neural network approach are grounded. The result of this work is the procedure for constructing a cognitive map using logical neural networks built on the basis of variable-valued logical functions. The advantage of the obtained cognitive map is the possibility of functioning within the framework of fuzzy logic.

Keywords: predicate, predicate significance, variable-valued logical function, logical neural network, cognitive map, cluster analysis, neural network.

Full text:
DmitrichenkoZhilov_2_18_1.pdf

DEVELOPMENT OF THE SOFTWARE CONCEPT OF THE TECHNIQUE OF ASSESSMENT OF QUALITY OF INFORMATION SYSTEMS “INSPECTOR”

UDC 004.05

O. M. Romanova (Knyazeva), K.N. Kurguzkin


The article considers the problem of assessing the quality of information systems (IS) of organizations. It was observed, that the most promising approaches in the field of IS quality assessment and management based on ISO 9000. The method “Inspector” which was developed by I.M. Azhmukhamedov and O.M. Romanova refers to such methods. The task of developing an algorithm and software that collects and processes expert data is actual. The article is devoted to the solution of this problem. The stages were identified in which experts data are collected for the “Inspector”: definition of IS functions; definition of IS subsystems; definition of elements of sets of concepts of fuzzy cognitive models of IS quality assessment; identification of links between the concepts of fuzzy cognitive models of IS quality assessment; formation of a knowledge base for assessing the current level of IS quality, consisting of fuzzy logic rules that determine the impact of each damage’s level of the damage hierarchy on information security services; condition assessment of concepts of fuzzy cognitive models of an estimation of quality of IS, which are input parameters of algorithms of a method “Inspector”. It is noted that at stage four-six it is necessary to use methods that excludes the influence of other experts on the opinion of one expert. As a result, the method of online questioning was chosen to solve the problem. It was suggested that the system is required in the form of a web portal. The algorithm of work was developed. The roles of portal users were identified. The structure of the portal form was defined.

Keywords: information security, quality assessment, infrastructure, software development, information system, decision maker, expert evaluation.

Full text:
RomanovaSoavtori_2_18_1.pdf

MANAGEMENT OF THE FUNCTIONING OF THE MAN – MACHINE INFORMATION SYSTEM ON THE BASIS OF MULTI-ALTERNATIVE OPTIMIZATION OF PERSONNEL COMPETENCIES

UDC 681.3

K.I. Lvovich, Y.P. Preobrazhensky


The information system is examined in the article as a man-machine system, the effectiveness, quality and reliability of its functioning is largely determined by the personnel level of necessary knowledge and skills, developed with the use of educational resources. In this case, the management of the information system functioning consists in the achievement of key indicators of its effectiveness through the personnel competencies optimization. The implementation of this approach to management within the framework of the concept of dual personnel training of information systems is proposed. The numeric sets of components that determine a compliance of competences with advanced requirements for the development of information systems are defined. A sequence of optimization tasks enabling to provide this level is created. A mathematical description of the mentioned objectives setting on the basis of the multi-alternative optimization method is developed.

Keywords: information system, man-machine system, dual personnel training, educational resource, multi-alternative optimization.

Full text:
LvovichPreobrazhenskyYP_2_18_1.pdf

INDOOR POSITIONING SYSTEM BASED ON BLUETOOTH BEACONS

UDC 004.8

V.M. Grinyak, A.S. Devyatisilnyi, V.I.Lulko, P.A. Tsibanov


The paper is devoted to research of possibility to use Bluetooth devices for indoors navigation. Relying on alternative measurements such as Wi-Fi network, onboard accelerometers, Bluetooth devices are vastly used to solve positioning and navigation problems when there are limitations to use global positioning satellite systems (such as GPS). Recently the indoors navigation became a stand-alone subclass of the research problems with subset of developed math models and the implementation hardware. Even though there is a lot of interest in the solution of the problem, there are still no standard approach. Due to the accuracy limitations of the broadly available mobile devices applying inertial navigation approach would dramatically reduce variety of the hardware it could be used. Relying on available Wi-Fi networks for evaluation of navigation parameters also has accuracy limitations. However, using Bluetooth signal considered as way prospective for solving navigation problems. Due to the small size, relatively low prices of Bluetooth transmitters and signal features (indoors walls and bulkheads are not transparent) it is possible to deploy special indoors infrastructure for navigation purposes. The paper concludes that nature of the measurement available for Bluetooth signals is applicable for indoors accurate enough navigation for typical distances “object-beacon” in the range not more than 5-7 meters.

Keywords: information system, indoor navigation, beacons, Bluetooth, position, velocity, least squares method.

Full text:
GrinyakSoavtori_2_18_1.pdf

INVESTIGATION OF THE FUNCTION OF INCOME RETENTION BY MEANS MONOTONE
DERIVATIVE

UDC 519.53

A.V. Starikov, M.L. Lapshina, S.V. Pisareva, A.A. Gribanov, A.L. Boykova


The paper describes a class of utility functions whose derivative is representable as a Laplace transform. The basic properties for the utility functions belonging to the described class are formulated. The problem of stochastic domination is analyzed, limiting properties of indices of absolute and relative risk aversion are investigated. The expediency of separating the utility function from the whole set is due to two considerations. First, this class includes almost all traditionally used in describing investors behavior of the utility function. Secondly, each function in L can be represented approximately as a sum with positive coefficients of exponential phase transitions. The main focus of the work is on two analytical methods. The first is the task of strengthening and mitigating risks, when a risk-averse investor has to decide what is best: to expose your income to participation in two risky projects, or to give up risk altogether, or to participate only in one of the projects? The second aspect highlights the behavior of absolute and relative risk aversion indicators. In this paper we give a more complete integral representation of functions belonging to L, and, a systematic description of the class; the statement is formulated in terms of lottery preference, fully characterizing the class, the basic mathematical concepts and properties of completely monotonic functions that are necessary for formal description and study of the introduced class, the precise definition of the class of the utility function, the characteristics of the basic properties and the statement of necessary and sufficient conditions for the function usefulness of the class being studied. In the article the question of stochastic domination on the introduced class is considered, corresponding criteria of domination are given. The findings are used further in connection with the task of strengthening or mitigating the risk with the simultaneous impact of independent random factors on the income of the investor. Finally, the paper presents an analysis of the asymptotic properties of the absolute and relative risk aversion indicators for utility functions from the introduced class

Keywords: utility function, class, risk, alternative, securities, preferences.

Full text:
StarikovLapshinaSoavtors_2_18_1.pdf

A STUDY OF THE POSSIBILITIES OF USING STEGANOGRAPHIC METHODS OF INFORMATION PROTECTION

UDC 681.3

A.V. Pitolin, Y.P. Preobrazhensky, O.N. Choporov


Steganographic methods are used to hide the very fact of the existence of certain messages. The paper analyzes the key concepts that are used in steganographic methods of information transformation. Describes the features of the steganographic methods hide information in graphic files. Developed the threat model unauthorized transfer of information by steganographic methods of information transformation using the graphical containers. The article Presents a classification scheme of threats of unauthorized information transfer using the methods of its steganographic transformation. An experiment was conducted to identify the most effective ways to counteract unauthorized access to information. The author has established that almost all methods of counteraction to unauthorized access on time of influence do not exceed 2 seconds. Highlighted ways to counter at the time of exposure that do not exceed 0.7 seconds. The experiment was conducted among 10 people with the help of the S-tools program and the created AntiStego software. The paper presents the algorithm of the program “AntiStego” together with the description of the software modules implementing counteraction to unauthorized access. A generalized scheme of the experiment for combating the unauthorized covert transfer of information.

Keywords: information security, steganographic approach, unauthorized access.

Full text:
PitolinSoavtors_2_18_1.pdf

DEVELOPMENT OF PEDESTRIAN ARTIFICIAL INTELLIGENCE UTILIZING UNREAL ENGINE 4 GRAPHIC ENGINE

UDC 004.42

D.Y. Bychkovskiy, F.N. Abu-Abed


The article demonstrates the implementation of AI for pedestrian simulation in the driving simulator by means of Unreal Engine 4 graphic engine and VR-technologies. The authors review the operation principles of behavior trees and their components. The paper describes the internal structure of a pedestrian AI class and methods of implementing object detection in the field of view and audibility utilizing Unreal Engine 4. The authors give the example of using Environment Query System included in the engine AI system and display the result of executing its queries, which used in the process of the virtual pedestrian behavior tree simulation. Since in the developed driving simulator it is necessary to achieve a high frequency of frame changes and low demands on the resources of the computer system, the article suggests an optimal solution for simulating a large number of pedestrians in a virtual city. The article shows the behavior tree and represents operation algorithms of the pedestrian AI’s basic components in block diagrams with annotations.

Keywords: Unreal Engine 4, Environment Query System, behavior tree, artificial intelligence, driving simulator.

Full text:
BychkovskiyAbuAbed_2_18_1.pdf

MODELS AND ALGORITHMS OF FORMATION THE OPTIMAL WORK TIMETABLE OF THE MOBILE MEDICAL BRIGADE

UDC 519.863

V. N. Kolpachev, N. A. Selezneva


In order to improve the accessibility of medical care and the quality of medical services to residents of remote, hard-to-reach areas and small settlements in certain regions of the Russian Federation, forms of medical care are being developed using mobile medical complexes serviced by mobile medical teams. The construction of an optimal work timetable, that is, a sequence of work that ensures their completion no later than the deadlines set, is an important stage in the scheduling of mobile medical brigades’ departures. When solving this problem, it is important to take into account the time for the movement of mobile medical teams and the schemes by which they will be delivered to the points of medical work, which in turn can be determined by meteorological, climatic, geographical conditions in the region, the area of the territory, the density of settlement residents, a model for locating settlements in certain territories and other reasons. The article deals with models and algorithms that correspond to some particular wording of tasks of determining the optimal order of execution of work by a mobile medical brigade, taking into account the time of its movement between points of deployment. An example of the application of the structures considered is given. Highlighted the actual problems in the field of health, for the research of which the models and algorithms described in the article can be used.

Keywords: mobile medical brigade, accessibility of medical care, optimal sequence of service, time of relocation of the brigade.

Full text:
KolpachevSelezneva_2_18_1.pdf

MATHEMATICAL MODEL OF CREATION OF THE RESERVE OF MONEY

UDC 519.8(075.8)

A. V. Ganicheva


The relevance of the study is due to the need for rational management of funds, as an organization (enterprise), and various communities, individual entrepreneurs, family budget and individual. The article developed a new method for assessing the optimal management of cash reserves. For continuous and discrete cases, the mathematical models based on the device of the linear differential and differential equations are constructed. The change of reserve as a function of time is shown. Options of assessment of parameters are offered under accurate and indistinct conditions. The conditions for optimal management of reserve funds, as well as the solution of the problems of determining the time for this level of reserve and the initial value of the reserve at a given forecast level are formulated. The effective and inefficient management of funds under clear and unclear conditions is defined. The analysis of the dependence of reserve funds on the values of the parameters of the equations describing the process of reserve formation is carried out. The model of components of a reserve is considered. The problem of their optimum combination when maximizing a reserve is solved. The methods of integer programming are used in the solution. The materials of the article are of practical value, as they can be used in technology, Economics, ecology, military Affairs, social sphere.

Keywords: system, asset, the reserve funds, the parameters of the equation, optimal control reserve.

Full text:
Ganicheva_2_18_1.pdf

MODELS AND ALGORITHMS OF THE SOLUTION BASED ON VERBAL DATA ANALYSIS IN PRODUCTS ON PLATFORM 1C: ENTERPRISE

UDC 004.021

A.V. Kondrashov, N.A. Popova


This article discusses the problem in taking responsible managerial decisions, which significantly affect the development of the company, the organization of the production process, the definition of the company’s strategy. For the tasks of this plan are software – decision support systems. This is one of the varieties of forms of artificial intelligence, designed to help decision-makers. There are a large number of decision support systems based on quantitative data, at all stages of the analysis to solve the problem of decision making. Verbal analysis of solutions, in contrast to them, is one of the sections in the theory of decision-making based on the use of non-numerical, qualitative information. It was revealed that there is a small number of decision support systems based on methods and algorithms of verbal analysis. In this paper, we review the main algorithms and methods for verbal analysis of solutions, such as: the ARAMIS method, the AIP method, as well as the basic methods of multi-criteria choice, and provides a model reflecting the interaction of products based on the 1C: Enterprise platform and implementing the listed methods of verbal analysis of solutions. The model shown combines various methods of verbal analysis of solutions, multicriteria selection and coordination procedures.

Keywords: Full text:
KondrashovPopova_2_18_1.pdf