OPTIMIZATION OF KNOWLEDGE BASES BY BULLETIN DIFFERENTIATION METHODS
V.F. Guzik, A.P. Samoylenko, A.I. Panychev, S.A. Panychev
The built-in system for monitoring and diagnostics of electronic equipment is considered. The performance indicators of the electronic device are modeled by complex time functions of the monitored parameters that display the state of the equipment functional units. A complex criterion for estimating the significance of variations in the sensors signals of functional control points of a controlled object is proposed. The decision on the state of the object under control is based on the results of measurements of its output characteristics and is made on the basis of the combination of two criteria – level and informational. The estimate of the significance of the parameter level characterizes the magnitude of the emissions of the output signal and is constructed on the basis of the likelihood ratio in accordance with the criterion of the minimum probability of an erroneous solution. The informational criterion is based on the principle of the maximum of Jain’s entropy and gives an estimate of the information amount obtained when measuring the output characteristic of a monitoring object. Estimates of the monitored signal variations significance for the distribution laws of random variables which most commonly used in the problems of electronic equipment reliability are obtained.
Keywords: : built-in system, tolerance control, diagnostics, random process, random variables distribution law.
OPTIMIZATION OF KNOWLEDGE BASES BY BULLETIN DIFFERENTIATION METHODS
The subject of this study is the subject area, which is a precedent relationship between objects and their characteristics used in solving image recognition problems.
Intellectual analysis of data is one of the necessary stages in the solution of poorly formalized problems; therefore, in many cases the accuracy of the solution of the task depends on the method of building knowledge bases, analyzing them and minimizing them. The development of common formal methods for revealing logical patterns in any given subject area seems to be a very pressing problem, as it provides the opportunity to form optimal knowledge bases, which greatly simplifies the solution and improves its quality.
In this paper, we use the apparatus for differentiating Boolean functions to analyze and minimize knowledge bases, which are the directions of modern discrete mathematics and find their application in problems of dynamic analysis and synthesis of discrete digital structures.
The main results of the study are a constructed logical function that analyzes the relationship between objects and characteristics that characterize them, which is an opportunity to reveal all the laws of a given subject area; as well as the method of minimizing knowledge bases obtained on the basis of logical data analysis, revealing a minimal set of decision rules, sufficient for solving the task.
Keywords: : Boolean function, logical operations, knowledge base, differentiation, minimization, logical axioms.
DEVELOPMENT OF INFORMATION SUBSYSTEM OF DECISION SUPPORT SYSTEM BASED ON BAYESIAN NETWORKS FOR AGRICULTURAL ENTERPRISES
The problem of the study is to increase the efficiency and necessity of implementing the KPI decision support system in the agro-industrial enterprise. In this regard, this article is aimed at describing the process of developing the KPI system.
Bayesian networks are the main method of studying the KPI system. The quality control subsystem in the KPI system consists of a list of the work performed by the machine operators. For the evaluation of each work, the KPI indicators are selected. The choice of the indicator depends on the type of work performed and the type of culture. Assess the selected indicators of a separate work performed is not enough, it is important to consider the dependencies between the indicators. Many indicators have probabilistic characteristics, as a result of which the Bayesian network was chosen to take into account interrelated indicators. The article gives an example of using a network to account for the interrelations of indicators.
This approach to the development of decision support systems allows us to obtain an adaptive Bayesian network setup procedure that is distinguished by the ability to change the vertexity of the network with the recalculation of the probabilities of influence on the final quality assessment. The structure of information display when issuing a waybill is obtained, differing in the representation to the dispatcher of the possibility of searching for an employee based on the Bayesian network of an average percentage of the machine operator’s efficiency.
The developed mathematical apparatus can be used in the agro-industrial enterprise, which requires the implementation of the KPI decision support subsystem.
Keywords: : Bayesian network, prior distribution, quality control, KPI system.
DYNAMICAL SYSTEMS MODELING BASED ON POLYNOMIAL NEURAL NETWORKS
UDC 519.62, 004.032.26
A.A. Sholokhova, A.N. Ivanov
In the article, a polynomial neural network architecture is presented. This architecture is utilized for dynamical systems identification. The given approach is based on matrix representation of Lie transform, that is useful for investigation of nonlinear systems of ordinary differential equations. The polynomial neural network, in this case, can play a role of an effective and efficient method of investigation of dynamical systems. Moreover, it joints advantages of parallel computing architecture with the strong mathematical theory of differential equations. The key concepts and formulations are briefly described. The numerical matrix integration of the systems of differential equations is also presented. As an example, the identification of the simple model problem is considered as well as an application of the technique for modeling of vessel motion is presented. In the conclusion the limitations and further development of the method is indicated.
Keywords: : polynomial neural networks, system identification, machine learning.
INFORMATION MODEL OF DEVELOPING CORPORATE INFORMATIONAL SYSTEMS FOR SOLVING THE PROBLEMS OF ORGANIZATIONAL MANAGEMENT OF THE ENTERPRISE
Actual issues of sustainable activity of enterprises in the market and development in the conditions of tough competition are reasonably based on modern information technologies and information systems. The well-known paradigm of the BPM concept is changing to the paradigm of the S-BPM concept.
The article analyzes both concepts and suggests an information model for the development of corporate information systems (CIS) for solving organizational management problems (PMO).
It is shown that when developing the CIS for the solution of PMO tasks, information technologies of the BPM concept are actively used. In order to make effective decisions by the top managers, they consider the tasks of system analysis and activity management. In solving these problems, business processes are modeled, where the decomposition of these processes plays a significant role. Key element of the concept: Top managers – Business Intelligence of the enterprise.
In recent years, when developing the CIS for solving the tasks of the PMO, the specialists began to introduce new information technologies of the S-BPM concept. This concept is based on the decision of production tasks directly by their executors and offers appropriate tools for modeling processes. At the same time, multiple problems of technological processes and actions are considered, allowing performers to solve them in the best possible way taking into account current production needs. Key element of the concept: Managers of the lower and middle levels of the enterprise.
The analysis of the BPM concept shows that the main principle of its information technologies in the development of CIS for solving the tasks of PMO is top-down design. Analysis of the concept of S-BPM shows that the main principle of its information technology in the development of CIS for solving the tasks of PMO is an upward projection. Taking into account the positive and negative aspects of both design principles shows that the information technologies of the S-BPM concept cannot replace the information technology of the BPM concept. A rational solution that allows to increase the efficiency of the development of CIS for solving the tasks of PMO is the integration of BPM and S-BPM technologies. Such an information model is proposed in this article. It facilitates the joint work of specialists in various areas of activity and the adoption of objective decisions by the management of the enterprise
Keywords: : system analysis, BPM, S-BPM, corporate information system, decision-making.
TRAINING OF CONSUMERS GLONASS EQUIPMENT ON THE BASIS OF THE HARDWARE SOFTWARE MODELING COMPLEX NAVIGATION MONITORING SYSTEMS
FOR MANAGING MOBILE OBJECTS
O.I. Bokova, S.V. Kanavin, N.S. Khokhlov
The purpose of this article is to develop a methodology for effective training of users of GLONASS navigation and monitoring systems using a specialized hardware-software modeling complex based on an interactive training system, as well as a description of the structure and composition of the modeling complex. The realized interactive educational complex is viewed as a structure that includes components of the management system for mobile objects of the internal affairs bodies, as well as bilateral and multilateral ties between them. An interactive educational complex for training ATS employees includes knowledge bases for maintenance, logistics and repair of navigation monitoring systems, as well as a modeling part that allows to solve applied tasks related to monitoring and management of mobile assets. Technical support for the training and testing of students is realized with the help of hardware and software tools and multimedia programs that in an interactive mode allow creating an effective training system by interaction of the teacher as a subject of this system with another subject-listener. The formation of the optimal sequence of studying the components of educational programs is carried out as a controlled procedure for the solution of test tasks and appeals to the theoretical material of the electronic textbook. The training is carried out taking into account the adaptation to the individual traits of the trainee, the variability of the procedure for studying the training material, and the implementation of remote control at all stages of training.
Keywords: : interactive learning technologies, interactive educational complex, mobile management, knowledge bases, navigation-monitoring systems.
ECONOMIC-MATHEMATICAL MODELING OF THE HEALTH LEVEL OF POPULATION IN THE RUSSIAN REGIONS
The article considers the economic and mathematical tools for solving the problem of integrated assessment and raising the level of public health in the region. The main health indicators serve as influencing factors. Linear models of integrated health indicators are constructed on available statistical data of the population of the Russian Federation and the Volgograd region from 2000 to 2014. The dynamic task of increasing the values of the public health integral index in the Volgograd Region was formulated and solved. Basic health indicators are used as phase variables of the dynamic model, taken into account in constructing the integral index. Investments in the fixed capital of the region by main types of economic activity are control variables. The information basis is the data of the social and economic situation of the region for the last 15 years. The presented dynamic model allows to carry out a comprehensive assessment of the health of the population of the region in the current and forecast period. Some scenarios of increasing integral health level of the region under different investment capital restrictions were considered and results were analyzed. The proposed approach can be used to evaluate various options of the region development strategy. In the article, the presented model of the integral indicator of population health support a complex estimation of the level of regional development in the current period and can be considered as a tool of decision-making support at the multivariate scenario analysis of regional development strategies in health.
Keywords: : mathematical modeling, population health, integral indicator of health, dynamic programming, control problem, comprehensive health assessment.
PROBABILITY IDENTIFICATION OF AIR TARGETS S BY TWO-COORDINATE RADAR
V.M. Grinyak, E.G. Lavrushina, T.M. Grynyak
The paper is devoted to the problem of recognizing low-altitude low-speed air targets (helicopters) moving in the area of responsibility of onshore ship traffic control systems. The main information base of such systems is the two-coordinate radar of the circular survey. Separation from the array of observable objects of air targets requires the use of special procedures for processing information. In the paper, a mathematical model of the problem of observing air objects is formulated, based on equations of the “state-measurement” type and finite-dimensional representations of the least squares method. In view of the initial nonlinearity of the problem, it is proposed to linearize it about some support solution that characterizes the a priori ideas about the trajectory of the observed object. The main attention is paid to the problem of the boundaries of the solvability of the problem under conditions of instrumental measurement errors. The results of numerical simulation for typical situations are presented. It is shown that the proposed algorithm makes it possible to decide on the degree of belonging of the object to the air class, while the problem is solvable in ranges of height / range ratio that are acceptable for a wide range of practical fields.
Keywords: : traffic control, air target, altitude, observation, radar, probability.
MODEL OF INFLUENCE OF CYBERATTACKS TO FUNCTIONING OF CONTESTANT FIRMS
V.I. Novoseltsev, A.N. Noev, D.E. Orlova
The mathematical model allowing in quantitative expression to establish influence of mutual cyberattacks to economic efficiency of contestant firms is considered. The basis of model is worked out by Lotke-Voltaire’s made in the assumption the modified equations that change of economic efficiency of each firm in the absence of the competitor and, accordingly, cyberattacks, is described by the logistical equation. The qualitative method of differential calculus defines conditions at which observance, despite mutual attacks, competitors do not undergo economic bankruptcy, and continue to function in a normal mode. As the integrated indicator characterizing economic efficiency of contestant firms, the volume of the goods realized by them or the rendered services is applied. The model can be used for a substantiation of requirements to maintenance of information security of competing subjects of the modern market in the conditions of mutual cyberattacks.
Keywords: : cyberattack, mathematical model, economic efficiency, information security, stability.
NETWORK-BASED SIMULATION OF THE RESULTS MONITORING EVALUATION OF ACTIVITY OF UNIVERSITIES
Y.E. Lvovich, I.L. Kashirina, A.N. Schwindt
The article presents the results of neural network modeling of the interrelation between the indicators of monitoring the effectiveness of the activity of universities and monitoring of the employment of graduates. The proposed models provide an opportunity to predict the impact of certain indicators of the effectiveness of the university on changing conditions for the success of graduates and identify indicators that have the strongest impact on the effectiveness of the employment process. Since the employment of graduates is the resultant indicator of the educational activity of the university and one of the key indicators of its relevance, the problem solved in the article seems to be relevant. In the course of the study it was possible to build neural network models with a sufficiently high degree of reliability. At the same time, it was found that 57 indicators of monitoring the performance of HEIs are significant for forecasting the proportion of graduates who have found employment during the calendar year following the year of release, and only 3 monitoring indicators are significant for forecasting the average amount of monthly payments to graduates in the first year after graduation from the university effectiveness. Based on the results of the study, a conclusion was made about the impact of modeling results on the relationship between the indicators of employment monitoring and performance monitoring on adjusting management decisions and improving the educational activity of the university.
Keywords: : monitoring, evaluation, efficiency of the university, neural network, multilayer perceptron.