TECHNIQUE OF MULTI-CRITERIAL ASSESSMENT OF COMPETENCE IN THE TASK OF FORMATION OF WORKING GROUPS FOR IMPLEMENTATION OF UNIQUE PROJECTS
N.A. Aleynikova, G.V. Shurshikova
The task of multi-criteria evaluation of the competencies and potential of the employees of the organization is investigated with a view to further distributing them among the works with the greatest efficiency. We believe that the work (tasks) are performed in the framework of a unique project. It is necessary to choose mathematical tools for the formalization of the task of selecting employees, since their competences and potential are evaluated according to a set of qualitative criteria, to develop a methodology for managing working groups. As a basic model for the optimal distribution of employees by work, it is proposed to use the assignment task model. The coefficients of its objective function, which are integral assessments of employees’ competencies, are proposed to be determined using the hierarchy analysis method (AHP). AHP allows you to create a clear structure linking the tasks within the project, the employees and the competencies that they should have, for finding the weights of the employees relative to each task. In the framework of the AHP, there is a problem of inconsistency of matrices of pairwise comparisons, which does not allow to get adequate weights for employees and, of course, correctly evaluate the coefficients of the objective function in the assignment problem. To overcome the inconsistency problem, it is proposed to use the mathematical apparatus of tropical (idempotent) mathematics. Tropical Mathematics also provides relatively simple finite formulas for determining the weight vector of parameters to be estimated. A methodology for multi-criteria competence assessment in the task of forming working groups for the implementation of unique projects was developed. The implementation of the stages of the technique is considered by example.
Keywords: :assignment problem, expert estimation methods, hierarchy analysis method, tropical (idempotent) mathematics.
SYNTHESIS OF LINEAR REGRESSION MODEL AND EIV-MODEL
M. P. Bazilevskiy
This paper is devoted to a synthesis of pair-wise linear regression model and simplest EiV-model (Errors-In-Variables model), better known as the Deming regression. The EIV model is a regression in which all variables contain random errors. Such models have a number of significant drawbacks, which makes it difficult to work with them. The synthesis proposed in the paper, called the two-factor model of a fully connected linear regression, is not only devoid of these shortcomings, but also has certain advantages. The main stages of the construction and analysis of two-factor models of fully connected linear regression are considered. The proposed fully connected linear regression model has much in common with the classical multiple regression model; however, these two types are based on completely different approaches. If multiple regression is based on the principle “independent variables affect the dependent one”, then the principle of fully connected regression is “all variables influence each other”. It is established that the approximation abilities of fully connected models do not exceed the capabilities of multiple regressions, but the former have a much more diverse interpretation. The developed synthesis can be used in the construction of multiple models as a tool for solving problems of reducing the dimensionality of data, eliminating multicollinearity and selecting informative regressors.
Keywords: :regression model, ordinary least squares, total least squares, Deming regression, EIV-model, fully connected linear regression model.
MANAGEMENT OF FUNDS ALLOCATION OF AN EDUCATIONAL
The article presents the expert optimization approach to improving the efficiency of funds allocation management in an educational organization, which is a combination of intelligent technologies, analytical and numerical methods. It is suggested that managerial decisions should be focused on the objectives of funds allocation and development strategy of the educational organization. Achievement of these goals is provided by the use of expert-optimization approach in the tasks of funds allocation between the budgeting objects. The functional funds allocation among school business processes is carried out with the use of an expert knowledge model of transforming the results of a SWOT analysis of building membership functions of vague relationships. The budget allocation of income and expenses between the centers of financial reporting is implemented on the basis of expert assessment with the use of linguistic variables and a formalized model of multi-alternative optimization. For the allocation of the investment budget among the educational organization development projects, a preliminary expert analysis of management accounting mechanisms with a transition to the multi-alternative optimization task is used.
Keywords: :management, funds allocation, expert-optimization approach, linguistic variables, management accounting, multi-alternative optimization.
TELECOMMUNICATION TRAFFIC ANALYSIS USING ORANGE ANALYTICAL SYSTEM
S.V. Palmov, A.A. Diyazitdinova, O.Y. Gubareva
To simplify the task of ensuring information security is possible through data mining usage. This technology can be used to predict attacks on the information systems. Decision tree is one of the effective tools for predictive models building. Orange is an analytical system that contains a large number of data mining algorithms, including a decision tree. With help of the system made an analysis of real data on network attacks obtained during the experimental study, with the aim of predicting DDoS attacks. Five metrics were used to assess the quality of work: accuracy, specificity, precision, recall and F-measure. The results of the analysis are presented in tabular form. The results were compared with the forecasts created by iWizard-E, an intelligent decision support system using a modified decision tree algorithm. iWizard-E surpasses Orange in the first three metrics, but inferior in the last two. The implementation of this algorithm in the Orange and iWizard-E systems cannot be applied to analyze the data of the above type, since they form forecasts with low reliability. It is necessary to improve the decision tree aimed at improving the quality of the generated prognostic models in the context of increasing the values of the “completeness” metric.
Keywords: :artificial intelligence, data mining, Orange system, decision making, traffic, F-measure.
METHOD OF AUTONOMOUS CORRECTION OF INERTIAL NAVIGATION SYSTEM OF UNMANNED AIRCRAFT ON THE BASIS OF MODERN GEOINFORMATION TECHNOLOGIES
A.V. Sizov, S.V. Ippolitov, A.Y. Savchenko, V.A. Malyshev
The method of correction of inertial navigation system based on modern geoinformation technologies with the use of optical-electronic system and electronic terrain map, allowing determining the coordinates of the location of the unmanned aircraft in offline mode without the use of satellite and radio navigation, is developed. In this case, the current coordinates of the unmanned aircraft are determined with the help of inertial navigation system. Then these coordinates, taking into account the error accumulated after the last correction of the inertial navigation system, are entered into an electronic terrain map. Thus, the boundaries of the working area of the electronic terrain map are determined, which significantly reduces the computational cost. The correction of the current coordinates of the location of the unmanned aircraft from the optical-electronic system is carried out by two types of data – the geographical coordinates of the three known landmarks (identical points) of the area and the coordinates of the position of the unmanned aircraft relative to these landmarks (relative coordinates – range, height and lateral deviation). Determination of geographical coordinates of three identical points is made in the electronic terrain map on the basis of recognition of the received by the optical-electronic system image. The calculation of the relative coordinates of the unmanned aircraft is carried out by the triangle method with the circumscribed (inscribed) circle (sphere), the vertices of which are three identical points, with the determination of their coordinates in the associated coordinate system of the unmanned aircraft as a result of the corresponding image processing by the optical-electronic system.
Keywords: :inertial navigation system, optical-electronic system, electronic terrain map.
APPLICATION OF FUZZY LOGIC IN THE SYSTEM OF AUTOMATIC CONTROL OF PNEUMATIC GUN SHOOTING DURING FIRE FIGHTING
A.B. Migranov, I.S. Maksyutov
The article describes the obtaining of mathematical model of technical object aircannons on the basis of methods of fuzzy logic. This topic is very relevant, because at the moment none of the existing automatic fire extinguishing systems does not provide a quick and effective elimination of fire with minimal losses. As a device for obtaining information, a thermal imager is used, which records an increase in temperature in the event of a fire and a drop in temperature in the event of a projectile entering the flame core. When the maximum value of temperature there is a change in the values of the launch angle and the control signal, adjusts the value of the pressure exerted on the projectile. Based on the formula for calculating the trajectory of the projectile, logical rules are drawn up, in which the input data are the launch angle and pressure, and at the output – the distance that the projectile will fly. The paper analyzes the characteristics of the behavior of the projectile and the result of its hit the target. On the basis of methods of fuzzy logic control system determines the area of the fire or maximizing the temperatures and calculates the rotation of the gun and distance for firing a projectile. For fire extinguishing installations (air guns) it is proposed to use an automated fire extinguishing control system based on the developed fuzzy rules.
Keywords: :fuzzy logic, fuzzy system, air gun, fire fighting.
MULTILEVEL ARCHITECTURE OF AN INTELLECTUAL MANAGEMENT DECISIONS SUPPORT SYSTEM IN RESOURCES SUPPLY SYSTEMS OF INDUSTRIAL PRODUCTION
A.A. Sokolov, A.P. Tyukov, M.V. Shcherbakov, T.A. Janovsky
This article discusses the problem of providing information about energy resources consumption and distribution at an industrial machine-building plant for decision makers on energy resources procurement that keep records of energy resources consumption. The purpose of the providing is to improve the accuracy of energy resources costs planning and decision-making support in energy efficient technologies choice to minimize energy consumption. This problem is solved by using an integrated solution. The architecture of this solution is presented. It includes: (1) an energy distribution model; (2) a method of synthesis the data collection network topology for fast implementation of the data collection process to supplement the model with missing data; (3) a data quality assessment method based on decision trees; (4) a method of decision-making support in choice of new equipment to reduce energy resources consumption. The prototype of the proposed solution that implements the proposed architecture was tested at the Volgograd hardware plant and other enterprises.
Keywords: :architecture of energy management system, decision support, energy management, energy efficiency, industry, data collection.
THE ALGORITHM OF CORRECTION OF THE INERTIAL NAVIGATION SYSTEM OF THE UNMANNED AIRCRAFT ON THE BASIS OF THE OPTICAL-ELECTRONIC SYSTEM AND THE ELECTRONIC TERRAIN MAP
A.V. Sizov, S.V. Ippolitov, A.Y. Savchenko, V.A. Malyshev
The paper presents an algorithm of correction of the inertial navigation system of an unmanned aircraft based on the usage of an optical-electronic system and an electronic terrain map, which will provide high accuracy of determining of the navigation parameters, the speed of the correction system, small size, cost and also autonomy of work. This algorithm implements a new method of correction of the inertial navigation system based on the developed mathematical model describing the procedures for solving navigation problems: determining the relative coordinates of three identical points (landmarks on the ground) in the coordinate system of the optical-electronic system associated with the unmanned aircraft; recalculating of the obtained relative coordinates with the help of the matrix of guide cosines into the geographic coordinate system; determining the geographical coordinates of identical points from the electronic terrain map; calculation of the current geographical coordinates of the unmanned aircraft on the basis of its relative coordinates and geographical coordinates of identical points. The solution of the described problems is carried out by the developed algorithm, the final step of which is the input of the current geographical coordinates of the unmanned aircraft into the inertial navigation system for its correction.
Keywords: :inertial navigation system, optical-electronic system, electronic terrain map, unmanned aircraft.
ALGORITHM FOR ADDING TURBOVINET EFFECT
The article discusses the occurrence of noise components from rotating structural elements of the aircraft or turboprop components and the effect of these components on the radio signal tracking aerodynamic object. The masking effect of signals from rotating elements affects the observation of the glider component, which interferes with the tracking of the object. The need to suppress the turboprop components in the radio signal is noted. To solve the problem, it is proposed to use fractal signal processing methods. An algorithm for suppressing turboprop spectral components in an echo signal of an aerodynamic object, based on the definition of the similarity function, is proposed. The article describes the steps of the algorithm and its block diagram. An example of a signal from a bank of temporal functions of micro-movements of an object’s structural elements, used as a basis for approximating the initial echo signal, is given. A simulation was performed for a single aerodynamic object, confirming the suppression of the turboprop component of the echo signal. The proposed algorithm is proposed to be used to classify the number of objects in a swarm of unmanned aerial vehicles. The necessity of decreasing the interval of discreteness of the parameters describing the kinematics of the object’s micro-movements is noted. The materials are of practical value in radiolocation when accompanied by unmanned aerial vehicles to eliminate interfering components in the far-Doppler portrait of the object, automatic coordination, navigation, and increased flight safety.
Keywords: :turboprop component, glider component, micromovement, echo signal, spectrum, radar, Doppler.