APPLICATION OF FUZZY ARTMAP NETWORK IN INTELLIGENT SYSTEMS OF INVASION DETECTION
The article deals with the organization of intelligent intrusion detection and detection systems. Research in the field of development of information security tools shows that today the most promising and flexible solutions are based on machine learning methods that can prevent damage from intrusions that were not noticed by standard means of combating computer attacks. In the proposed approach, it is proposed to use a sequential reverse search with a return to select significant features and the Fuzzy neural network ARTMAP to detect and diagnose attacks. Network Fuzzy АRTMAP is able to adapt to the dynamics of computer attacks and allows you to recognize intrusions in the information system in real time, without the need to load datasets in batches. This makes it possible to automate the analysis of safety protocols in a continuous mode. The extensive use of ART family networks in intrusion detection tasks makes it possible to consider the search for approaches that improve their performance. In this paper, the control hyperparameters network Fuzzy ARTMAP proposed to adjust automatically with the use of a genetic algorithm According to the results of the computational experiment, the reduced set of characteristics reduces the computation time by 21%. The accuracy of the classification algorithm was 100% and 99.89% for the detection stage and the diagnostic stage, respectively.
Keywords: neural network, Fuzzy ARTMAP, genetic algorithm, intrusion detection, intelligent information security systems.
FUZZY COGNITIVE MODELING OF DEMAND CONTROL SYSTEM FOR EXPRESS LOANS
G.I. Goremykina, N.A. Shchukina
One of the main ideas to achieve the banks highest efficiency is the introduction of innovative tools considered. Intellectualization of mathematical modeling and, in particular, fuzzy cognitive approach allow to carry out intellectual decision-making process. This process give the chance modeling the person reasoning and consider his cognition. The article proposes a fuzzy cognitive approach to modeling the Express loans demand and its management system. The modeling system is represented as the fuzzy weighted oriented multigraph with transmitted impulse transmitted. The system model is implemented in the form of sequential execution of the following stages: the purpose definition; the fuzzy cognitive map construction; dynamic modeling using the impulse processes; the scenario analysis situation and the choice of the best. The program decision support system “Quill” as computer modeling tool is used. The developed model of the management system serves as the basis for the trends analysis in the development of various situations that arise during the banks work in Express loaning. It allows to predict and model behavior strategies in response to external influences, as well as to determine the management paths that allow to increase the Express loans demand.
Keywords: fuzzy cognitive modeling, Express loans, fuzzy weighted oriented graph, control system.
APPLICATION OF THE WEAKLY-MANIPULATED GROUP PROCEDURES OF MAKING A CONSENSUAL DECISION IN PROJECT MANAGEMENT
In this article have been described the procedure that increase convergence of actual and planned variants of the execution of project. For this purpose, the decision maker (DM) engage the council of experts under him, who, develops and offers him a single consensual decision for the most appropriate requirements of the DM and implemented, from the point of view of experts, the realization of the project. The purpose of the procedure is to reduce the possibility of manipulating the decision-making process through the use of special mechanisms of the theory of active systems and the voting procedure, encouraging experts to offer a qualitative decision, аnd agents to execute it. Open quantitative criteria are used in the process of developing and making a group decision, which increases the transparency of the process. This procedure is supporting decision-maker in the decision-making process by offering him one best solution from all the many alternative solutions worked out by the group members. The author offers the mechanism that is harmonize interests of DM, agents and experts by synchronizing targets functions of named subjects in that way so it will be profitable for experts to offer the qualitative decisions and will not try to manipulate, and for agents to choose more difficult plan.
Keywords: non-manipulability, group decision-making, project management, theory of contracts .
ANALYSIS OF THREATS TO INFORMATION SECURITY WHEN THE MANAGEMENT OF FUNDS USING MOBILE DEVICES
A.G. Aleksandrov, S.G. Klyuev, E.S. Polikarpov, M.A. Ledovskaya
The issues of using mobile applications, mobile communication devices as a means of committing theft of funds from electronic bank accounts, balance funds of mobile accounts are investigated. In the article methods of committing money thefts from a settlement account through the “Mobile Bank” are considered. The way of committing the theft of funds from an electronic account using malicious software was investigated. The Trojan program used by attackers was distributed via SMS-mailings, in which there was a link to downloading a malicious program under the guise of licensed software, during the installation of which administrator’s rights were requested, also links to the installation of the Trojan program came via instant messengers and personal messages on social networks, and Also, they were placed on the walls of users of social networks. The method of committing theft of funds from an electronic account using SMS banking is considered. It is a procedure for transferring money by sending a specially generated SMS to the bank number. One of the new types of fraud using the capabilities of mobile communications, namely USSD codes, has been investigated. The user of the cellular network was informed of the mobile phone check and is asked to dial the USSD code, if this request is made by the “cellular operator”, scammers get access to the SIM card, which allows them to make virtually any actions: make calls at the expense of the subscriber, access to the mobile bank.
Keywords: mobile applications, theft, mobile banking, SMS banking.
CONSTRUCTION OF GEODESIC LINES APPLIED TO THE PROBLEM OF PERSECUTION IN THE SYSTEM OF COMPUTER MATHEMATICS «MATHCAD»
A.A. Dubanov, M.N. Bildushkina
This article deals with the modeling of geodetic lines, with respect to the pursuit problem. When predicting the trajectory to the prospective location of the object of pursuit, it is preferable to use geodetic lines. For this, a local dynamic coordinate system is selected. The abscissa of a given coordinate system is a line belonging to the horizontal plane of projections and connecting the horizontal projections of the pursued point with the pursuing point. When solving a boundary problem with given boundary conditions in the form of the coordinates of points, the “shooting” method was used. To do this, a series of “shots” is produced from the haunting point in a given range of angles. Based on the results of a series of “shots”, an interpolating curve is constructed, where the argument is the angle from the specified range, and the value is the minimum distance to the point of pursuit from the trajectory points. Further, by built-in means of computer mathematics systems, an angle is sought such that the minimum distance to the point of pursuit from the points of the trajectory is zero. As a programming environment, for clarity, the computer mathematics system “MathCAD” was chosen. The system “MathCAD” allows you to quickly and clearly make animated images, which allowed the results of the program to be placed on the channel “Youtube.com”.
Keywords: pursuit problem, pursuit object, pursuit object, horizontal projection of the velocity vector, surface equation, Christoffel symbols, local coordinate system, boundary conditions, shooting method.
FUZZY MATHEMATICAL MODELS FOR PREDICTION AND EARLY DIAGNOSIS OF OCCUPATIONAL DISEASES OF AGRICULTURAL WORKERS IN CONTACT WITH PESTICIDES
F. A. Surkov, N. V. Petkova, S. F. Sukhovskiy
This article deals with the problem of forecasting prices for real estate in the long and medium term for management decisions. The real estate market is one of the most dynamic areas of the Russian economy. Rapidly changing factors and price dynamics require a thorough study of new advanced methods using innovative technologies. Forecasting is an integral part of the mass valuation of real estate, it is impossible to plan future expenses or to build economic development plans. The price situation described by the average prices in the residential real estate market is a fundamental object for evaluation and forecasting in the study of the residential real estate market. Based on average prices, prices are managed in the residential real estate market. These indicators are considered when forecasting the market price of real estate, which is important in the development of the subjects of the real estate market auxiliary techniques for the selection of strategic actions for the development and improvement of the housing sector. Mass valuation of real estate as a complex system requires not only the definition of the parameters characterizing the price of real estate, and the identification of dependencies that link these parameters, but also the construction of a forecast of real estate prices in the future. Market conditions are constantly changing, and time has a direct impact on all market processes and decision-making. Seasonal calibration of prices for real estate objects is executed. The idea of using artificial neural networks that meet the modern requirements of real estate valuation is analyzed and proposed. A mathematical model based on harmonic series (Fourier series) and a neural network model are constructed and analyzed. A comparative analysis of the growth trends in the value of real estate.
Keywords: time series, real estate valuation, Fourier series, statistical methods, artificial neural networks.
FUZZY MATHEMATICAL MODELS FOR PREDICTION AND EARLY DIAGNOSIS OF OCCUPATIONAL DISEASES OF AGRICULTURAL WORKERS IN CONTACT WITH PESTICIDES
N.A. Korenevsky, R.V. Stepanov, R.A. Krupchatnikov,
V.V. Aksenov,N.L. Korzhuk
The work is devoted to solving the urgent problem of improving the quality of medical care for workers of agriculture in contact with agricultural chemicals. In the course of the research it was shown that the problem of forecasting and early diagnosis of occupational diseases of agricultural workers employed in crop production belongs to the class of poorly formalized problems with fuzzy data structure, which served as the basis for the choice as the basic apparatus of research methodology of synthesis of hybrid fuzzy decision rules. During the synthesis of fuzzy decision rules, it was found that in order to achieve high quality of decision-making, in addition to risk factors associated with pesticides, the level of psycho-emotional stress, fatigue and ergonomically defective agricultural machinery, environmental risk factors, individual characteristics of the body, etc. should be used as informative features. As a concrete example, the variant of application of the proposed method and information-analytical model in the synthesis of models of forecasting and diagnosis of diseases of the nervous system from the effects on the human body of nitrates-containing pesticides is described. In the course of mathematical modeling and expert evaluation it was shown that the confidence in the decisions exceeds the value of 0.85. The practical application of the proposed method and models will improve the quality of medical services to employees of agriculture providing an increase in working age and reduce disability.
Keywords: agro-industrial complex, occupational diseases, forecasting, early diagnosis, fuzzy hybrid models.
ANALYSIS OF ALGORITHMS FOR DETECTING MOVING OBJECTS IN THE VIDEO IMAGE
V. V. Bernikov, A. P. Preobrazhenskiy, O. N. Choporov
The problem related to the detection of objects on video images, has many practical applications related to security issues, information processing in virtual reality, management of mobile robots, etc. The paper considers the most frequently used methods of allocation moving objects in relation to video sequences obtained from household cameras in the presence of noise in images. The main features of object detection are shown. The characteristics of the main methods used for the analysis are described: the method of background subtraction, the method of time difference, the method of optical flow. The main problems of processing video sequences are identified, the impossibility of using classical methods is described, and ways to improve the quality of moving objects are proposed. The table of comparative analysis of methods is given: time spent on calculation, accuracy of detection, advantages and disadvantages. There is also a table comparing the success of methods when detecting objects, which specifies the percentage of successful object definition at a given video resolution and a certain environment. It has been demonstrated that video resolution has a noticeable effect on the success of the detection of moving objects, as the higher the resolution, the more preliminary information for processing the algorithm has in each frame.
Keywords: video modeling, optical flow, object detection, processing of the frame, video sequence.
DEFINITION OF THE COEFFICIENTS OF THE MATHEMATICAL MODEL OF QUALITY MANAGEMENT OF TRAINING BY THE METHOD OF LINEAR PROGRAMMING
V.I. Sumin, L.D. Kuznetsova, M.A. Lukin
This article examines the process of analyzing the level of quality of education in a higher educational institution. This problem was solved on the basis of using problem-oriented components of the educational process management system of the higher educational institution. To form problem-oriented components of the educational process management system of a higher educational institution, it is necessary to develop a model and algorithm for the process of making managerial decisions in it. Formalization and typification of educational information is carried out, which takes into account the time and indicators of the evaluation of the effectiveness of the quality management of training. Formed sets and sequence of a set of actions on the information that is used in the management of the quality of training. The processing time of elements of educational information in a higher educational institution is considered known on the grounds that it is regulated by normative documents. An evaluation of the duration of the step of taking managerial influences is determined on the basis of a certain set of procedures that in a certain sequence process the educational information of a higher educational institution. The coefficients of importance of the elements of providing information that determine the formation of managerial influence are determined. The procedures for providing information perform functions: determining parameters for a particular procedure, selecting and arranging the selected information, developing mathematical models. A mathematical formulation of the problem is defined in a general form, which allows us to formalize the task of optimizing the management impact, which is used in the management of the quality of instruction using the linear programming method.
Keywords: predicate, predicate significance, variable-valued logical function, logical neural network, cognitive map, cluster analysis, neural network.