Abstract: the article describes a method of determining the parameters of Mamdani fuzzy inference system based on its identity with the Takagi-Sugeno system. The author substantiates the properties that can be used as universal apprximators for both systems. The article introduces an algorithm of formation functions of membership of the right-hand parts of the Mamdani rules and the method of formation of the system as a whole.

Keywords: Software, fuzzy, logic, Mamdani, Takagi, approximator, Sugeno, automatization, identity, output.

Abstract: the article deals with the problem of decomposition of simulation models for organization of the distributed modelling of complex systems on multiprocessor computing systems. To speed up the process of modelling the modelling program shall be divided into parts for parallel execution on different processors. The author offers the approach to the use of an automatic classification method for automation the parallelization of simulation programs.

Keywords: Software, simulation modeling, complex systems, multi-processor computing systems, decomposition of simulation model, automatic classification, distributed modeling, acceleration of computation, parallel computing, modeling programs.

Abstract: the article is devoted to a topical issue of development of the education in the field of the supercomputer systems, raises questions and suggests constructive solutions for building multiprocessor computation clusters as the initial phase in the realization of program of training specialists in the area of high performance computing. Author gives an example of building a cluster on the specific equipment and shows the results of testing the cluster during the program of modeling of distributed automated control system.

Keywords: Software, supercomputing technology, computing clusters, high performance computing, parallel programming, specialization on parallel computing, mathematical modelling, numerical experiment, mass parallelism.

Abstract: the article describes the method of calculation of buffer storage capacity of commutation nodes for computer network that does not require setting the exact values for functions of distribution of incoming messages flow and duration of its processing. The proposed method makes it possible to calculate the required value of the buffer storage capacity using the average value of the intensity and duration of the incoming flow of messages.

Keywords: oftware, computer networks, switching systems, the probability of message loss, buffer storage, information packets, the intensity of flows, packet handling, overflow, rectangular pulses.

Abstract: forecasting is one of the main issues in the analysis of the time series. The goal is to determine future behavior of a time sires by its know past values. In this article the author proposes a method of time series prediction based on the idea of allocating basic patters (templates) from the input data allowing to define the internal rules of the studied series. Currently on of the approaches in the field of time series prediction is the Data Mining (or “data excavation”) system. This is due to the fact that classical methods, based only on the linear (ARIMA) and non-linear (GARCH) models of prediction can’t provide the required accuracy. Usage of the methods developed with this technology makes it possible to increase the performance of prediction and reveal hidden patterns in the studied time series.

Keywords: Software, time series, approximation, piecewise-linear approximation, forecasting, data excavation, basic patterns, patterns, local extremes, algorithm.

Abstract: the article suggests a new way to automate the search of anomalous zones in the structure of the under sleeper pad base of the railway through the search of anomalous zones with the upper track structure examination during the overall control and diagnosis of the railway based on the building a model using the GPR radarograms representation. The proposed method is based on the article devoted to the methods of search for the anomalous zones, that points out the need of finding a connection between anomalous data and describing them in a unified mathematical representation model. This method is presented as a description of the mathematical model made up of mathematical models of all anomalous axes of phase synchronism obtained by earlier studies of the ballast railway. The method can be used to automate the classification of data on the ballast railway structure, not previously investigated, and in using data about the structure of the known railway track sections.

Keywords: Software, ground penetrating radar, georadar, layer, radiogram, track, method, model, anomaly, vector.

Abstract: The author focuses on the special aspects and algorithms of automatic generation of a parametric model of a non-parametric description of the drawing based on the adaptive core network of the drawing that changes depending on the size values used. Adaptive network serves as an effective universal parametric model of the drawing as it applies to the entire drawing and therefore to the all important points of the basic graphic primitives, that defines the shape of the item shown in the drawing. At the same time all elements of the drawing specification (various technological keys) are indirectly related to that network. This allows to automatically build almost complete design drawings of modified items. Building of the adaptive core network depends only on the basic graphical elements, view and sizes used. It is not depended on the order and way of formation of graphic primitives (the algorithm of constricting the item), and time and means of dimensional notating of the drawing. That makes it possible to use such network to automatically generate the parametric description of almost any design drawing previously build in the non-parametric systems. It requires only clear dimensional notation for the shape of the item, i.e. the original drawing must meet the requirements of “Unified system for design documentation” allowing to produce the item. The software systems based on the adaptive network may find wide use in the development departments of engineering design offices and businesses.

Keywords: Software, parameterization, adaptation, basic, network, drawing, type, model, algorithm, relation.

Abstract: the authors rise a problem of finding the optimal binary aperiodic sequences for the target detection tasks. The article presents an algorithm for a complete search “brunch and bound”, introduces a concept of equal transformations, describes it use for computational complexity reduce. The methods of optimization lower the computational complexity of the algorithm through to the usage modern processor instructions, computational graphic clusters, parallelization, batch search.

Keywords: Software, binary sequences, aperiodic sequence, optimal sequence, pulse autocorrelation function, methods of optimization, brunch and bound, NVidia CUDA, equivalent sequences, Barker codes.

Abstract: the article considers the application of learning management systems to the disciplines that require the student to write programs of various complexity for learning the studied material. The aim of the article is to demonstrate the use of the Moodle elements for carrying out practical works in such disciplines. “System software” and “Computer graphics” courses serve as an example. The author proposes several approaches to the organization of evaluation of programming assignments.

Keywords: Software, Moodle, teaching of programming, learning tools, e-learning, learning management system, student, programming, system software, computer graphics.

Abstract: the article reviews a technique of designing the knowledge base oriented neural networks represented by semantic networks. The technique is based on the appliance of a unified model of a neural network. A distinctive feature of the proposed design technique for processing the knowledge bases is in usage of a component approach and the libraries of compatible components of neural networks to reduce the labor contribution during the development, decrease the requirements for the qualification of developers and solve the problem of integration of neural network specific methods with other methods of representation and processing data in the development of hybrid intellectual systems.

Keywords: Software, hybrid intelligent system, knowledge base, semantic network, model, neural network, method of design, component, library, specification.