Category Archives: Issue # 2(17)

THE SHORTCOMINGS IN THE USE OF ARTIFICIAL NEURAL NETWORKS FOR SOLVING PROBLEMS OF BINARY CLASSIFICATION

UDC 681.3

N. I. Murashkin, V. N. Kostrova

The article aims at identifying problems of the use of artificial neural networks for solving problems of binary classification. For solving problems of binary classification it is expected to classify samples that are already available to a certain class. A leading approach to the study of this problem is the algorithm of Levenberg-Marquardt, which allows to optimize the parameters of nonlinear regression models. As optimization criterion is adopted to the root mean square error of the model on the training set. It is proposed to accelerate the computation to apply the method to the elastic distribution. The materials of the article are of practical value to professionals who use artificial neural networks for classification tasks.

Keywords: binary tasks, artificial neural networks, algorithm, algorithm of Levenberg-Marquardt, algorithm of Gauss-Newton, method of M. Riedmiller and G. Brown.

Full text:
MurashkinKostrova_2_17_1.pdf

THE DESIGN CALCULATION METHOD OF WIDEBAND INTERFERENCE LASER PLATES POLARIZERS

UDC 535.345.67

L.A. Gubanova, D.N. Perevozkin

The interference plates-polarizers are widely used in optical devices, in particular, they are used in electrooptical Q-switches of pulsed solid-state lasers. The standard all-quarter-wave construction of the interference layers of the polarizer plates is characterized by a narrow band of the working spectral range, which does not fully correspond to modern requirements. A method is proposed for calculating the practically feasible designs of broadband interference polarizer plates, based on the alignment of the thicknesses of the layers included in the non-quarter-wave structures, synthesized using widespread computer software for the calculation of interference optical coatings.

Keywords: optical interference polarizer, polarization contrast, porous multilayer interference coating, OptiLayer, optimization.

Full text:
GubanovaPerevozkin_2_17_1.pdf

THE SIMULATION OF THE SCATTERING OF PULSES OF RADIO WAVES ON HOLLOW STRUCTURE

UDC 621.396

V. V. Kostyuchenko, N.A.Ankina

On the basis of the method, allowing a numerical solution of the full system of Maxwell’s equations, carried out the study of the scattering of a pulse with nanosecond duration of the three-dimensional hollow structure of rectangular cross-section. The calculation of the shapes of the reflected signals for different ratios between the spatial lengths of the pulses and the size of the diffraction structure. It was demonstrated that the value of the effective area of the scattering hollow structures with sizes close to the spatial length of the radar pulse, will be about the same as in the case of scattering long (monochromatic) pulses.

Keywords: momentum, scattering, hollow structure, Maxwell equations, finite difference method in the time domain.

Full text:
KostyuchenkoAnkina_2_17_1.pdf

THE SIMULATION OF SCATTERING OF ELECTROMAGNETIC PULSES ON THE SURFACE OF THE COMPOSITE IMPEDANCE OF THE CYLINDER

UDC 621.396

V. V. Kostyuchenko, V. N. Kostrova

This paper considers the problem of scattering of electromagnetic impulse on the composite dielectric cylinder having upper and lower half-planes different values of impedance. The excitation of the cylinder is based on third-party third-party source, which are infinite along the sides of the thread. On the basis of Maxwell’s equations, the wave equation is derived. Determined green function of the composite impedance of the cylinder. Derived the expression for the impedance boundary conditions on the surface of the cylinder. The calculation of the magnetic component of the electromagnetic field in the far zone, depending on time for different values of the impedance cylinder.

Keywords: electromagnetic wave scattering, impedance cylinder, momentum, wave equation.

Full text:
KostyuchenkoKostrova_2_17_1.pdf

RESEARCH OF THE EFFICIENCY OF THE GENETIC ALGORITHM WITH VARIOUS
METHODS OF SELECTION, CROSSOVER TYPES AND STRATEGIES OF FORMATION OF GENERATIONS IN SEARCHING OF EXTREMUMS OF TEST FUNCTIONS

UDC 004.023

V.S. Maraev, E.A. Bezzubenko, D.A. Cherkashin, A.S. Mihalev

In this article the analysis of materials on genetic algorithms is carried out. The main ideas and principles underlying work of genetic algorithms are considered. The basic stages of the classical genetic algorithm work are analyzed in detail. The review of the most common methods of selection (roulette and tournament), types of crossover (single-point and uniform) and strategies of formation of generations (classical and elitist) is executed.
On test functions the research of genetic algorithm with different methods of selection, types of crossover and strategy of formation of generations is carried out. For each type of algorithm, an estimate of the probability of finding a true solution is given. The received results of the experiments are carefully analyzed. The advantages and disadvantages of different methods of selection, types of crossover, strategy of formation of generations are revealed. The recommendations on the expediency of using genetic algorithms in various situations are stated. The possible directions for further research are defined.

Keywords: genetic algorithm, global extremum, population, generation, selection, crossover, De Jong’s function, Rosenbrock’s function, Rastrigin’s function.

Full text:
MaraevSoavtors _2_17_1.pdf

DEVELOPMENT OF THE GROUP EXCURSION TOURS INFORMATION ACCOUNTING SYSTEM

UDC 004.9

K.A. Makovy, A.N. Zelenina, R.R. Shishkin

The urgency of travel agency and tour operator activity automation as well as the problem of information component of their organization are indicated. The model of the subject field of the tour agency activity on the organization of group excursion tours is offered, the structure of the information system is described, and the structure of the database of the information system is proposed.

Keywords: information system, children’s tourism, automation of travel agency.

Full text:
MakovyZeleninaShishkin _2_17_1.pdf

THE USE OF MULTI-CRITERIA APPROACH IN THE ANALYSIS OF ALTERNATIVE ENERGY SOURCES

UDC 681.3

A. P. Preobrazhensky

This paper is devoted to consideration of the objectives related to the optimal choice of parameters controlled in the systems of electric power generation. We discuss the possibilities for the application of the main criterion for the case of multicriteria optimization of the process of electricity generation based on alternative sources. Refers to the need to focus on the Pareto set. Indicated that one of the solutions to a multicriteria problem can be a combination of goal programming, and narrowing the scope of trade-offs involving data, what is the relative importance of the criteria. The use of simplifications when there is a formation of Pareto-optimal solutions for specific processes of power generation based on alternative sources can be considered as an important task, to ensure that its consideration has been reduced and time costs to a reasonable level.

Keywords: optimization, renewable energy, multicriteria approach, function, method, algorithm, parameter.

Full text:
Preobrazhensky_2_17_1.pdf