articles
|
№ 2(80)
27 april 2019 year
Rubric: Algorithmic efficiency Authors: Dli M. I., Puchkov A., Rysina (Lobaneva) E. |
Algorithms of visualization of numerical data characterizing the state of objects and systems of various
nature with the aim of finding hidden patterns in them using convolutional neural networks are presented.
The algorithms used methods for obtaining images from numerical data on the basis of the discrete
Fourier transform of time series fragments, as well as on the basis of the application of visualization
using three-component system diagrams, if such a three-component representation of the system is
possible. The software implementation of the proposed algorithms was performed in the Linux environment
in the Python 3 language using the Keras open neural network library, which is a superstructure
above the TensorFlow machine learning framework. For the learning process of the neural network, a
Nvidia graphics processor was used that supports the technology of the CUDA parallel computing software
and hardware architecture, which significantly reduced the learning time. The proposed approach
is the recognition States of the objects according to their visualized data are based on the recognition of
no boundaries or forms of the figures in the images and their textures. Also presented is a program that
generates sets of images to implement the process of learning and testing convolutional neural networks
in order to pre-tune them and assess the quality of the proposed algorithms.Keywords: Internet, Internet
security, parental control applications, user security, information security, Internet threats.
Continue...
|
|---|---|
|
The article describes the problems of scheduling systems development. The authors demonstrate complexity
of feasible schedules generation for comprehensive technological databases. The study concluded that
the task belongs to the class of non-polynomial complexity. The article formalizes the task to plan as a single
mathematical model. Particular emphasis was placed on the fact that the mathematical model should have
the property of practical problem solving. The main task is to minimize the project development time, and
the main goal is to uniform loading of each resource in a complex system. This article proves that exact solution
of mathematical optimization is not effective since it demands huge amount of computational resources.
Authors demonstrate that genetic algorithm implementation allows to find approximate feasible solution. The
authors concluded that it is acceptable to use hybrid algorithms to solve the problem. It is proposed to use
heuristic methods to further improve the resulted mathematical model. Article also demonstrates how these
modules are integrated into technological data visualization systems developed by them. The PrPlan software
package allows interacting with existing systems in the enterprise and includes process data uploading interfaces.
It can group process operations of the same type and ensure generation of technological solutions based
on prototypes. The developed mathematical model and software will significantly optimize the technological
processes in production and ensure a high level of stability in the performance of each operation. It enforces
a significant economic growth and increase the efficiency of the enterprise in general. The developed mathematical
model was successfully tested in practice in the developed PrPlan software package. Additional optimizations
that can be implemented in the model can be equally well made in the algorithm of the software
system. This will allow us to make changes quickly, without disturbing existing processes.
Continue...
|
|
|
The article discusses the design of a neural network system to determine the position of a source
of information signals. Determining the coordinates of an unknown source is an important procedure
in improving the efficiency of wireless electronic communications systems. Solving the problem requires
overcoming a number of difficulties associated with the optimal reception of signals from
sources, placement of elements of information transmission systems, and relative complexity of the
meter, which includes means for converting incoming signals. The method of information processing
is based on the use of systems having a variety of spaced reception points organized as a complex of
receivers for remote data transmission. After passing through the group of functional blocks, the preprocessed
signal from each receiver enters the computational module, which is based on a heterogeneous
neural network. The neurocontroller is made of three types of neural blocks forming a threelayer
neural network structure. The first layer is composed of oscillator neurons to maintain the constant
functioning of two other types of neurons, the organization of which requires constant stimulation
for the functioning of the entire network. The second type and third type neural network modules
are designed as signal processing devices adding and cutting off harmonic components. The substantiation
of the applied learning algorithm is performed and the effectiveness of the designed neural network
information processing system is shown.
Continue...
|
|
|
An approach to the construction of a technological scheme, data base and application support for
organizing the processes for inventory and cataloging of the book fund as well as for managing use
of the fund items is proposed. There are situations occurring in real life where some practical conditions
may affect applicability of the methods commonly used for solving the underlying tasks. One
of the restrictions deals with a situation when the fund owners need to developing bibliographic description
of their library books written on different languages assume participation of external experts
with knowledge of the language of publications. The proposed technology options for the implementation
of this task complemented by a description of the principles of building an application that meet
the established requirements provide the necessary support for the work of specialists involved in the
preparation of the filing cabinet and further work with the reader contingent. Although the principles
described in the paper were realized on MS Access they should be generally valid for other platforms.
Continue...
|
|
|
In modern conditions of blurring the boundaries between the virtual and the real world, as well as
the transition of virtual threats into reality, the issues of user security on the Internet are becoming increasingly
important. This is especially true for children and adolescents who are at high risk because
of their young age, lack of skills in safe behavior on the Internet, and lack of understanding of what
moral and/or physical harm this or that information can cause. Therefore, parental control applications
that extend and complement the capabilities of information security tools on the user's devices
are in increasing demand. Basically, such applications provide: monitoring and limiting time of operation of the device, monitoring and restricting access to sites (by age restrictions, by type of sites, by
forbidden words, black or white lists) and applications on the device, tracking the user's movements
(for mobile devices), monitoring online, generation of various reports and statistics on the use of the
device and Internet resources, remote control of the device. The article provides a comparative analysis
of such applications, discusses the functional features of some of them, provides recommendations
for the selection of parental control applications based on user requests, as well as determines
the prospects for their development.
Continue...
|
|
|
№ 2(80)
27 april 2019 year
Rubric: Models and Methods Authors: Volkova V., Kozlov V., Loginova A., Romanova E., Shirokova S. |
The article characterizes and interprets the concepts introduced in the theory of the information
field A.Denisov and the discrete version of this theory, which name– the informational approach to the analysis of systems: sensual information (perception information, element base, data), logical information
(essence or information potential) and their logical intersection, which in theory A.Denisov
corresponds to the category of information complexity, content, meaning. It is shown how these concepts
arose in the theory of the information field as a result of two laws of reflection — sensory and
logical, as they are interpreted in a discrete version of the theory. It is considered how the reflection of
objects or processes goes through several stages. During their passage, the term “information” is used
all the time, but until a more specific name of the perceived and / or transformed essence corresponding
to a particular decision–making process is found. Understanding this process makes the available
measures of information possible to more accurately use, as well as the mating terms “data (J) – concepts
(H) –knowledge (C)”. Such approach allows to determine the measures which can be entered for
measurement of the selected stages of information transformation based on deterministic and probabilistic
approaches, choosing them taking into account specific objectives and the conditions of application
of the theory of A.Denisov.
Continue...
|
