Proceedings of the IV International research conference "Information technologies in Science, Management, Social sphere and Medicine" (ITSMSSM 2017)
Session: Computational Technologies
19 articles
Proceedings Article
Fault-tolerant on-board computer systems designing based on symmetry groups modeling
Liubov Lomakina, Maksim Nadezhki, Nikolay Sil'yanov
Structure of on-board computer system based on a high-speed switching network is shown. Tolerance for single fault of processing modules is provided. Fault-tolerance based on models of symmetry groups is considered. Algorithm for generating reconfiguration tables is developed. The example is shown applying...
Proceedings Article
Benchmarking of neuroevolutionary approach for controlling task of trolley balance
Sergey Rodzin, Ada Rodzina
The article analyzes the neuroevolution of the problematic issues - a promising approach for solving complex problems of machine learning neural networks, adaptive management, and multi-agent systems, evolutionary robotics, search game strategies, computer art. The authors propose a neuroevolutionary...
Proceedings Article
Visualization Management of the Spatial Data Containing Uncertainty
Stanislav Belyakov, Marina Savelyeva, Marina Belyakova, Sergey Zubkov
The paper is devoted to the development of a method of visualization management of the spatial data on electronic maps. It is assumed that spatial data are obtained from sources that didn't allow to define fully and consistently all characteristics of objects or events. There are defects of display in...
Proceedings Article
The Results of the Modified MVA Application
Ahmed Wesam Mohammed Abdo, Dmitry Bykov
The article provides a brief description of the use of the modified method MVA and the results obtained with MVAThe article provides a brief description of the use of the modified method MVA and the results obtained with MVA
Proceedings Article
Text structures synthesis on the basis of their system-forming characteristics
Liubov Lomakina, Anna Surkova, Dmitry Zhevnerchuk
This paper deals with different text structure synthesis methods using the concept of hidden parameters. Three main methods of text structure synthesis using the concept of hidden parameters were described in this paper: information, parametric and non-parametric. The hidden parameters concept implies...
Proceedings Article
Lacunary sequences that do not influence the uniqueness of solution of the inverse Borg-Levinson problem
Irina Kinzina, Larisa Smirnova, Olga Torshina
Here we present the inverse problem of spectral analysis with the Dirichlet boundary conditions for the Laplace operator with a potential defined in a bounded domain of multidimensional space. The uniqueness theorem of the recovery of potential in the inverse Borg-Levinson problem with boundary conditions...
Proceedings Article
Adaptive system of intelligent environment based on neural networks
Pavel Nikolaev
This paper describes the concept of adaptive system of intelligent environment for smart homes and intelligent buildings. This intelligent system is based on one of the methods of artificial intelligence and machine learning - artificial neural networks. The key feature of the proposed system is the...
Proceedings Article
Quantitative characteristics of quality of the a?tiv?-pulse television systems
Ekaterina Zaytseva, Ivan Pustynsky
The quantitative characteristics of quality assessment in the active-pulsed television system, taking into account the loss in agreeing an optoelectronic transducer and a television transmitter, are consider.
Proceedings Article
Quadrocopter Control in Auto Tracking Mode
Andrey Mikhaylov, Polina Kovalenko, Alexander Kataev, Elena Maksimova, Anna Alekseenko
In this work the following has been done: ROS configuring, installing of catkin, exploring of Parrot AR.Drone 2.0 application programming interface (API), quadrocopter and computer data exchange through Wi-Fi. Result of work is a project with implemented different object tracking methods: Histogram Back...
Proceedings Article
Comparison of object classification methods in seed stream separation
Andrey Vlasov, Alexander Fadeev
The paper presents a study of machine learning approaches to detect and classify seeds of a grain crop in order to enhance agricultural seed purification line. The main features of seeds that are hard to recognize during a separation with mechanical methods are resolved with the help of machine learning...
Proceedings Article
Review and analysis of means and methods for automatic data extraction from heterogeneous sources
Alexey Samoylov, Alexey Tselykh, Nikolay Sergeev, Margarita Kucherova
There is a problem in the process of data analysis, which is related to their extraction and preparation. This problem is the consequence of a necessity for integration of heterogeneous structures both in structure and format. The technical solution to this problem is to use ETL-systems that automate...
Proceedings Article
The matching points methods for solving the problem of the tracking objects
Polina Kovalenko, Andrey Mikhaylov, Alexander Kataev, Vladimir Rozaliev, Yulia Orlova
This article interprets a concept of key points and its descriptors, object tracking and key points matching goals. The concept of object detection and detection classification methods are described. Key points matching methods based on standard OpenCV functions and matching machine learning methods...
Proceedings Article
Controlling the correctness of physical exercises performance
Alexander Vybornyi, Vladimir Rozaliev, Yulia Orlova
This document contains the description of the program for the control of the correct physical exercises performance implementation using Microsoft Kinect, the method of the comparison between live motions performed by the user and recorded motions, description of the testing of the program and also information...
Proceedings Article
A Fault-tolerant Two-tier Pattern Of Secure Access 'Connecting Node'
Vladimir Kolomoitcev, Vladimir Bogatyrev
The purpose of this paper is to study a fault-tolerant system of secure access to the corporate network and to select the options for allocating resources of the server for the system's information protection software that is installed on it, given that the conflicting requirements, arising in this case,...
Proceedings Article
Patents Images Retrieval and Convolutional Neural Network Training Dataset Quality Improvement
Alla Kravets, Nikita Lebedev, Maxim Legenchenko
The paper considers the problem of the analysis of patents' figures for formalization of subjective opinions of the patent office experts that reviews applications for inventions. Drawings omission may indicate an incomplete description of the invention and entail the rejection of patent applications...
Proceedings Article
Building a model of the external environment of a robot based on stereo vision
Alexander Goritov, Sergei Yakovchenko
In this article, the problems of constructing an external environment of a robot based on stereo vision are considered. Finding ways to solve problems related to building a three-dimensional model of the working environment. The theoretical part describes the basic formulas and definitions of stereoscopic...
Proceedings Article
Automatic calculation of the dynamic characteristics of the manipulator on the basis of euler - lagrange equation
Alexander Goritov, Maria Molokova
Robotics is very popular in today's world. The robots are widely used in various fields of human life. They are used in medicine for development of space in the field of safety at work and at home. However, the design and simulation of the robot is a long and tedious process. Therefore, special programs...
Proceedings Article
Named Entity Recognition in Natural Language Texts obtained through Audio Interfaces
Nail Gafurov, Alexey Platonov
The article describes the features of named entity recognition from natural language texts in English obtained by audio interfaces and a method for increasing the efficiency of technologies based on machine learning by using a modified data set for training.
Proceedings Article
Image Converting into Complex Networks : Scale- Level Segmentation Approach
Andrey Trufanov, Nikolay Kinash, Olga Berestneva, Alexei Tikhomirov, Alessandra Rossodivita
Image analysis and recognition is being a contemporary domain for successful tries to apply complex networks as an instrument for thorough studies. Researchers noted that an image having traditionally converted into a network (i.e. taking into account Euclidean distance between pixels only) possesses...