Academic Journal of Lviv Polytechnic. Series of Computer Systems and Networks №881, 2017

УДК 621.3 (681,519,536,62,50,003,004)

Berezko L.O., Huryk Y.P. Implementation of DPDK based TCP/IP protocols stack for OS Linux.

The performance problem of network stacks currently implemented in operating systems. Analysis of frameworks for high-performance packet IO. An architectual diagram of the custom network stack.
Кеуwords: network stack, NIC, DPDK.

Berezko L., Klachko I. Computer mobile network of the city of Lviv.

The problem of the choice of non-cable technology on the basis of which a network for data transmission on the territory of the city of Lviv, including dense buildings and those for which the cable network is not relevant, is considered. Several basic technologies of wireless communication are considered and technology is proposed for solving this problem.
Кеуwords: computer network, WiMAX technology.

Botchkaryov A., Golembo V., Kraikin Yu. Wireless sensor-actuator network as a part of the cyber-physical system.

The problem of developing wireless sensor-actuator network as a part of the cyber-physical system is considered. The ways of implementation of the wireless connections’ scheme are analyzed. The network structure and algorithms of its operation are proposed. The results of implementation of the sensor and actuator nodes are considered.
Кеуwords: wireless sensor-actuator network, cyber-physical system.

Glukhov V., Khomits V. Approach to implementation on FPGA of data compression algorithm C language descriptions by means of Vivado package

The features of devices for monochrome images lossless compression by JPEG-LS method in modern element base are discussed. Capabilities of Vivado package (Xilinx) for JPEG-LS algorithm C- to suitable for implementation in FPGAs VHDL-descriptions transformation were tested and described. C language structures, which can not be processed by specified means and possible circumvention of such structures were defined.
Кеуwords: lossless compression, FPGA, JPEG-LS, software implementation, hardware implementation.

Glukhov V., Khomits V. Approach to implementation of JPEG-LS lossless image compression method on FPGA.

The features of devices for monochrome images lossless compression by JPEG-LS method in modern element base are discussed. Details of compression algorithm JPEG-LS, its C language implementation and its time characteristics are described.
Кеуwords: lossless compression, FPGA, JPEG-LS, software and hardware implementation.

Zholubak I., Glukhov V. Multiplier realization of the high level Galois fields in FPGA

In this paper, the implementation of matrix multipliers of the Galois fields with basics 2, 3, 5, 7, 13 and the analysis of the implementation of multipliers with a higher basis on the FPGA Xilinx Spartan-6 and Altera – Cyclone-5 is considered. It is shown that the smallest hardware costs will be in multiples of Galois fields with a base 2. For the implementation of the Guild cells with a large foundation, the core generator of the modified Guild cells was implemented.
Кеуwords: Galois fields GF(dm), multiplier, modified Guild cell, LUT, nucleus generator.

Ihnatovych A., Ivantsiv R., Pavych N. Efficiency evaluation criterion of security components of computer systems.

Current situation of efficiency evaluation of security components of computer systems and networks is analyzed. It is founded that mentioned in the article effectiveness assessment methods are not sufficiently provided with fundamental theory and methodology and to great extent are subjective. Usage of generalized efficiency evaluation criterion is proposed. Methodology of usage of such criterion on the test case with block ciphers is overviewed. In the article is shown that usage of the proposed criterion increases the objectivity of the process of the efficiency evaluation of security components of computer systems and networks.
Кеуwords: efficiency evaluation, criterion for evaluating the effectiveness, security components, computer systems.

Klushyn Y. Increasing the accuracy of evaluation of the performance period of software complex components in multiprocessor computer systems under noise stochastic modeling.

To improve the accuracy of the estimation of the time of execution of complex software complexes on parallel computers, an algorithm for the uniform distribution of vertices of a graph of a given set of interrelated works is developed. This algorithm is used in the method of plywood stochastic simulation of multiprocessor computer systems.
Кеуwords: parallel computing systems, complex interconnected works, direct stochastic modeling, Markov process.

Melnyk A., Lykhotop D., Grebeniak A. Embedded local Wi-Fi computer network with configuration using Bluetooth technology.

The design principles of a mobile LAN for cyber-physical systems based on microprocessors with a WI-FI wireless interface, aimed at high speed data receiving and transmission between customers, as well as the number of clients up to 16 per access point that are simultaneously connected and have the ability to transmit data are developed and investigated. In particular, the problem of switching network clients among themselves is investigated. The offered formats of data packets for forwarding from customer to customer by identifier, from client to client group of one type, client identification - for complete information about the device, and client settings - for sending client configuration file settings by ID. Functions to separate "packaged" packages when forwarding, all possible checks on the integrity of the data packet and the correctness of its formation are implemented. The Bluetooth Low Energy (BLE) technology as an additional channel for network configuration is proposed to use, namely: configuring the name of a non-cable network, access password, module operation modes (autodetection, access point, station), encryption modes, restrictions on access from other devices, regardless of module mode settings in current time. The upper levels of the Bluetooth protocol stack (GAP, GATT), the specification, and the main aspects to blend the device into BLE are considered. An Android application that simplifies the work of the network and, together with it, creates a management and monitoring system is developed. An example application, which is a user interface for the basic network settings configuring is provided.
Кеуwords: embedded local wi-fi computer network, cyber-physical system, Bluetooth Low Energy technology.

Pavych N., Kutkovyi B. Accelerated servicing method of api calls to cloud-database management systems.

Analyzed the current state of the Application Programming Interface (API) calls to cloud database management systems. The expediency of creating tools to reduce the time for servicing such requests and the effective synchronization of the local and cloud databases has been established. The main features and principles of data replication are clarified. The expediency of using the counter of generations in the replication process instead of the system timer is justified. An asynchronous method of accelerated servicing for API calls to cloud database management systems is proposed by using a synchronization accumulative table and registering changes in databases using a two-stage set of generations. A library that provides the implementation of asynchronous API queries for the Salesforce cloud management system has been developed. The library can be used in any Ruby on Rails application. The evaluation of the benefits for the proposed solutions in the test case was carried out. The results of the test studies confirm the minimization of the service time for API calls to the cloud database management systems based on the proposed asynchronous method.
Кеуwords: API calls, accelerated servicing, database management systems, cloud database.

Paramud Y., Yarkun V. Algorithmic and software means of handwritten symbols recognition.

In this article is considered the algorithm of logistic regression and construction of the neural network for the recognition of handwritten symbols in the image. Examples of implementation of two approaches for solving the problem of numerical recognition are given. The efficiency of using a neural network, as the provision of the most reliable recognition results, is explored.
Кеуwords: logistic regression, neural network, symbols recognition, machine learning, cost function, gradient descent.

Pasternak I. Means of units verify the reliability of communication network systems cyber physical.

Analyzed the principles of building communication networks. The advantages and disadvantages of existing today means implementing diagnostic environments. A reliable means of verification nodes in a communication network cyber physics system.
Кеуwords: communication network, client, server, cyber physics system.

Protsko I., Rykmas R. Automatic generation of the efficient algorithms of DCT-II based on cyclic convolutions.

Program of efficient implementation the discrete cosine transform of type-II using cyclic convolutions have been considered. The stages of automatic code generation the algorithms for the computation of DCT-II an arbitrary size N have been determined. The algorithm of DCT-II presents a better program performance for short sizes of transform, than known FFTW library.
Кеуwords: discrete cosine transform (DCT), block-circular structure, hashing array, cyclic convolution, program implementation, automatic code generation.

Puyda V. Multi-processor computer vision system.

We propose a computer vision system based on multi-processor architecture that uses multi-port memory with equal access to all special microprocessors.
Кеуwords: computer vision system, video stream, image segmentation, identification.

Puyda V. Special processor for feature detection based on the surf algorithm.

We propose a structure of special processor implementing feature detection in a video stream based on the SURF algorithm to be used in computer vision systems.
Кеуwords: computer vision, video stream, SURF features, image identification.

Riznyk V., Solomko M. Combinatorial method of minimizing boolean functions.

Considered the new procedure of logic algebra – super-sticking of variables, which is carried out in the presence of a truth table in complete binary combinatorial system with a repetition or incomplete of the system considered. The efficiency of the algebraic operation of super-sticking variables greatly simplifies the algorithm for minimizing boolean functions, which allows manual minimization of the functions.
Кеуwords: boolean function, method of minimizing, minimization of logic function, block-design with repetition, minterms, super-sticking of variables.

Salo A., Kravets O. Protocols of executive devices in vending ciberphysic systems.

In the article review of interfaces and peripheral device protocols for vending machines has been conducted and they have been compared. Based on the peculiarities shown in the comparative characteristic realization of unified program interface for the set of given protocols has been suggested. The stages of interaction between control board and actuators have been described. The structural scheme of interface realization has been shown.
Кеуwords: Vending, MDB, Executive, ccTalk, CCNET, SSP, unified interface.

Tymoshchuk P. Parallel rank-order filtering based on Impulse K-Winners-Take-All Neural Network.

A continuous-time K-winners-take-all (KWTA) neural network (NN) which is capable of identifying the largest K of N inputs, where a command signal has presented. The network is described by a state equation with a discontinuous right-hand side and by an output equation. The state equation contains an impulse train defined by a sum of Dirac delta functions. The main advantage of the network is not subject to the intrinsic convergence speed limitations of comparable designs. Application of the network for parallel rank-order filtering has described. Theoretical results are derived and illustrated with computer simulation example that demonstrates the network’s performance.
Кеуwords: continuous-time network, K-winners-take-all (KWTA) neural network (NN), state equation with a discontinuous right-hand side, impulse train, Dirac delta function, parallel rank-order filtering.

Trembach B. Method of spatial identification of acoustic signals source in the Two-Dimensional Hemming Space.

The theoretical bases of the correlation method of spatial identification of the source of acoustic signals in the two-dimensional Hemming space of Cartesian coordinates are described. The structural model of the spatial identification of sources of acoustic signals in Cartesian coordinates of a two-dimensional Hemming space with the priority placement of microphones as receivers of acoustic signals is proposed. Examples of analytical calculations of the system characteristics of the hardware and time complexity of the correlation system based on a certain number of microphones and the corresponding number of interrelations are presented. The structural solutions of the hardware special processor implementation of such a class of multichannel devices for recognition and identification of types and the spatial location of sources of acoustic signals are developed. It is shown the possibility of using such a class of devices in the field of special military equipment of military use.
Кеуwords:acoustic signals, correlators, special processors, Hemming space.

Title pages

Editorial board of Academic Journal "Computer Systems and Networks"

Editor-in-chief: Dr., Professor, Anatoliy Melnyk

Deputy editor: Dr., Professor, Roman Dunets

Executive secretary: PhD., Docent, Jaroslav Paramud

Editorial team

  • Prof., PhD., D.Sc. V.Hlukhov
  • Prof., PhD., D.Sc. O.Drozd
  • Prof., PhD., D.Sc. O.Ivakhiv
  • Prof., PhD., D.Sc. S.Lupenko
  • Prof., PhD., D.Sc. V.Melnyk
  • Prof., PhD., D.Sc. A.Nakonechny
  • Prof., PhD., D.Sc. J.Nikolaichuk
  • Prof., PhD., D.Sc. V.Opanasenko
  • Prof., PhD., D.Sc. O.Pomorovа
  • Prof., PhD., D.Sc. V.Tarasenko
  • Prof., PhD., D.Sc. Zdenek Pliva
  • Prof., PhD. Vedat Coskun
  • Prof., PhD. Jesus Ceretero
  • Prof., PhD. Tanya Vladimirova
  • Prof., PhD. Jiafu Wan
  • Doc, PhD., D.Sc. R.Kochan