Кафедра "Електронні обчислювальнi машини" (КЕОМ ДІІТ)

Permanent URI for this communityhttp://crust.ust.edu.ua/handle/123456789/695

ENG: Department "Electronic Computers"

Browse

Now showing 1 - 40 of 319

Advanced Study on Resource-Saving Methods of Forming Information Infrastructure of Sorting Stations
(BP International, West Bengal, India, 2021) Kosolapov, Anatolii A.
EN: This chapter discusses a resource-saving method for choosing a rational structure of an automated control system when technical structure migration from a centralized system based on a powerful processor to a functionally distributed system based on microcontrollers. The method allows you to determine a rational number of subsystems that effectively use the computing and financial resources of the project. The approach is illustrated by a real example of designing an automated control system for a marshalling yard.
An Approach to Assessing the Operational Reliability of Real-Time Systems at the Stage of Conceptual Design
(ScientificWorld-NetAkhatAV, Karlsruhe, 2023) Belyaev, Nikolai; Kosolapov, Anatoliy; Egorov, Oleh Yo.; Sokur, Maria; Parpolita, Oleksandr M.
ENG: Сurrently, many facilities operate in real-time mode in an environment with a high level of radio-magneto-electronic interference. The software of such systems, debugged in stationary conditions, during the period of pilot operation gives a large number o.
Basis for Innovation in the Computerization of Society
(ScientificWorld-NetAkhatAV, Karlsruhe, Germany, 2022) Kosolapov, Anatolii A.; Egorov, Oleh Yo.; Dziuba, Volodymyr V.; Parpolita, Oleksandr M.
ENG: In this chapter, the authors have tried, in the context of the high rate of innovation in the computerization of society, to highlight the immutable in their view basic concepts and their definitions, which make it possible to understand the essence of the ongoing transformations. The paper considers the main stages and levels of the implementation of enterprise automation systems and components of their structures. A formula for describing the concept of "CS architecture" is proposed, a generalized structure of a WEB-system and its safe implementation is given.
Choice of the Optimal Parameters of Measuring the Shaft Rotation Frequency of the Hydraulic Transmission of the Locomotive Using Microcontroller
(Дніпропетровський національний університет залізничного транспорту імені академіка В. Лазаряна, Дніпро, 2017) Zhukovytskyy, Igor V.; Kliushnyk, Ihor A.
ENG: Purpose. The article provides for finding solution to the problem of developing and improving the means for measuring tachometric data of the previously created information and measuring system for testing hydraulic locomotive transmission by substantiating the optimal sensor design and signal processing algorithms. At the same time first of all it is necessary to start from the possibility of modifying the already existing test bench for hydraulic locomotive transmissions at the Dnipropetrovsk diesel locomotive repair plant «Promteplovoz». Methodology. In the work, the researchers proposed a methodology for modifying the sensor design and the algorithm for processing its signals. It is grounded on previous developments of tachometric sensor of the optical type on the basis of D-2MMU-2 sensor of the microprocessor automated test bench system of hydraulic locomotive transmission in the locomotive repair plant conditions. Selection of the necessary measurement algorithm and the number of sensor teeth is substantiated by calculating instrumental and methodological errors. Also, the studies aimed at identifying the source of interference in the measurement of rotational speed are described and solution for its elimination has been found. Findings. For the designed rotation speed sensor of the optical type based on the existing D-2MMU-2 sensor, the authors analyzed the dependence of the methodological and instrumental errors. Based on the obtained data more rational variant of the rotation speed calculation algorithm is proposed, and the number of teeth of the sensor disk is justified. Further, the main source of measurement interference was established and a method for improving the hardware of the hydraulic locomotive test bench was proposed. Originality. There were conducted the studies according to the methodological and instrumental errors of the designed rotation speed of sensor. The mechanisms of interference filtering arising from the sensor rotation speed fixing were proposed. Additional studies have shown the need for a hardware revision of signal conditioner scheme. Practical value. Conducted studies make it possible to establish a rational number of sensor disk teeth, which allows improving the measurement algorithm. It was also performed a hardware improvement of signal conditioner scheme from the sensor, helping to get rid of interferences. The results of measurements in studies are the initial data to perform further studies in order to determine the technical condition of hydraulic transmission UGP 750-1200 during factory testing after repair.
Computer architecture
(Ukrainian State University of Science and Technologies, Dnipro, 2023) Yehorov, Oleh I.; Dziuba, Volodymyr V.; Ivin, Pavlo
ENG: Methodical recommendations are intended for students of the 3rd year of the specialty 123 "Computer engineering" to prepare for practical work in the discipline "Computer architecture".
Computer Architecture
(Ukrainian State University of Science and Technologies, 2024) Kosolapov, Anatolyi; Yehorov, Oleh I. ; Tymoshenko, Liudmyla
ENG: Educational and methodical recommendations are intended for students of the 3rd year of the specialty 123 "Computer Engineering" to prepare for the coursework in the discipline "Computer Architecture". Educational and methodological recommendations contain the main theoretical provisions for mastering the material, instructions for performing coursework, requirements for analysis of results and design of works.
Conceptual Resource-Saving Design of Real-Time Socio-Technical Systems
(IOP Publishing Ltd, England, 2021) Kosolapov, Anatolii A.; Ivin, Pavlo
EN: The article discusses the methodological resource-saving approach to the System design of socio-technical systems for real-time managing (STS RTM). The definition of STS RTM from the point of view of computer systems architecture is introduced. This approach made it possible to classify the main paradigms of using computer systems, including the modern stage, corresponding to STS RTM. For such complex systems, it is important to ensure their energy efficiency, which is ensured by the use of resource-saving models and methods for optimizing structural solutions. This is ensured by minimizing the total length of communications at the enterprise, saving computing and financial resources during system migration from a centralized structure to a functionally distributed hierarchical multi-microcontroller system. STS is a human a real-time machine system, therefore, the system's response time to the processing of requests related to the issuance of messages to the system's operating personnel is determined. The complex of formulated tasks and their solution on a common information and analytical base is extremely difficult without a unified system design methodology and automation tools for solving problems. Such a Framework is described in this article.
Cемиотико-агентно-онтологическая модель интеллектуальных систем
(ООО "Научный мир", Иваново, 2017) Косолапов, Анатолий Аркадьевич
RU: В работе рассматривается предложенная автором гибридная интегрированная семиотико-агентная-онтологическая модель интеллектуальных систем. САО-модель является развитием семиотической модели Д.А. Поспелова на основе новых парных агентных моделей и онтологических баз знаний для хранения агентов и описания системной семантики и прагматики. Дополненная средствами имитационного моделирования, организации диалога и процедурами принятия решений в условиях неполноты и неопределённости, а также большого количества данных САО-модель будет интеллектуальным инструментарием для создания, познания и развития интеллектуальных систем.
Cемиотико-агентно-онтологическая модель интеллектуальных систем (препринт)
(ООО "Научный мир", Иваново, 2017) Косолапов, Анатолий Аркадьевич
RU: В работе рассматривается предложенная автором гибридная интегрированная семиотико-агентная-онтологическая модель интеллектуальных систем. САО-модель является развитием семиотической модели Д.А. Поспелова на основе новых парных агентных моделей и онтологических баз знаний для хранения агентов и описания системной семантики и прагматики. Дополненная средствами имитационного моделирования, организации диалога и процедурами принятия решений в условиях неполноты и неопределённости, а также большого количества данных САО-модель будет интеллектуальным инструментарием для создания, познания и развития интеллектуальных систем.
Databases : methodical recommendations for individual task
(Ukrainian State University of Science and Technologies, Dnipro, 2022) Pakhomova, Victoria M.
ENG: Methodological recommendations are aimed at preparing and doing individual tasks in the discipline «Databases» for foreign applicants of Bachelor’s Degree of specialties 123 «Computer Engineering» and 125 «Cybersecurity».
Design of Databases by Bachelor’s Degree Applicants when Writing a Qualification Paper
(Kupriyenko SV in conjunction with KindleDP, USA, Seattle, 2023) Pakhomova, Victoria M.
ENG: For use by applicants for a bachelor's degree when writing qualification papers, the «BachelorDesignDB» methodology is proposed, which consists of the following stages: review of sources on existing databases; study of the subject area in order to form an initial attitude; database design using well-known methods («Normal Forms» and «Essence-Relation») and analysis of the design results obtained; creation of a designed database with the help of the selected software application and its protection; optimization and performance improvement of the created database; formulating conclusions and providing recommendations for the practical use of the created database.
Detection of Attacks of the U2R Category by Means of the SOM on Database NSL-KDD
(Український державний університет науки і технологій, ННІ «Інститут промислових та бізнес технологій», ІВК «Системні технології», Дніпро, 2022) Pakhomova, Victoria M.; Mehelbei, Yehor O.
ENG: Creating an effective system for detecting network attacks requires the use of qualitatively new approaches to information processing, which should be based on adaptive algorithms capable of self-learning. The mathematical apparatus of the Kohonen self-organizing map (SOM) was used as a research method. Python language with a wide range of modern standard tools was used as a software implementation of the Kohonen SOM addition, this section compiles the Python software model «SOM_U2R» using a Kohonen SOM. Created «SOM_U2R» software model on database NSL-KDD an error research was performed for different number of epochs with different map sizes. On the «SOM_U2R» model the research of parameters of quality of detection of attacks is carried out. It is determined that on the «SOM_U2R» created software model the error of the second kind of detection of network classes of attacks Buffer_overflow and Rootkit is 6 %, and for the class Loadmodule reached 16 %. In addition, a survey of the Fmeasure was conducted for a different number of epochs of learning the Kohonen SOM. It is determined that for all network attack classes (except Buffer_overflow) the F-measure increases, reaching its maximum value at 50 epochs.
Detection of Attacks on a Computer Network Based on the Use of Neural Networks Complex
(Дніпровський національний університет залізничного транспорту імені академіка В. Лазаряна, Дніпро, 2020) Zhukovyts’kyy, Igor V.; Pakhomova, Victoria M.; Ostapets, Denis O.; Tsyhanok, O. I.
ENG: Purpose. The article is aimed at the development of a methodology for detecting attacks on a computer network. To achieve this goal the following tasks were solved: to develop a methodology for detecting attacks on a computer network based on an ensemble of neural networks using normalized data from the open KDD Cup 99 database; when performing machine training to identify the optimal parameters of the neural network which will provide a sufficiently high level of reliability of detection of intrusions into the computer network. Methodology. As an architectural solution of the attack detection module, a two-level network system is proposed, based on an ensemble of five neural networks of the multilayer perceptron type. The first neural network to determine the category of attack class (DoS, R2L, U2R, Probe) or the fact that there was no attack; other neural networks – to detect the type of attack, if any (each of these four neural networks corresponds to one class of attack and is able to identify types that belong only to this class). Findings. The created software model was used to study the parameters of the neural network configuration 41–1–132–5, which determines the category of the attack class on the computer network. It is determined that the optimal training speed is 0.001. The ADAM algorithm proved to be the best for optimization. The ReLU function is the most suitable activation function for the hidden layer, and the hyperbolic tangent function – for the output layer activation function. Accuracy in test and validation samples was 92.86 % and 91.03 %, respectively. Originality. The developed software model, which uses the Python 3.5 programming lan-guage, the integrated development environment PyCharm 2016.3 and the Tensorflow 1.2 framework, makes it pos-sible to detect all types of attacks of DoS, U2R, R2L, Probe classes. Practical value. Graphical dependencies of accuracy of neural networks at various parameters are received: speed of training; activation function; optimization algorithm. The optimal parameters of neural networks have been determined, which will ensure a sufficiently high level of reliability of intrusion detection into a computer network.
Detection of U2R Attacks by Means of a Multilayer Neural Network
(Sworld & D. A. Tsenov Academy of Economics, Svishtov, Bulgaria, 2024) Pakhomova, Victoria M.; Mostynets, Vladyslav L.
ENG: As a research method, multi layer neural network (MLNN) configurations 41-1-Х-4 were used, where 41 is the number of input neurons; 1 – the number of hidden layers; X – the number of hidden neurons; 4 – the number of resultant neurons created using the Neural Network Toolbox of the MatLAB system, to detect U2R network attacks: y1 – Rootkit attack, y2 –Buffer_overflow attack, y3 – Loadmodule attack, y4 – No attack. Using the open database of NSL-KDD network traffic parameters on the created MLNN, a study of its error and number of epochs at different number of hidden neurons (25, 35 and 45 was carried out using different training algorithms: Levenberg-Marquardt; Bayesian Regularization; Scaled Conjugate Gradient. It is determined that the smallest value of the MLNN error was based on the use of the hyperbolic tangent as a function of activating a hidden layer according by the Levenberg-Marquardt training algorithm, and it is enough to have 25 hidden neurons. An assessment of the quality of detection of U2R attacks on MLNN configuration 41-1-25-4 at its optimal parameters was carried out. It is determined that errors of the first and second kind are 9 % and 10 %, respectively.
Determination of Network Attacks Using Neural Network Technologies
(ScientificWorld-NetAkhatAV, Karlsruhe, Germany, 2021) Pakhomova, Victoria N.
ENG: Formulation of the problem. Intrusion-Detection Systems (IDS) are used to detect network attacks in real time. In the information and telecommunication system (ITS) of railway transport, the problem of a large volume of network traffic arises, since standard approaches to data processing cease to be effective. One of the most effective approaches to classifying a large amount of data is the use of neural network technology. This approach allows detecting not only already known network attacks, but also detecting new ones.
Determination of the Optimal Parameters of Wireless Local Network on the Created Program Using the Ant Algorithm
(ProConference in conjunction with KindleDP Seattle, Washington, USA, 2022) Pakhomova, Victoria M.; Salohub, Maksym V.
ENG: The «WLAN_EliteAS» program, created in the JavaScript language of the ant algorithm, determines the optimal number of base stations of wireless local networks and their location on the territory of USUST. Initial data of the «WLAN_EliteAS» program: parameters of the territory of USUST (coordinates of vacant places; number of clients that need to be connected to base stations); wireless local network parameters (base station coverage radius, maximum number of clients to one base station); parameters of the ant algorithm (number of ordinary and elite ants, irrigation and evaporation, greed and laziness). The quality of the obtained solutions depends significantly on the choice of parameters of the ant algorithm.
Development of a Framework for Conceptual Design of RTS (FCD_RTS)
(Український державний університет науки і технологій, ІВК «Системні технології», Дніпро, 2024) Kosolapov, Anatolii A.; Egorov, Oleh Yo.; Parpolita, Oleksandr M.; Zhuk, Stepan
ENG: The paper proposes new results in improving the CoDeCS framework for the conceptual design of complex systems. A new architecture consisting of a subsystem for generating variants of enterprise information architectures (GEntA) and a subsystem for conceptual analytics (ConAn) for characterisation of real-time computer systems (RTSCS) is considered. Both subsystems rely on a common intellectual knowledge bank consisting of a base of facts, a base of production rules and a base of goals formed on the basis of the known experience of conceptual design of complex information-management computer systems. The paper describes the information-technological structures of formalised production lines and presents the first results of subsystems development.
Development of a Self-Diagnostics Subsystem of the Information-Measuring System Using Anfis Controllers
(НВП ПП «Технологічний центр», 2018) Zhukovyts’kyy, Igor V.; Kliushnyk, Ihor A.
EN: A hybrid self-diagnostic system was designed to evaluate correctness of functioning of sensors of the information-measuring system of testing hydraulic transmissions of diesel locomotives of UHP 750 type. The system features the possibility of checking certain four parameters in steady-state operation conditions using known mathematical dependencies. For the other 14 parameters (for which mathematical dependencies were not studied and which have a high complexity of calculations), 14 neural-fuzzy ANFIS networks were developed. Self-diagnostic algorithms using ANFIS controllers were elaborated. The algorithms provide prediction of individual system parameters with the help of ANFIS controllers and a further comparison of the predicted parameters with the measured parameters. The ANFIS controller structure with the proposed Sugeno rule set was constructed and its efficiency was shown. Network training and test of the diagnostic subsystem were performed using the data sets obtained in a series of tests of hydraulic transmissions conducted at Promteplovoz diesel locomotive repair plant. The test results have shown that application of the proposed procedure ensures obtaining of correct result of the self-diagnostic subsystem operation.
Distribution of Information Flows in the Advanced Network of MPLS of Railway Transport by Means of a Neural Model
(Dnipro National University of Railway Transport named after Academician V. Lazaryan, 2019) Zhukovyts’kyy, Ihor; Pakhomova, Victoria N.; Domanskay, Halyna; Nechaiev, Andrew
ENG: Abstract. Ensuring interoperability of railway transport is possible only due to the developed information structure. Today, Ukraine uses the information-telecommunication system (ITS) of railway transport, which is based on a data communication network. The effectiveness of its work is largely determined by the routing system. The current algorithm for choosing the shortest route, which is used in the existing routing protocol (OSPF), does not always lead to an effective result. However, there is MPLS technology, which could improve the quality of the ITS network by creating virtual channels between its nodes. The authors proposed a scheme for selecting tunnels for the flows in the MPLS network, which is based on the neural model of a multilayer perceptron of configuration 18–3–3–10 with the activation function Softmax in hidden layers and a linear activation function in the input layer. To simulate the network operation, flow data is needed: class of service (CoS), sender and recipient identifiers, average flow rate vector and tunnel data (their initial load). The final load of the tunnels is taken as the resulting output of the neural network, on the basis of which the tunnel is selected for the flow of the k-th class of service.
Forecasting Network Traffic in the Information and Telecommunication System of Railway Transport by Means of a Neural Network
(MATEC Web of Conferences, 2023) Zhukovytskyy, Igor V.; Pakhomova, Victoria M.
ENG: Network traffic is one of the most important actual indicators of the information and telecommunication system (ITS) of railway transport. Recent studies show that network traffic in the ITS of railway transport is self-similar (fractal), for the study of which the Hirst indicator can be used. One of the possible solutions is a method of network traffic forecasting using neural network technology, which will allow you to manage traffic in real time, avoid server overload and improve the quality of services, which confirms the relevance of this topic. The method of forecasting the parameters of network traffic in the ITS of railway transport using neural network technology is proposed: for long-term forecasting (day-ahead) of network traffic volume based on network traffic volumes for the previous three days using the created multilayer neuro-fuzzy network; for short-term prediction (one step forward, which takes five minutes) of network traffic intensity based on network traffic intensities for the previous fifteen minutes using the created multilayer neural network. The corresponding samples are formed on the basis of real values of network traffic parameters in the ITS of railway transport. Studies of optimal parameters of the created multilayer neural network, which can be integrated into specialized analytical servers of the ITS of railway transport, are carried out, which will provide a sufficiently high level of short-term forecasting of network traffic parameters (in particular intensity) in the ITS of railway transport at the stage of deepening the integration of the national transport network into the Trans-European Transport Network.
Formation of Competencies Among Applicants of Foreign Origin in Blended Learning «Local Networks» Discipline
(Sergeieva&Co, Germany, Karlsruhe, 2022) Pakhomova, Victoria M.
ENG: The proposed «BlenLearnEnglLAN» methodology for the formation of competences among applicants of foreign origin bachelor's degree in the «Computer Engineering» specialty during blended learning in the «Local Networks» discipline: 1) study of basic concepts and fundamental principles of various network technologies during lectures held using the «Zoom» system; 2) compilation of the structure of the local network and assessment of its correctness, according to the compiled structure, creation of a simulation model of the local network in NetCracker Pro and conducting research on it during laboratory work carried out face-to-face; 3) research of network traffic parameters using neural network technology and obtained data on a simulation model during independent work using recommended sources; 4) development of theoretical material using the lecturer's presentations and testing in the «Leader» system, arguing the choice of network technology based on the obtained results of research on simulation models.
Formation of Competencies and Soft Skills when Performing Brigade Discipline Tasks «Mathematical Foundation of Information Security»
(Sergeieva&Co, Karlsruhe, Germany, 2024) Pakhomova, Victoria M.
ENG: The proposed methodology of "SoftSkillsMathFIS" for the formation of competencies of applicants for a bachelor's degree in blended learning in the discipline "Mathematical Foundations of Information Security": 1) study of mathematical concepts (symbols Legendre and Jacobi, their properties) during lectures conducted with the help of Zoom system, 2) algorithmization and programming for the implementation of the Solovey-Strassen test and the organization of relevant research during laboratory work, 3) acquisition of practical skills in using probabilistic tests to determine the primality of a number on based on various mathematical approaches and tools when performing independent work with use of recommended sources, 4) elaboration of theoretical material on using the lecturer's presentations and passing testing in the "Lider" system.
Formation of Competencies in Applicants of the Bachelor’s Degree of Foreign Origin in Distance Learning in the «Database» Discipline
(Sergeieva&Co, Germany, Karlsruhe, 2022) Pakhomova, Victoria M.
ENG: The «ForeignDistLearnDB» methodology on the formation of competencies of applicants for foreign origin «Bachelor» in «Computer Engineering» in distance learning in the «Databases» discipline, consisting of the following stages: 1) familiarization with the basic models of data representation (during lectures); 2) study of DDL, DML and DQL constructs that form the basis of SQL (during laboratory work); 3) designing a relational database using the «Normal Forms» and «Essence-Relation» methods (during the individual task); 4) analysis of the process and results of database design by different methods (mathematical and graphical); 5) elaboration of theoretical material with the use of lecturer presentations and modular testing in the «Lider» system.
Framework Conceptual Design of Complex Real-Time Management System (CoDeCS)
(Luminary Publication, India, 2018) Kosolapov, Anatolii A.; Loboda, Dmytro H.
EN: The modern information management systems are the complicated systems with territorial and by the functionally distributed complexes integrated on the basis of networks technologies and workings in the real time. When designing and developing such systems, the role of their conceptual design increases. A large number of used parameters, incompleteness of data require the use of special techniques and frameworks of the system designing. The work deals with the concept of the modern information management systems architecture and the main stages of system design based on the national standard 34. The methodology of designing complex management (information) systems working in real time is proposed. The methodology is based on ontological models of knowledge about the problem domain.
Identifying Threats in Computer Network Based on Multilayer Neural Network
(Дніпропетровський національний університет залізничного транспорту імені академіка В. Лазаряна, Дніпро, 2018) Zhukovyts’kyy, Igor V.; Pakhomova, Victoria M.
ENG: Purpose. Currently, there appear more often the reports of penetration into computer networks and attacks on the Web-server. Attacks are divided into the following categories: DoS, U2R, R2L, Probe. The purpose of the article is to identify threats in a computer network based on network traffic parameters using neural network technology, which will protect the server. Methodology. The detection of such threats as Back, Buffer_overflow, Quess_password, Ipsweep, Neptune in the computer network is implemented on the basis of analysis and processing of data on the parameters of network connections that use the TCP/IP protocol stack using the 19-1-25-5 neural network configuration in the Fann Explorer program. When simulating the operation of the neural network, a training (430 examples), a testing (200 examples) and a control sample (25 examples) were used, based on an open KDDCUP-99 database of 500000 connection records. Findings. The neural network created on the control sample determined an error of 0.322. It is determined that the configuration network 19-1-25-5 copes well with such attacks as Back, Buffer_overflow and Ipsweep. To detect the attacks of Quess_password and Neptune, the task of 19 network traffic parameters is not enough. Originality. We obtained dependencies of the neural network training time (number of epochs) on the number of neurons in the hidden layer (from 10 to 55) and the number of hidden layers (from 1 to 4). When the number of neurons in the hidden layer increases, the neural network by Batch algorithm is trained almost three times faster than the neural network by Resilient algorithm. When the number of hidden layers increases, the neural network by Resilient algorithm is trained almost twice as fast as that by Incremental algorithm. Practical value. Based on the network traffic parameters, the use of 19-1-25-5 configuration neural network will allow to detect in real time the computer network threats Back, Buffer_overflow, Quess_password, Ipsweep, Neptune and to perform appropriate monitoring.
Information Analytics of Solve a Problem of Software Reliability Evaluation for Sociotechnical Systems at the Conceptual Design Stag
(ДВНЗ «ПДТУ», Маріуполь, 2021) Kosolapov, Anatolii A.; Ivin, Pavlo
EN: The scientific works proposes a method for evaluation the software reliability of a computer-based process control in real time system at the at the conceptual design stage. The proposed approach makes it possible to evaluate the possibilities of reserving transactions in real time.
Information-Measuring Test System of Diesel Locomotive Hydraulic Transmissions
(Дніпропетровський національний університет залізничного транспорту імені академіка В. Лазаряна, Дніпропетровськ, 2015) Zhukovytskyy, Igor V.; Kliushnyk, Ihor A.; Ochkasov, Oleksandr B.; Korenyuk, Roman O.
ENG: The article describes the process of developing the information-measuring test system of diesel locomotives hydraulic transmission, which gives the possibility to obtain baseline data to conduct further studies for the determination of the technical condition of diesel locomotives hydraulic transmission. The improvement of factorytechnology of post-repair tests of hydraulic transmissions by automating the existing hydraulic transmission test stands according to the specifications of the diesel locomotive repair enterprises was analyzed. It is achieved based on a detailed review of existing foreign information-measuring test systems for hydraulic transmission of diesel locomotives, BelAZ earthmover, aircraft tug, slag car, truck, BelAZ wheel dozer, some brands of tractors, etc. The problem for creation the information-measuring test systems for diesel locomotive hydraulic transmission is being solved, starting in the first place from the possibility of automation of the existing test stand of diesel locomotives hydraulic transmission at Dnipropetrovsk Diesel Locomotive Repair Plant «Promteplovoz». Methodology. In the work the researchers proposed the method to create a microprocessor automated system of diesel locomotives hydraulic transmission stand testing in the locomotive plant conditions. It acts by justifying the selection of the necessary sensors, as well as the application of the necessary hardware and software for information-measuring systems. Findings. Based on the conducted analysis there was grounded the necessity of improvement the plant hydraulic transmission stand testing by creating a microprocessor testing system, supported by the experience of developing such systems abroad. Further research should be aimed to improve the accuracy and frequency of data collection by adopting the more modern and reliable sensors in tandem with the use of filtering software for electromagnetic and other interference. Originality. The authors developed the information-measuring system that improves the hydraulic transmission test process by automating and increasing the accuracy of measurements of control parameters. The measurement results are initial data for carrying out further studies to determine the technical condition of the hydraulic transmission UGP750-1200 during the plant post-repair tests. Practical value. The paper proposed the alternate design of microprocessor hydraulic transmission test system for diesel locomotives, which has no analogues in Ukraine. Automated data collection during the tests will allow capturing the fast processes to determine the technical condition of hydraulic transmission.
Intelligent Computer Network for Railway Transport Using Neural Network for Determining the Optimal Route
(Sergeieva&Co, Karlsruhe, Germany, 2025) Pakhomova, Victoria M.; Budnikov, Oleksandr
ENG: At the present stage, the information and telecommunications system of railway transport uses local area networks of Ethernet family technologies and the OSPF protocol, when used in real time, a problem arises due to constant changes in the volume of transmitted data, and for its solution it is advisable to use a neural network tool, which confirms the relevance of the topic. As a mathematical apparatus for solving the problem of determining the optimal route, a neural network of the configuration «56-1-X-56» was taken, where 56 (first position) is the number of input neurons (delays on routers); 1 is the number of hidden layers; X is the number of hidden neurons that require additional research; 56 (last position) is the number of output neurons (signs of the entry of computer network channels into the route). In the program mode of the Deep Learning Toolbox package of the MatLAB environment, a corresponding model “Delay_path” was created, on which the root mean square error and the number of epochs of training of neural networks with different numbers of hidden neurons were studied using different neuron activation functions according to different learning algorithms on samples of different lengths. It was determined that the accuracy of the created neural network tool is 70 % for the considered fragment of the information and telecommunications system of railway transport.
Intelligent Computer Network for Railway Transport Using Neuro-Fuzzy Means for Determining the Optimal Route
(Sworld & D.A. Tsenov Academy of Economics, Svishtov, Bulgaria, 2025) Pakhomova, Victoria M.; Lanevych, Vladyslav
ENG: At the present stage, the information and telecommunications system of railway transport uses local networks of the following technologies: Ethernet; Fast Ethernet; Gigabit Ethernet, as well as the OSPF routing protocol, when used in real time, a problem arises due to constant changes in the volume of transmitted data, and for its solution, it is possible to consider the use of a neurofuzzy tool, which confirms the relevance of the topic. As a mathematical apparatus for solving the problem of determining the optimal route, a neural fuzzy network of the configuration «12-24-144-144-1» was taken, where 12 is the number of input neurons (delays on routers); 24 is the number of hidden neurons taking into account the terms; 144 is the number of hidden neurons according to the number of rules; 1 is the number of resulting neurons (total delay on routers along the route). Using the Fuzzy Logic Toolbox package of the MatLAB environment, a Sugeno ANFIS algorithm (with a Gaussian membership function for hidden neurons) was created, on which the mean square error and the number of learning epochs were studied using various learning optimization methods (Backpropagation, Hybrid) on samples of different lengths. It was determined that the accuracy of the created neurofuzzy tool is 80% for the considered fragment of the railway transport information and telecommunications system; a general scheme of an intelligent computer network based on ANFIS was proposed.
Intelligent Routing in the Network of Information and Telecommunication System of Railway Transport
(Дніпровський національний університет залізничного транспорту імені академіка В. Лазаряна, Дніпро, 2019) Pakhomova, Victoria M.; Skaballanovich, Tetiana I.; Bondareva, Valentyna S.
ENG: Purpose. At the present stage, the strategy of informatization of railway transport of Ukraine envisages the tran-sition to a three-level management structure with the creation of a single information space, therefore one of the key tasks remains the organization of routing in the network of information and telecommunication system (ITS) of railway transport. In this regard, the purpose of the article is to develop a method for determining the routes in the network of information and telecommunication system of railway transport at the trunk level using neural network technology. Methodology. In order to determine the routes in the network of the information and telecommunica-tion system of railway transport, which at present is working based on the technologies of the Ethernet family, one should create a neural model 21-1-45-21, to the input of which an array of delays on routers is supplied; as a result vector – build tags of communication channels to the routes. Findings. The optimal variant is the neural network of configuration 21-1-45-21 with a sigmoid activation function in a hidden layer and a linear activation function in the resulting layer, which is trained according to the Levenberg-Marquardt algorithm. The most quickly the neural net-work is being trained in the samples of different lengths, it is less susceptible to retraining, reaches the value of the mean square error of 0.2, and in the control sample determines the optimal path with a probability of 0.9, while the length of the training sample of 100 examples is sufficient. Originality. There were constructed the dependencies of mean square error and training time (number of epochs) of the neural network on the number of hidden neurons ac-cording to different learning algorithms: Levenberg-Marquardt; Bayesian Regularization; Scaled Conjugate Gradi-ent on samples of different lengths. Practical value. The use of a multilayered neural model, to the entry of which the delay values of routers are supplied, will make it possible to determine the corresponding routes of transmission of control messages (minimum value graph) in the network of information and telecommunication system of railway transport at the trunk level in the real time.
Investigation of Multilayer Neural Network Parameters for Determination of R2l Category Network Attacks
(Sergeieva&Co, Karlsruhe, Germany, 2021) Pakhomova, Victoria M.; Bikovska, Daria H.
ENG: To determine R2L network attacks, Python created the MLP software model using the open KDDCup database, which was used to study the values of accuracy and error from the number of neural network learning epochs based on various data: activation functions, hidden neurons, optimization methods. The optimal parameters and configuration of the neural network for detecting classes of network attacks are determined: Ftp_write, Guess_passwd, Imap, Multihop, Phf, Spy, Warezclient, Warezmaster.
Investigation of the pPssibility of using Neurofuzzy Network to Determine the Extent of DoS Attack
(Sworld & D.A. Tsenov Academy of Economics – Svishtov, Bulgaria, 2023) Pakhomova, Victoria M.; Kovalov, Rodion
ENG: As a research method, ANFIS configurations 4-5-8-16-16-1 were used, where 4 is the number of input neurons; 5 – total number of layers; 8 – the number of neurons of the first hidden layer; 16 – the number of neurons of the second hidden layer; 16 – the number of neurons of the third hidden layer; 1 – the number of resultant neurons created using the Fuzzy Logic Toolbox of the MatLAB system, the resulting characteristic is the degree of confidence that the DoS attack occurred at the following terms: low; medium; high. Using the open database of NSL-KDD network traffic parameters on the created ANFIS, a study of its error at different affiliation functions on samples of different lengths was carried out using different methods of training optimization. It is determined that the smallest value of the ANFIS error was based on the use of the multiparameter Bell function by the Hybrid learning optimization method, and it is enough to have a training sample of 70 examples.
Local Networks : methodical recommendations for laboratory works
(Ukrainian State University of Science and Technologies, Dnipro, 2022) Pakhomova, Victoria M.; Miroshnychenko, Iryna H.
ENG: Methodological recommendations are aimed at preparing and doing individual laboratory tasks in the discipline «Local Networks» for foreign applicants of Bachelor’s Degree of specialties 123 «Computer Engineering» and 125 «Cybersecurity».
Methodology for Forming Competences in Students of Specialties «Computer Engineering», «Cybersecurity and Information Protection» when Completing a Course Project in the Discipline «Computer Networks»
(ProConferenceOrg in conjunction with Sergeieva&Co, Karlsruhe, Germany, 2025) Pakhomova, Victoria M.
ENG: The proposed methodology «NeuralRoutingNetwork» for the formation of professional and subject competencies of applicants for the degree of «bachelor» in the specialties «Computer Engineering», «Cybersecurity and Information Protection» when performing a course project in the discipline «Computer Networks»: 1) obtaining an idea of the organization of routing in modern computer networks based on the use of the created neural network tool; 2) compiling a configuration of a neural (fuzzy) network for determining routes in a computer network; 3) creating a model of a neural (fuzzy) network in accordance with the compiled structure using the selected neuropackage; 4) preparing samples for training and testing the created neural (fuzzy) network; 5) determining the optimal parameters of the created neural (fuzzy) network; 6) assessing the accuracy of determining routes in a computer network based on the created neural network tool.
Methodology for Learning SQL Injections Based on a Created Software Application for Blended Learning in the Discipline of «Databases»
(ProConferencein conjunction with KindleDPSeattle, Washington, USA, 2025) Pakhomova, Victoria M.; Vichev, Daniyl
ENG: In blended learning for applicants for the bachelor's degree in the specialty «Cybersecurity and Information Protection» in the discipline «Databases», the «Blend_DB_SQLi» methodology is proposed, which involves: studying SQL injections; classifying SQL injections; the impact of SQL injections; methods for detecting and preventing SQL injections; reviewing control examples and performing an individual task according to the given option based on the use of the «SQL_Testing» software application created in Python: 1) INJECTION (SQL injection vulnerability, which allows obtaining hidden data); 2) AUTH (SQL injection vulnerability, which allows bypassing the system login); 3) LEAK (SQL injection vulnerability, which allows unauthorized data leakage); 4) EXAM (performing the task without using comments); preparing the applicant according to the list of questions; passing the test by the applicant.
Methodology for the Formation of Competences of First Degree Holders in the Discipline «Mathematical Foundation of Information Security»
(Sergeieva&Co, Karlsruhe, 2023) Pakhomova, Victoria M.
ENG: The proposed methodology "MathFISLearn" for the formation of competencies of applicants for the degree "bachelor" in distance learning in the discipline "Mathematical foundations of information security": 1) the study of basic mathematical concepts, theorems and methods in the following sections: the theory of divisibility; theory of decomposition; number theory; the theory of lichens and the theory of algebraic structures during lectures conducted using the "Zoom" system, 2) algorithmization and programming for the implementation of: Euclid's algorithm; extended Euclidean algorithm; Fermat algorithm; decomposition of the number by dividing by sampling; sieve of Eratosthenes; Miller's test and organization of relevant research during laboratory work, 3) acquisition of practical skills in solving systems of equations according to the module based on various mathematical approaches and means when performing independent work using recommended sources, 4) elaboration of theoretical material using lecturer presentations and passing testing in the "Lider" system.
Methods of Forming Competencies in Applicants for the Specialty «Cybersecurity» when Performing a Course Assignment in the Discipline «Local Networks»
(Germany, Karlsruhe: Sergeieva&Co, 2023) Pakhomova, Victoria M.
ENG: The methodology of «AttackDetectionLAN» for the formation of professional and subject competencies of applicants for the degree «Bachelor» in the specialty «Cybersecurity» in the course assignment in the discipline «Local Networks» is proposed: 1) obtaining an idea of the network categories of attacks and the corresponding network classes of attacks; 2) configuration of a multilayer neural network to detect network attacks; 3) creation of a neural model in accordance with the composite structure using the selected neuropackage; 4) on the basis of an open NSL-KDD database, preparation of samples for training and testing of the created neural network; 5) determination of the optimal parameters of the created neural network
Methods of Forming Competencies in Applicants for the Specialty «Cybersecurity» when Performing a Course Assignment in the Discipline «Mathematical Foundation of Information Security»
(ProConferenceOrg in conjunction with Sergeieva&Co, Karlsruhe, Germany, 2024) Pakhomova, Victoria M.
ENG: The methodology of "ComparSystem MathFIS" for the formation of professional and subject competencies of applicants for the degree "Bachelor" in the specialty "Cybersecurity" at fulfillment of the course task in the discipline "Mathematical Foundations of Information Security": 1) getting an idea of the system of comparisons of the first degree; 2) the study of fundamental theorems (in particular, the Chinese remainder theorem); 3) analysis of the control example of the solution systems of comparisons by modules; 4) solving an individual problem using the substitution method and the Chinese remainder theorem; 5) formulation of the relevant conclusion.
Models and Method for Estimate Information-Time Characteristics of Real-Time Control System
(Seventh Sense Research Group, 2019) Kosolapov, Anatolii A.
EN: In the work proposes models for describing and calculating the characteristics of automated real-time control systems at the conceptual design stage. The models are based on the proposed notion of a φ - transaction.
Modern Ukrainian Features of the System Design of IT-Architectures of Rehabilitated Enterprises
(Український державний університет науки і технологій, ІВК «Системні технології», Дніпро, 2023) Kosolapov, Anatolii A.
ENG: After the end of martial law in peaceful Ukraine, one of the priority tasks will be the reconstruction of destroyed enterprises and industries. These processes must begin with the conceptual design of the IT architectures of the restored enterprises. However, the successful resolution of these tasks has a number of established difficulties. The paper provides a list of these features, which affect the paradigm shift of computerization and the transition of management systems to socio-computer-integrated systems. These peculiarities require changes in the training of Masters in Computer Engineering and their accelerated training in the new curriculum (as future systems analysts). In order to organize such training, a methodology for conceptual design of IT-architectures, including Soft Skills, is proposed.