ISSN: 2310-8061
Електронний архів Харківського національного університету радіоелектроніки «ElAr КhNURE» є інституціальним репозиторієм, що містить публікації наукових праць та досліджень науково-педагогічних працівників, інших співробітників, здобувачів вищої освіти ХНУРЕ, а також публікації сторонніх наукових організацій. Серед них монографії, статті з наукових журналів та збірників, матеріали науково-практичних заходів, наукові публікації (розміщуються за умови наявності рецензії наукового керівника) та кваліфікаційні роботи здобувачів вищої освіти (розміщуються за дозволом автора КвР).
З усіх питань звертатися до адміністратора ElAr KhNURE за адресою: yuliia.derevianko@nure.ua
Фонди
Виберіть фонд, щоб переглянути його колекції.
Останні подання
Comparative analysis of models for short-term forecasting of electricity consumption
(2024) Korablyov, M.; Kobzev, I.; Chubukin, O.; Antonov, D.; Polous, V.; Tkachuk, O.
Forecasting electricity consumption is an urgent task, and the solution significantly affects the efficiency of the use of energy resources. The paper considers short-term forecasting of electricity consumption, which predicts the amount of energy that will be used in a short period, from several hours to several days in advance. There are various short-term forecasting models, so it is important to reasonably choose a model that provides analysis and effective forecasting of electricity consumption to optimize the use of energy resources. The purpose of the work is to analyze the main forecasting models, such as statistical models (autoregressive model, moving average, exponential smoothing, moving average with autoregression and integration) and deep learning models (artificial neural network, recurrent neural network, long short-term memory, transformer), indicating their advantages and disadvantages, and choosing the best of them. The experimental results of a comparative analysis of power consumption forecasting models are presented, which showed that the transformer model was 1.5% - 2% more effective in power consumption forecasting according to various metrics. Its higher level of accuracy, reflected in low error values and high coefficient of determination, indicates its high adaptability to the dynamics of electricity consumption.
Immune Model for Controlling Characters in Computer Games
(CEUR Workshop Proceedings (CEUR-WS.org), 2023) Korablyov, M.; Fomichov, O.; Chubukin, O.; Antonov, D.; Dykyi, S.
The rapid development of information technologies led to the emergence of new opportunities for game software developers. In the field of game application development, a large number of platforms and patterns of architecture development, as well as game environments, have appeared, which allow simplifying and automating the process of development and deployment of the game software. The game application used in the work simulates a futuristic space world where the player interacts with other characters in a free game space. An analysis of game resources, which can be controlled by the player and other game characters, has been carried out. The main features of the behavior of game characters controlling spaceships on the map of the game world are defined. The task of controlling the behavior of characters in game software can be considered as a classification problem, for which it is proposed to use artificial immune systems. Among the existing immune models, the most promising for practical application is the artificial immune network model, which was chosen as the basis for creating a model for controlling the behavior of characters in computer games. But it cannot be used to solve the problem of managing game characters without additional modifications. A modified model of the immune network – behavioral aiNET (baiNET) was proposed, which can be used to solve the problem under consideration. The software implementation of the game software tool, in which the control of the game characters is carried out using the baiNET model, has been completed. Experimental studies were carried out with different numbers of game characters on different-sized maps of the game world, which showed that the proposed baiNet
immune model is effective and simple to implement and modify. This makes it possible to use it to control characters in games of other genres.
Peculiarities of Cs1-xRbxCu2Cl3 Solid Solutions Absorption Spectra
(Eskisehir Technical University, 2023) Kovalenko, O.; Yunakova, O.; Yunakov, N.
Автоматизація вибору компонентів інформаційного захисту локальних обчислювальних мереж
(ХНУРЕ, 2024) Житник, В. Ю.; Усов, О. О.; Харченко, Н. А.
Метою доповіді є створення концепції програмного комплексу, що на основі аналізу мережі дозволить формувати оцінку захищеності мережі.
Enhancing Information Transmission Methods Using Femtosecond Radiation
(2024) Hnatenko, O. S.; Chaplyhin, V.; Kravchuk, O.
In telecommunications, there is increasing interest in developing stable sources for the third fiber optic transmission window, particularly ring fiber lasers with passive mode-locking. Erbium-doped optical fibers, operating at a wavelength of 1550 nm, play a key role in this field. It is expected that these lasers will eventually replace many semiconductor data transmission lasers used in Dense Wavelength Division Multiplexing (DWDM) systems according to the ITU frequency grid.