ISSN: 2310-8061
Репозиторій Харківського національного університету радіоелектроніки «ElAr КhNURE» є електронною платформою, що містить публікації наукових праць та досліджень науково-педагогічних працівників, інших співробітників, здобувачів вищої освіти ХНУРЕ. 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 в ElAr
Виберіть фонд для перегляду його колекцій.
Останні подання
Тип документа:Публікація, Methods for Preventing Overfitting in Microclimate Forecasting Tasks(2026) Yevsieiev, V.; Holod, I.The paper addresses the problem of overfitting in neural network models used for forecasting microclimate parameters in industrial facilities. It is shown that in microclimate control systems overfitting leads not only to reduced forecasting accuracy, but also to unstable control actions, increased energy consumption, and accelerated wear of actuators. The main focus is on NNARX-type neural network models, which use historical values of input and output parameters and are sensitive to limited and uneven training data. Practical methods for preventing overfitting are analyzed, including Dropout, weight regularization, and training data variation. The applicability of Dropout in the hidden layer of NNARX without violating autoregressive relationships is substantiated. It is shown that the combined use of these methods makes it possible to improve forecast stability, ensure smoother control signals, and enhance the reliability of intelligent microclimate control systems under real industrial operating conditions.Тип документа:Публікація, Data Analysis and BI in Business Environment: Further Development and Online Tools(ХНУРЕ, 2025) Tokhtamysh, N.; Polozov, О.; Khalina, V.; Romanovych, A.In chapter a comparison of Business Intelligence (BI) and Business Analytics (BA) systems is provided. It was considered several platforms of Business Intelligence. A few examples of brands that have successfully leveraged BA and BI to gain a competitive edge and drive business success were given. Each brand’s specific use cases may vary, but they all share a commitment to data-driven decision-making and extracting valuable insights from their data assets.Тип документа:Публікація, Прямі іноземні інвестиції у цифровий розвиток: досвід ЄС та України(ХНУРЕ, 2025) Тохтамиш, Н. І.; Герасимюк, Д. Ю.; Романович, А. М.Розглянуто проблеми сталих іноземних інвестицій у центри обробки даних, хмарну інфраструктуру, кібербезпеку, платформи електронного урядування, дослідження та розробки систем штучного інтелекту.Тип документа:Публікація, Intelligent Cyber-Physical Modules for Monitoring Digital Protection of Production Facilities for Use in Emergency Situation(2026) Chala, O.; Borodai, Y.This paper highlights the intermediate results of research related to the development, design, and implementation of intelligent cyber-physical monitoring modules for digital protection of production facilities for use in emergencies. This allows for data processing directly on devices (at the "edge" of the network) to minimize delays in critical situations. The use of Digital Twins will ensure continuous synchronization of a physical object with its digital model for simulating emergency response scenarios without risk to real production. The research results provide insights into the initial aspects of designing and developing intelligent cyber-physical modules for monitoring digital protection in production for use in emergencies, which could be useful for researchers and developers in the fields of production automation, civil security, and emergency response robotics.Тип документа:Публікація, Using Quantum Computings During Collaborative Mobile Robot Trajectory Constructing(2025) Yevsieiev, V. V; Maksymova, S. S.; Starodubcev, M. G; Demska, N. PThe article considers a method for constructing a trajectory of a collaborative mobile robot using quantum computing in combination with classical optimization algorithms. The purpose of the study is to develop a mathematical model and numerical simulation of a quantum-oriented approach to constructing a trajectory of a collaborative robot, which allows minimizing energy costs in motion planning and ensuring obstacle avoidance in a dynamic environment. The scientific novelty of the work lies in the application of quantum optimization methods for multivariate planning, which allows avoiding local minima and guaranteeing the search for globally optimal solutions even in the case of complex configuration spaces. During the numerical simulation, it was demonstrated that the formed trajectories ensure successful obstacle avoidance and reaching the target point without deviations from the grid. Conclusions: analysis of the results showed stabilization of the energy function at the level of −350…−420, which confirms the effectiveness of optimization and convergence to the best solutions after 100–150 iterations. The constructed graphs confirmed that the robot’s movement is consistent with the calculated quantum plans, and the deviation between the predicted and executed trajectories is minimized. The use of the energy efficiency criterion allowed us to evaluate different route construction scenarios, where the best plans stabilized with a margin of optimality relative to the worst options by 15–20%. Qualitative analysis of the constructed trajectories confirmed the consistency between the predicted and executed paths, and quantitative results proved a reduction in the number of steps when reaching the target point. The results obtained prove that the proposed method is promising for constructing reliable and energy-optimal trajectories in collaborative robotic systems Industry 5.0.