Факультет комп’ютерних та інформаційних технологій
Постійне посилання на фондhttps://repository.lntu.edu.ua/handle/123456789/49
Переглянути
10 результатів
Результати пошуку
Item type:Наукова стаття, Modern Programming Technologies in the Tasks of Identification and Classification of Military Aircraft Using Machine Learning Algorithms(Lublin: Lublin University of Technology, 2024-12-16) Terletskyi, Taras; Kaidyk, OlehThis article addresses the development of an intelligent military aircraft identification system using artificial intelligence, machine learning, and deep self-learning technologies to enhance national security and military efficiency. The system aims to automatically and accurately recognize and classify aircraft in images, offering advantages over traditional methods such as higher productivity, speed, accuracy, and the elimination of human error. The importance of deep learning solutions for threat detection and operational efficiency is emphasized. Modern visual data-based object recognition methods and tools are analysed. The methodology includes collecting and preprocessing data, developing a high-precision recognition system based on Yolov8, annotating objects with Roboflow, and creating training, validation, and testing subsets in the yolo format. The paper details the dataset formation process and presents satisfactory results in fast recognition of military aircraft with high classification accuracy. A comparative analysis of Yolov8, R-CNN, and GPT-4 models shows Yolov8's superiority in prediction accuracy and performance. The article describes the model management system for adjusting hyperparameters, selecting object categories, and initiating the training and forecasting process. Testing results demonstrate Yolov8's optimality for military aircraft identification, achieving accurate target identification in complex situations using advanced deep learning algorithms.Item type:Наукова стаття, Solving operational tasks in the design of video surveillance systems(2025) Bahniuk, Natalia; Terletskyi, Taras; Kaidyk, Oleh; Kostiuchko, Serhii; Kondius, InnaThe article discusses the problem of CCTV design, which consists in the constant change of recommended criteria for equipment selection caused by the continuous and rapid evolution of technologies. The results of the analysis of existing standards are presented and discrepancies are identified. This trend leads to the destabilization of clear quality criteria and the risk of unreasonable CCTV design. The paper highlights the methods and results of research into changes in the spatial resolution of images from a range of technical characteristics of video cameras based on the relevant theory, which is implemented analytically and confirmed by computer modeling using specialized software. The results of the study, obtained by calculation and modeling, indicated a general discrepancy in the data obtained, which does not exceed the permissible limits. The data presented in the study results will help designers make an informed choice of video cameras, which will reduce the risk of excessive design.Item type:Наукова стаття, Multiprocessing as a Way to Optimize Queries. Advances in Transdisciplinary Engineering(2024) Khrystynets, Natalia; Melnyk, Kateryna; Lavrenchuk, Svitlana; Miskevych, Oksana; Kostiuchko, SerhiiDeveloping an effective web application involves the use of various methods and techniques to ensure fast and efficient processing of requests. Sometimes it is not possible to solve the problem of multiprocessing with a single tool, such as a programming language or framework. This work investigates the use of asynchronous methods of processing requests using queues. Job operation in background and non-background modes relative to the main web process is studied. Analytics are provided to analyze a web application with 13,000 requests to process daily. It is proposed to optimize the processing by using the Laravel framework and the Python server dual-tasking using the Supervisor tool on Linux, as well as using a task scheduler for each task. The paper presents positive findings about this algorithm, which contributes to the efficiency of web development and provides a great user experience on the website. Fast processing of web application requests can be a valuable competitive advantage for a business or organization. Research in this field helps to maintain their high competitiveness. In addition, the study of query processing speed is important in scientific research, as it contributes to the development of new algorithms, optimization methods and technologies.Item type:Наукова стаття, Effective Content Moderation Using Modern AI Tools(2024) Bortnyk, Kateryna; Bahniuk, Nataliia; Kondius, Inna; Melnyk, Kateryna; Melnychuk, Yuliia; Kondius, KostiantynIn the paper we develop a web application that integrates AI capabilities for content moderation, while providing an effective and balanced user protection system based on general comparative analysis of two leading tools for content moderation: Microsoft Content Moderator and Google Perspective API. Moderation mechanisms using AI algorithms have been developed, allowing not only to filter unwanted content, but also to adapt to changing conditions and user needs. We present the comparison results of two language models of Google Perspective API and Microsoft Content Moderator and appropriate tools taking into account the specific helpful, honest, harmless criteriums that is aligned with human values and include emotional tonality supported by developers.Item type:Наукова стаття, Model of formalized information security audit of an organization with a critical infrastructure facility for compliance with international security standards(CEUR-WS, 2025) Lishchyna, Nataliia; Lishchyna, Valerii; Kozubtsov, Igor; Yashchuk, AndriiThe article emphasizes the importance of conducting information security audits for information systems of critical infrastructure organizations. Effective protection is ensured by aligning security systems with international standards. The audit monitors and assesses compliance but remains effective only when performed regularly by trained specialists. Due to the routine nature of audits and wartime constraints, such as power outages and loss of communication, AI-based methods are often impractical. Therefore, the authors propose a temporary solution using formalized security assessment criteria with clear indicators for objective verification. The study develops a methodology for conducting audits aligned with international standards, addressing the lack of practical guidance in existing ones. It also analyzes global regulatory documents to identify typical management approaches and proposes an adaptable checklist-based methodology covering 10 key information security areas, particularly useful for organizations operating under wartime conditions. © 2025 Copyright for this paper by its authors.Item type:Наукова стаття, The system of dynamic optimization pricing by machine learning(Greece, 2024) Konotopchyk, Artem; Melnyk, Kateryna; Lavrenchuk, Svitlana; Khrystynets, Nataliia; Melnyk, Pavlo; Melnyk, Pavlo; Bortnyk, KaterynaBased on the real retail data collected over eight months, a number of models are developed to determine the most efficient machine learning algorithm. It is found that the KNeighbors Regressor model demonstrates the best performance for a small number of transactions, achieving a low MSE of 0.00091 and a high R2 of 0.72 in the validation set. For a large number of transactions, Random Forest Regressor and Decision Tree Regressor show the best ability to capture complex relationships and handle nonlinearties in the data, thanks to the ensemble learning technique. Whereas the Linear Regressor and Support Vector Regressor models demonstrated large deviations from the real price on the test data. The results of the study demonstrate the relevance of rtificial intelligence algorithms in dynamic pricing trategies, showing the ability to quickly process huge amounts of data, taking into account numerous factors and changes in market demand.Item type:Наукова стаття, Threats detection and analysis based on SYSMON tool(2023) Bahniuk, Nataliia; Linchuk, Oleksandr; Bortnyk, Kateryna; Kondius, Inna; Melnyk, Kateryna; Kondiu, KostiantynIn this work, an nalysis for the study of threats in a real environment with the possibility of conducting a fullfledged analysis of threats, as well as their simulationhas been developed for research purposes. Designed laboratory was built for the threats research, specification of deploying and configuring Sysmon, imitation of an attack in laboratory conditions and its investigation by implicit signs, the processesing of threat analysis using the Sysmon tool. We present a system based on the analysis of continuous input chan-nels of Sysmon logs. The system is based on the Cyber Threat Analysis Ontology and analyzes SYSMON logs to classify software according to different threat levels and enhance cyber defense capabilities with situational awareness, prediction and auto-mated actions. The developed laboratory improves the effectiveness of threat analysis using the Sysmon tool, makes study of threats, deploying and configuring Sysmon, imitation of an attack in laboratory conditions and its investigation by implicit signs. It can be applied for the study of threats in a real environment with the possibility of conducting a full-fledged analysis of threats, as well as their simulation for research purposes.Item type:Наукова стаття, Development of network traffic monitoring system elements using Deep Learning(Piscataway, NJ: IEEE, 2024) Melnyk, Vasyl; Bahniuk, Nataliia; Bortnyk, Kateryna; Kondius, Inna; Zubovetska, Nataliia; Kondius, KostiantynIn this article we develop a network traffic monitoring system elements using deep learning that demonstrates the high effectiveness of deep learning in detecting and analyzing network traffic, which contributes to ensuring the security and stability of corporate networks. In this context we develop algorithms for detecting and countering potential threats in network traffic, providing deeper analysis and effective response to cyber threatsItem type:Наукова стаття, Business information system for forecasting raw material stocks for the production of flexible packaging(Greece, 2024-10-11) Здолбіцька, Ніна Василівна; Ostapchuk, Oleksandr; Лавренчук, Світлана Василівна; Терлецький, Тарас Володимирович; Кайдик, Олег Леонтійович; Zhyharevych, OksanaA specialized information system of the enterprise has been developed for forecasting and raw materials ordering, which allows for the optimization of warehouse stocks of raw materials and reduces the risks of under-fulfillment of orders for finished products. It is important to control warehouse stocks and orders for basic raw materials of pure film. The essence of control comes down to constant monitoring of raw material balances in warehouses, and forecasting orders for base films in advance, since the execution of raw material deliveries is also stretched from two weeks to several months. The developed program automatically takes into account the available balance of raw materials in warehouses, the ordered quantity, and the required quantity according to forecasts, which improves the raw materials turnover ratio in warehouses. As customer expectations and behavior change dynamically, having such demand forecasting software empowers companies and helps them respond quickly to changes. An analytical decision-making mechanism based on a weighting function that provides the degree of raw material relevance for an order has been proposed. Recommendations have been given for choosing weighting function coefficients. The research results have been implemented in a business process at an enterprise engaged in the production of flexible packaging. The advantage of this system is the userfriendly interface, in particular the advisory component regarding the need and number of orders.Item type:Наукова стаття, Multiprocessing as a Way to Optimize Queries(IOS Press, 2024-02-13) Христинець, Наталія Анатоліївна; Мельник, Катерина Вікторівна; Лавренчук, Світлана Василівна; Міскевич, Оксана Іванівна; Костючко, Сергій МиколайовичDeveloping an effective web application involves the use of various methods and techniques to ensure fast and efficient processing of requests. Sometimes it is not possible to solve the problem of multiprocessing with a single tool, such as a programming language or framework. This work investigates the use of asynchronous methods of processing requests using queues. Job operation in background and non-background modes relative to the main web process is studied. Analytics are provided to analyze a web application with 13,000 requests to process daily. It is proposed to optimize the processing by using the Laravel framework and the Python server dual-tasking using the Supervisor tool on Linux, as well as using a task scheduler for each task. The paper presents positive findings about this algorithm, which contributes to the efficiency of web development and provides a great user experience on the website. Fast processing of web application requests can be a valuable competitive advantage for a business or organization. Research in this field helps to maintain their high competitiveness. In addition, the study of query processing speed is important in scientific research, as it contributes to the development of new algorithms, optimization methods and technologies.