Сучасні інформаційні системи
Постійне посилання на розділhttps://repository.kpi.kharkov.ua/handle/KhPI-Press/62915
Офіційний сайт http://ais.khpi.edu.ua/
У журналі публікуються результати досліджень з експлуатації та розробки сучасних інформаційних систем у різних проблемних галузях.
Рік заснування: 2017. Періодичність: 4 рази на рік. ISSN 2522-9052 (Print)
Новини
Включений до "Переліку наукових фахових видань України, в яких можуть публікуватися результати дисертаційних робіт на здобуття наукових ступенів доктора і кандидата наук" (технічні науки) наказом Міністерства освіти і науки України від 04.04.2018 № 326 (додаток 9, п. 56).
Переглянути
3 результатів
Результати пошуку
Документ Development of a method for assessing the adequacy of a computer system model based on Petri nets(Національний технічний університет "Харківський політехнічний інститут", 2024) Shyman, Anna; Kuchuk, Nina; Filatova, Anna; Bellorin-Herrera, OleksandraThe purpose of modeling any system using a Petri net is to study the behavior of the modeled system based on the analysis of the defined properties of the Petri net. Therefore, it is necessary to develop a method for assessing the adequacy of the model, based on the assessment of the degree of its correspondence to the behavior of the system. The object of research is the behavior of a system model built using a Petri net. The subject of the research is the value of the deviation of the simulated processes from the real values. The goal of the research is to develop a method for assessing the adequacy of the description of the dynamics of the researched process in a model of a computer system based on Petri nets.Conclusions. The developed method makes it possible to assess the adequacy of the model based on Petri nets with accuracy to the entered assumptions. The method allows timely background history of dynamic processes and justify the choice of its length. The method also allows reducing the possibility of an irrational increase in the size of the synthesized model.Документ Practical principles of integrating artificial intelligence into the technology of regional security predicting(Національний технічний університет "Харківський політехнічний інститут", 2024) Shefer, Oleksandr; Laktionov, Oleksandr; Pents, Volodymyr; Hlushko, Alina; Kuchuk, NinaObjective. The aim is to enhance the efficiency of diagnostics for determining the level of air attack safety through the practical integration principles of artificial intelligence. Methodology. Models and technologies for safety diagnostics of the region (territorial community) have been explored. The process of building an artificial intelligence model requires differentiation of objects at a level to accumulate assessments-characteristics of aerial vehicles. The practical integration principles of artificial intelligence into the forecasting technology are based on the Region Safety Index, used for constructing machine learning models. The optimal machine learning model of the proposed approach is selected from a list of several models. Results. A technology for predicting the level of regional safety based on the Safety Index has been developed. The recommended optimal model is the Random Forest model ([('max_depth', 13), ('max_features', 'sqrt'), ('min_samples_leaf', 1), ('min_samples_split', 2), ('n_estimators', 79)]), demonstrating the most effective quality indicators of MAE; MAX; RMSE 0.005; 0.083; 0.0139, respectively. Scientific Novelty. The proposed approach is based on a linear model of the Region Safety Index, which, unlike existing ones, takes into account the interaction of factors. This allows for advantages of the proposed method over existing approaches in terms of the root mean square error of 0.496; 0.625, respectively. In turn, this influences the quality of machine learning models. Practical Significance. The proposed solutions are valuable for diagnosing the level of safety in the region of Ukraine, particularly in the context of air attacks.Документ Generating currency exchange rate data based on Quant-GAN model(Національний технічний університет "Харківський політехнічний інститут", 2023) Bao, Dun; Zakovorotnyi, Oleksandr; Kuchuk, N. G.This paper discusses the use of machine learning algorithms to generate data that meets the demands of academia and industry in the context of exchange rate fluctuations. Research results. The paper builds a Quant-GAN model using temporal convolutional neural networks (CNN) and trains it on end-of-day and intraday high-frequency rates of currency pairs in the global market. The generated data is evaluated using various statistical methods and is found to effectively simulate the real dataset. Experimental results show that data generated by the model effectively fits statistical characteristics and typical facts of real training datasets with good overall fit. The results provide effective means for global FX market participants to carry out various tasks such as stress tests and scenario simulations. Future work includes accumulating data and increasing computing power, optimizing and improving GAN models, and establishing evaluation standards for generating exchange rate price data. As computing power continues to grow, the GAN model’s ability to process ultra-large-scale datasets is expected to improve.