Електронний репозитарій ПДАУ
Полтавський державний аграрний університет
Електронний репозитарій (сховище, архів) наукових публікацій – електронний архів результатів науково-дослідної роботи, публікацій науковців, викладачів, аспірантів та студентів університету, кваліфікаційних робіт студентів для їх централізованого зберігання та надання відкритого доступу до них світовій академічній спільноті у режимі онлайн.
Нові надходження
Method of Assessing the State of Hierarchical Objects based on Bio-Inspired Algorithms
(Advanced Information Systems, 2023) Odarushchenko, O. B.; Одарущенко, Олена Борисівна
Nowadays, no state in the world is able to work on the creation and implementation of artificial intelligence in isolation from others. Artificial intelligence technologies are actively used to solve both general and highly specialized tasks in various spheres of society. In the process of assessing (identifying) the state of complex and objects of analysis and management, there is a high degree of a priori uncertainty regarding their state and a small amount of initial data describing them. At the same time, despite the huge amount of information, the degree of non-linearity, illogicality and noisy data is increasing. That is why the issue of improving the efficiency of assessing the condition of complex and objects is an important and urgent issue. The object of research is the objects of analysis. The subject of the research is the identification and forecasting of the analysis objects state with the help of bio-inspired algorithms. In the research, the evaluation and forecasting method was developed using fuzzy cognitive maps and the genetic algorithm.
Application of Formal Verification Methods in a Safety-Oriented Software Development Life Cycle
(Proceedings of the 13th IEEE Conference Dependable Systems, Services and Technologies, DESSERT2023, Athens, Greece, 2023-10-14) Odarushchenko, O. B.; Одарущенко, Олена Борисівна
This article delves into the growing significance of ensuring reliability and functional safety in hardware and embedded software of programmable controllers amidst rapid technological advancement. With the rise of FPGA-based digital Instrumentation and Control Systems (ICS), the need for dependable solutions has led to the development of the RadICS FSC (Functional Safety Controller) Platform by LLC RPC Radiy. While programmable controllers are pivotal across industries, vulnerabilities in their embedded software can lead to dire consequences for safety, economy, and the environment, particularly in safety-critical applications. Given this backdrop, testing embedded software becomes integral to ensuring reliability and safety. Tailored testing approaches are essential due to the unique characteristics of hardware, software, and specific controller applications. These approaches must encompass functional aspects as well as potential vulnerabilities exploitable by malicious actors.
Development of a solution search method using an improved locust swarm algorithm
(Eastern-European Journal of Enterprise Technologies, 2023-10-30) Odarushchenko, O. B.; Одарущенко, Олена Борисівна
The object of the research is deci¬sion support systems. The subject of the research is the decision-mak¬ing process in management problems using the locust swarm algorithm and evolving artificial neural networks.
A solution search method using an improved locust swarm algo¬rithm is proposed. The research is based on the locust swarm algorithm for finding a solution regarding the state of an object. For training locust agents (LA), evolving artificial neu¬ral networks are used. The method has the following sequence of steps:
– input of initial data;
– processing of initial data tak¬ing into account the degree of uncer¬tainty;
– initial setting of LA in the search area;
– determination of the initial speed of the LA movement;
– a search vector is generated taking into account the degree of uncertainty;
– calculation of the change in the value of the LA fitness function;
– training of LA knowledge bases.
The originality of the proposed method lies in the arrangement of LA taking into account the uncertainty of the initial data, improved proce¬dures of global and local search tak¬ing into account the degree of noise of data about the state of the analy¬sis object. Also, the originality of the research is avoiding the concentra¬tion of LA on the current best posi¬tions, reducing the probability of pre¬mature conv/ ergence of the algorithm and maintaining a balance between the convergence rate of the algorithm and diversification. The peculiarity of the proposed method is the use of an improved procedure for LA training. The training procedure consists in learning the parameters and archi¬tecture of individual elements and the architecture of the artificial neural network as a whole.
Актуальність та проблеми застосування електронного документообігу в економічній експертизі
(2026) Чабанюк, О.; Лега, Ольга Василівна
У статті досліджено актуальність та проблеми застосування електронного документообігу (ЕДО) в процесі проведення економічної експертизи. Розглянуто сутність та функціональне значення ЕДО в системі управління підприємством і судово-експертній діяльності. Систематизовано основні джерела електронних документів (бухгалтерські програми, банківські системи, податкову звітність та системи електронних закупівель) та визначено переваги їх використання експертами. Виявлено й класифіковано ключові групи проблем застереження ЕДО (правові, технічні, організаційні, інформаційні), пов’язані з надійністю доказової бази, кібербезпекою та ідентифікацією автентичності цифрових слідів. Запропоновано комплексні шляхи підвищення ефективності використання електронних документів в економічній експертизі через удосконалення законодавства, стандартизацію методик і підвищення кваліфікації експертів.
Improvement of the Optimization Method based on the Wilk Flock Algorithm
(Eastern-European Journal of Enterprise Technologies, 2023) Protas, N. M.; Odarushchenko, O. B.; Vakulenko, Y. V.; Degtyareva, L. M.; Протас, Надія Михайлівна; Одарущенко, Олена Борисівна; Вакуленко, Юлія Валентинівна; Дегтярьова, Лариса Миколаївна
The problem that is solved in the research is to increase the efficien¬cy of decision making in management tasks while ensuring the given reliabili¬ty, regardless of the hierarchical nature of the object. The object of the research is decision making support system. The subject of the research is the decision making process in management tasks using an improved wolf flock algorithm. The hypothesis of the research is to increase the efficiency of decision making with a given assessment reliability. In the course of the research, an improved opti¬mization method based on an improved wolf flock algorithm was proposed. In the course of the conducted research, the general provisions of the theory of arti¬ficial intelligence were used to solve the problem of analyzing the objects state and subsequent parametric management in intelligent decision making support systems.