https://repository.hneu.edu.ua/handle/123456789/172 Mon, 20 Apr 2026 05:43:23 GMT 2026-04-20T05:43:23Z https://repository.hneu.edu.ua/handle/123456789/39444 Назва: A systematic approach to comparative analysis of software testing methods Автори: Brynza N. Короткий огляд (реферат): The paper presents a systematic approach to the comparative analysis of software testing methods, including manual, automated, and intelligent testing. The relevance of software quality assurance and the complexity of selecting an appropriate testing method depending on project conditions are emphasized. A methodology based on criteria such as cost, defect detection accuracy, and execution time is proposed. The study outlines key stages, including data collection, modeling, and experimental validation using modern tools and machine learning technologies. Thu, 01 Jan 2026 00:00:00 GMT https://repository.hneu.edu.ua/handle/123456789/39444 2026-01-01T00:00:00Z https://repository.hneu.edu.ua/handle/123456789/39401 Назва: Small Language Models for perplexity-based text classification Автори: Gorokhovatskyi O. Короткий огляд (реферат): The research explores the use of Small Language Models (SLMs), specifically those with 1B parameters or fewer, to classify text as either AI-generated or human-written in the Ukrainian language. By leveraging perplexity – a measure of a model's uncertainty – as a key feature, the study evaluates the performance of models like Gemma 3 and Llama 3.2. The authors further propose a classification method using Convolutional Neural Networks (CNN) trained on token-level probability vectors, achieving accuracy rates up to 0.8559. Thu, 01 Jan 2026 00:00:00 GMT https://repository.hneu.edu.ua/handle/123456789/39401 2026-01-01T00:00:00Z https://repository.hneu.edu.ua/handle/123456789/39400 Назва: Shallow Neural Networks for classifying Ukrainian AI-generated content Автори: Peredrii O. Короткий огляд (реферат): This research addresses the challenge of detecting AI-generated content in Ukrainian IT-related documents. The study highlights the unreliability of commercial detectors on Ukrainian text and proposes a custom tool utilizing shallow Artificial Neural Network (ANN) models. Using a custom dataset of over 5,000 text fragments, the researcher developed five model architectures (M1-M5) that achieve 87-88% test accuracy. The tool provides two levels of analysis – Chunk Reports and Sentence Reports – to assist educators in identifying potential AI usage without relying on automated decision-making. Thu, 01 Jan 2026 00:00:00 GMT https://repository.hneu.edu.ua/handle/123456789/39400 2026-01-01T00:00:00Z https://repository.hneu.edu.ua/handle/123456789/39120 Назва: Robust decentralization of information management systems Автори: Udovenko S. G.; Zatkhey V. A.; Teslenko O. V. Короткий огляд (реферат): An approach to determining control influences for a decentralized information management system that ensure its robustness to structural disturbances is considered. An algorithm for selecting a suboptimal strategy for forming controls over system objects is proposed. Wed, 01 Jan 2025 00:00:00 GMT https://repository.hneu.edu.ua/handle/123456789/39120 2025-01-01T00:00:00Z