Наукові статті
Постійне посилання зібранняhttps://repository.lntu.edu.ua/handle/123456789/310
Переглянути
2 результатів
Результати пошуку
Item type:Наукова стаття, Architectural And Engineering Aspects Of Integrating The Novita Ai Api Into A Web Application For Image Generation(Lutsk: LNTU, 2026-03-28) Povstiana, Yuliia; Lishchyna, Nataliia; Surynovych, Olena; Boiko, LevThis paper investigates architectural and software engineering approaches to integrating the Novita AI image generation service into a web-based application that supports scalable and asynchronous request processing. The proposed solution is based on a clear separation of responsibilities between frontend and backend components, where the backend handles validation, orchestration of long-running tasks, interaction with external APIs, and data persistence. Communication is implemented using REST for synchronous operations and WebSocket-based notifications for asynchronous updates, while resource-intensive tasks are executed through a queue-based mechanism to prevent interface blocking. Integration with the Novita AI service is encapsulated within a dedicated service layer, ensuring modularity, maintainability, and extensibility. An experimental evaluation was conducted to measure execution times of key operations, including image generation, transformation, upscaling, and custom model training. The results confirm the effectiveness of asynchronous processing and demonstrate that custom models improve output consistency at the cost of a minor increase in generation time. The novelty of this study lies in the architectural justification of asynchronous API integration for AI-based image generation with support for custom model training, validated through experimental performance evaluation.Item type:Наукова стаття, Architecture And Experimental Evaluation Of A Cross-Platform Mobile Application For Adaptive Learning Using Large Language Models(Lutsk: LNTU, 2026-05-29) Povstiana, Yuliia; Samchuk, Lyudmila; Lishchyna, Nataliia; Boiko, LevThe paper addresses the design and experimental evaluation of the architecture of a cross-platform mobile application for adaptive foreign language learning using large language models. An architectural approach based on a dedicated AI Integration Layer is proposed, enabling the separation of business logic and improving the reliability of interaction with external AI services. The system implements adaptive content generation considering individual user characteristics. Special attention is given to performance optimization through the implementation of a multi-level caching mechanism, which reduced AI service usage costs by 74 % and decreased response latency. An experimental evaluation of system performance demonstrated stable operation under a load of up to 100 concurrent users with an average response time of 280-500 ms, and identified a degradation threshold at 160-170 users. The obtained results confirm the effectiveness of the proposed approach and its applicability for developing modern mobile educational systems based on large language models.