Перегляд за Автор "Molchanova M."

Зараз показуємо 1 - 2 з 2
  • Ескіз
    Документ
    Representative Samples Forming of Urban Aerial and Satellite Imagery for Building Footprint Segmentation
    (2025) Vit R.; Molchanova M.; Mazurets O.; Мазурець, Олександр Вікторович
    This paper presents an approach to forming representative training samples of urban aerial and satellite imagery for building footprint segmentation. It is shown that the performance and generalization ability of convolutional neural networks strongly depend not only on dataset size, but also on controlled coverage of urban scene variability, imaging conditions, and annotation conventions. The proposed methodology combines large-scale satellite benchmarks with polygon footprint labels and aerial imagery from unmanned platforms as complementary domains, explicitly addressing domain shift, occlusions, and perspective distortions. Sample representativeness is assessed through the training and validation behavior of YOLO-family segmentation models, including convergence stability and metric profiles. The experimental results demonstrate stable learning dynamics and the presence of challenging boundary cases typical of real urban environments, confirming the effectiveness of the proposed data formation strategy for robust building footprint segmentation in practical geospatial applications.
  • Ескіз
    Документ
    Software architecture of information system for exchanging LLM thematic prompts
    (2025) Denysenko, B.; Shevchuk, P.; Molchanova M.; Mazurets, O.; Мазурець, Олександр Вікторович
    The article presents the design of a software architecture for an information system focused on the exchange of thematic prompts for large language models. As the use of LLMs grows across various domains, the need for a structured platform to manage, share, and evaluate prompts becomes critical for productivity, reproducibility, and collaboration. The system is based on the MVC architectural pattern (Laravel framework) and includes key modules for authentication, prompt management, subscription/payment handling, and administration. The proposed solution enables role-based access, prompt versioning, user feedback, and integration with LLM APIs, laying the foundation for scalable, collaborative, and transparent prompt engineering