Перегляд за Автор "Sineglazov, Viktor Mykhailovych"

Зараз показуємо 1 - 2 з 2
  • Ескіз
    ДокументВідкритий доступ
    Platform for Medical Data Processing and Treatment Plan Management
    (Igor Sikorsky Kyiv Polytechnic Institute, 2025) Damaskina, Olena Ihorivna; Sineglazov, Viktor Mykhailovych
    Master’s thesis: 122 pages, 2 figures, 2 tables, 70 references, 2 appendices. The object of research is the processes of medical data processing, integration, and management in modern healthcare information systems using artificial intelligence technologies. The subject of research is architectural, algorithmic, and software methods for developing medical platforms for medical data processing, medical image analysis, treatment plan formation and management, as well as quality assurance and validation of AI components. The purpose of the research is to develop and study a platform for medical data processing and treatment plan management with integrated artificial intelligence and Explainable AI modules, ensuring reliability, interpretability of results, and data quality control. The relevance of the research is driven by the rapid digital transformation of healthcare and the increasing volume of medical data, particularly medical images, which require automated, reliable, and interpretable processing. At the same time, significant challenges remain related to data integration, data quality, AI result validation, and compliance with regulatory requirements. The scientific novelty of the research consists in: (1) a systematic approach to the design of a medical platform covering the full medical data lifecycle; (2) integration of AI-based medical image analysis with Explainable AI mechanisms to improve transparency and trust in the results; (3) formalization of quality control and validation points at different levels of the system architecture. The practical value of the research lies in the developed prototype of a medical platform that can be used for medical data processing, ophthalmological image analysis, and support of treatment plan management processes. The proposed architecture provides modularity, scalability, compliance with medical data standards, and the ability to integrate with existing healthcare information systems.
  • Ескіз
    ДокументВідкритий доступ
    SpectralCA: Hybrid Neural Network for UAV-Based Hyperspectral Landmine Detection
    (Igor Sikorsky Kyiv Polytechnic Institute, 2025) Brovko, Danil Vitaliiovych; Sineglazov, Viktor Mykhailovych
    Master's dissertation: 111 p., 29 figures, 20 tables, 41 references, and 2 appendices. The relevance of this research lies in the growing demand for unmanned aerial vehicles (UAVs) capable of operating reliably in complex environments where conventional navigation becomes unreliable due to interference, poor visibility, or camouflage. Hyperspectral imaging (HSI) provides unique opportunities for UAV-based computer vision by enabling fine-grained material recognition and object differentiation, which are critical for navigation, surveillance, agriculture, and environmental monitoring. The object of the study is hyperspectral image classification. The subject of the research is development of a high-performance deep learning architecture for a classification task in hyperspectral imaging. The purpose of this work is to modify the Mobile 3D Vision Transformer (MDvT) by introducing the proposed SpectralCA block. This block employs bi-directional cross-attention to fuse spectral and spatial features, enhancing accuracy while reducing parameters and inference time. Experimental evaluation was conducted on the WHU-Hi-HongHu dataset, with results assessed using Overall Accuracy, Average Accuracy, and the Kappa coefficient. The findings confirm that the proposed architecture improves UAV perception efficiency, enabling real-time operation for navigation, object recognition, and environmental monitoring tasks. Versions of this work were published in arXiv and presented at the 2025 IEEE 8th International Conference on Methods and Systems of Navigation and Motion Control. Also, this research won first place at the 2025 International Student Research Competition in Artificial Intelligence.