Approach for Comparative Analysis of Effectiveness of using MobileNetV3 and ViT Neural Network Models for Graphical Localization of Destroyed Buildings Remains Areas

Скорочена інформація про документ
dc.contributor.authorDidur, V.O.
dc.contributor.authorMolchanova, M.O.
dc.contributor.authorTyschenko, O.O.
dc.contributor.authorMazurets, O.V.
dc.contributor.authorМазурець, Олександр Вікторович
dc.date.accessioned2025-05-26T12:51:23Z
dc.date.available2025-05-26T12:51:23Z
dc.date.issued2025
dc.description.abstractThis study presents a comparative analysis of MobileNetV3 and Vision Transformer (ViT) neural networks for graphical localization of destroyed building remains. A custom software solution was developed to process images from robotic systems, train both models on a labeled dataset, and evaluate their performance in realistic conditions. Results showed that both architectures achieved high accuracy, with ViT offering strong classification precision and MobileNetV3 excelling in efficiency for edge deployment. The findings highlight each model's potential for disaster response applications involving automated debris analysis.
dc.identifier.citationDidur V.O., Molchanova M.O., Tyschenko O.O., Mazurets O.V. Approach for Comparative Analysis of Effectiveness of using MobileNetV3 and ViT Neural Network Models for Graphical Localization of Destroyed Buildings Remains Areas. Formation of Innovative Potential of World Science. Proceedings IX International Scientific and Practical Conference. May 16, 2025. Waterford, Republic of Ireland. Pp. 94-97
dc.identifier.urihttps://elar.khmnu.edu.ua/handle/123456789/18384
dc.language.isoen
dc.titleApproach for Comparative Analysis of Effectiveness of using MobileNetV3 and ViT Neural Network Models for Graphical Localization of Destroyed Buildings Remains Areas
dc.typeСтаття
Файли
Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
123-186-PB-95-98.pdf
Розмір:
275.63 KB
Формат:
Adobe Portable Document Format
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Назва:
license.txt
Розмір:
4.26 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити
Зібрання
Кафедра комп’ютерних наук