Analysis of Precision of Finding the Destroyed Remains Buildings on Photos using MobileNetV3 and ViT Neural Networks

Скорочена інформація про документ
dc.contributor.authorDydo, R.
dc.contributor.authorSobko, O.
dc.contributor.authorMolchanova, M.
dc.contributor.authorMazurets, O.
dc.contributor.authorМазурець, Олександр Вікторович
dc.date.accessioned2025-05-26T12:49:33Z
dc.date.available2025-05-26T12:49:33Z
dc.date.issued2025
dc.description.abstractThis study presents a comparative analysis of the precision and recall of MobileNetV3 and Vision Transformer (ViT) neural networks in detecting destroyed building remains from photographic data. Using a curated dataset of disaster-zone images, both models were trained and evaluated on key performance metrics. Results show that while both architectures performed well, ViT consistently achieved higher accuracy and generalization, particularly in complex material classes. The findings support the use of ViT in high-precision post-disaster assessment systems and highlight its potential for integration into automated, real-time damage detection platforms.
dc.identifier.citationDydo R., Sobko O., Molchanova M., Mazurets O. Analysis of Precision of Finding the Destroyed Remains Buildings on Photos using MobileNetV3 and ViT Neural Networks. Science and Technology: New Horizons of Development. Proceedings I International Scientific and Practical Conference. May 14-16, 2025. Prague, Czech Republic. Pp. 208-214
dc.identifier.urihttps://elar.khmnu.edu.ua/handle/123456789/18383
dc.language.isoen
dc.titleAnalysis of Precision of Finding the Destroyed Remains Buildings on Photos using MobileNetV3 and ViT Neural Networks
dc.typeСтаття
Файли
Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
Prague_Czech-Republic_14.05.25-209-215.pdf
Розмір:
343.1 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