Enhanced ANN-based ensemble method for bridge damage characterization using limited dataset

Autor: Ivan Izonin, Illia Nesterenko, Athanasia K. Kazantzi, Roman Tkachenko, Roman Muzyka, Stergios Aristoteles Mitoulis

Publikováno v: Scientific Reports, Vol 14, Iss 1, Pp 1-10 (2024)

Abstract Bridges are vital assets of transport infrastructure, systems, and communities. Damage characterization is critical in ensuring safety and planning adaptation measures. Nondestructive methods offer an efficient means towards assessing the co

Externí odkaz: https://doaj.org/article/5cb4a8ae18c8472ab2eb2ab51bc1f17f

An interpretable ensemble structure with a non-iterative training algorithm to improve the predictive accuracy of healthcare data analysis

Autor: Ivan Izonin, Roman Tkachenko, Kyrylo Yemets, Myroslav Havryliuk

Publikováno v: Scientific Reports, Vol 14, Iss 1, Pp 1-14 (2024)

Abstract The modern development of healthcare is characterized by a set of large volumes of tabular data for monitoring and diagnosing the patient's condition. In addition, modern methods of data engineering allow the synthesizing of a large number o

Externí odkaz: https://doaj.org/article/0519662a8bfd4dd8ae6b98908eb2beb7

The experimental study of glass multilayer columns using digital image correlation

Autor: Mykhailo Surmai, Roman Tkach, B. Demchyna

Publikováno v: Archives of Materials Science and Engineering. 1:32-41

Purpose: The purpose of the research is to study the deformability of glass multilayer columns at the central compression using digital image correlation. It becomes possible to use the method of digital image correlation for the experimental study o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d66f1c6fa3485022c6714371c206560a
https://doi.org/10.5604/01.3001.0013.1990

Enhanced Input-Doubling Method Leveraging Response Surface Linearization to Improve Classification Accuracy in Small Medical Data Processing

Autor: Ivan Izonin, Roman Tkachenko, Pavlo Yendyk, Iryna Pliss, Yevgeniy Bodyanskiy, Michal Gregus

Publikováno v: Computation, Vol 12, Iss 10, p 203 (2024)

Currently, the tasks of intelligent data analysis in medicine are becoming increasingly common. Existing artificial intelligence tools provide high effectiveness in solving these tasks when analyzing sufficiently large datasets. However, when there i

Externí odkaz: https://doaj.org/article/e4e0628ada11463dbf82e60153f6d744

Impact of thermal annealing on photoacoustic response and heat transport in porous silicon based nanostructured materials

Autor: Pavlo Lishchuk, Guillaume Castanet, Vladimir Lysenko, Fabrice Lemoine, Roman Tkach, K. Dubyk, Roman Ostapenko, David Lacroix, A. G. Kuzmich, Mykola Isaiev, Ali Belarouci, Svitlana Naumenko, Vasyl Kuryliuk

Publikováno v: THERMOPHYSICS 2019: 24th International Meeting of Thermophysics and 20th Conference REFRA
THERMOPHYSICS 2019: 24th International Meeting of Thermophysics and 20th Conference REFRA, Oct 2019, Smolenice, Slovakia. pp.020008, ⟨10.1063/1.5132727⟩
AIP Conference Proceedings
AIP Conference Proceedings, American Institute of Physics, 2019, THERMOPHYSICS 2019: 24th International Meeting of Thermophysics and 20th Conference REFRA, pp.020008. ⟨10.1063/1.5132727⟩

International audience; Features of heat transport in silicon-based porous structures with different morphology before and after thermal annealing are investigated. Specifically, fractal-like porous silicon and silicon nanowire arrays samples were co

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::928b9611121c6ebcb215ec45550e5f3c
https://hal.archives-ouvertes.fr/hal-02397960