Alexander Selivanov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alexander Selivanov has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Aleksei V. Semenov
National Research Lobachevsky State University of Nizhny Novgorod
1 shared publication Andrei Bortnikov
Central Institute of Aviation Motors, Moscow, Russia
1 shared publication- Artem Shelmanov
AIRI
1 shared publication - Boris Vasilyev
Central Institute of Aviation Motors, Moscow, Russia
1 shared publication Daniil Chesakov
1 shared publication- Dmitry V. Dylov
Artificial Intelligence Research Institute, Moscow, Russian Federation and Skolkovo Institute of Science and Technology, Moscow, Russian Federation
1 shared publication
Latest Publications
- Open Access
Medical Image Captioning via Generative Pretrained Transformers
The automatic clinical caption generation problem is referred to as proposed model combining the analysis of frontal chest X-Ray scans with structured patient information from the radiology records. We combine two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The proposed combination of these models generates a textual summary with the essential information about pathologies found, their location, and the 2D heatmaps localizing each pathology on the original X-Ray scans. The proposed model is tested on two medical datasets, the Open-I, MIMIC-CXR, and the general-purpose MS-COCO. The results measured with the natural language assessment metrics prove their efficient applicability to the chest X-Ray image captioning.
Open AccessMedical Image Captioning via Generative Pretrained Transformers
The automatic clinical caption generation problem is referred to as proposed model combining the analysis of frontal chest X-Ray scans with structured patient information from the radiology records. We combine two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The proposed combination of these models generates a textual summary with the essential information about pathologies found, their location, and the 2D heatmaps localizing each pathology on the original X-Ray scans. The proposed model is tested on two medical datasets, the Open-I, MIMIC-CXR, and the general-purpose MS-COCO. The results measured with the natural language assessment metrics prove their efficient applicability to the chest X-Ray image captioning.
- 21 September 2020
- Published by ASME International
Determining the Optimal Crystallographic Orientation in a Single Crystal Turbine Blade to Increase its Strength Reliability
The high-pressure turbine blades of most modern gas turbine engines are made of single-crystal alloys. Single-crystal materials have significant anisotropy characteristics; therefore, the orientation of the axes of the single crystal relative to the geometrical axes of the blade has a great effect on the stress-strain state, static strength, and dynamic characteristics of the blade. Here, the necessary optimization of both the axial orientation (the optimal value of which may differ from ) and the azimuthal orientation is confirmed. The problem was solved by considering the anisotropic temperature–orientation characteristics of the alloy and the uneven temperature field of the blade. The values of the optimal crystallographic orientations were determined. Notably, casting tolerances for the deviation of the crystallographic axes must be considered when searching for the optimal position of the axes of the single crystal.
- 21 September 2020
- Published by ASME International
Determining the Optimal Crystallographic Orientation in a Single Crystal Turbine Blade to Increase its Strength Reliability
The high-pressure turbine blades of most modern gas turbine engines are made of single-crystal alloys. Single-crystal materials have significant anisotropy characteristics; therefore, the orientation of the axes of the single crystal relative to the geometrical axes of the blade has a great effect on the stress-strain state, static strength, and dynamic characteristics of the blade. Here, the necessary optimization of both the axial orientation (the optimal value of which may differ from ) and the azimuthal orientation is confirmed. The problem was solved by considering the anisotropic temperature–orientation characteristics of the alloy and the uneven temperature field of the blade. The values of the optimal crystallographic orientations were determined. Notably, casting tolerances for the deviation of the crystallographic axes must be considered when searching for the optimal position of the axes of the single crystal.