Results 21 to 30 of about 50 (50)

Reference-based diffusion model for super-resolution

Научно-технический вестник информационных технологий, механики и оптики
This article is devoted to digital image processing algorithms, namely, super-resolution task. Currently, various methods of image restoration based on deep learning are actively developing.
A. K. Denisov, S. V. Bykovskii, P. V. Kustarev   +2 more
doaj   +1 more source

Prospects of machine learning applications in affective disorders

Digital Diagnostics
Mental disorders are a significant medical and social issue globally. Currently, approximately 970 million individuals suffer from mental disorders, with over 300 million diagnosed with depression or bipolar disorder. Recently, there has been significant
Ekaterina S. Mosolova, Alexander E. Alfimov, Elena G. Kostyukova, Sergey N. Mosolov   +3 more
doaj   +1 more source

Polynomial function selection in Kolmogorov-Arnold Networks for medical image segmentation with limited data

Научно-технический вестник информационных технологий, механики и оптики
Modern methods for processing medical images are mostly based on convolutional neural networks and transformer architectures. A major issue is the large number of parameters in existing neural network models, which leads to high computational resource ...
G. Yu. Manzhos, I. V. Tomilov, N. F. Gusarova, Yu. O. Valitova   +3 more
doaj   +1 more source

Роль искусственного интеллекта в прогнозировании трудных дыхательных путей у взрослых: обзор литературы

Вестник интенсивной терапии
ВВЕДЕНИЕ: Развитие искусственного интеллекта (ИИ) открыло возможность его применения в практике анестезиолога на направлении, связанном с развитием наиболее жизнеугрожающих осложнений — прогнозировании трудных дыхательных путей.
Андрей Юрьевич Зайцев, А. Б. Сорокин, Ю. А. Зайцев, К. В. Дубровин, Э. Г. Усикян   +4 more
doaj   +1 more source

Explainability and interpretability are important aspects in ensuring the security of decisions made by intelligent systems (review article)

Научно-технический вестник информационных технологий, механики и оптики
The issues of trust in decisions made (formed) by intelligent systems are becoming more and more relevant. A systematic review of Explicable Artificial Intelligence (XAI) methods and tools aimed at bridging the gap between the complexity of neural ...
D. N. Biryukov, A. S. Dudkin
doaj   +1 more source

Review of deep learning methods for imaging photoplethysmography data processing

Научно-технический вестник информационных технологий, механики и оптики
This paper presents a review of contemporary deep learning methods for processing remote photoplethysmography data. Architectures of convolutional neural networks, transformers, recurrent, and generative models are examined for video signal preprocessing
I. M. Rubin, M. A. Volynsky
doaj   +1 more source

Цифровая реставрация объектов монументального искусства с применением методов компьютерного зрения и машинного обучения

Современные инновации, системы и технологии
В статье исследуется возможность применения библиотеки OpenCV (реализованной на языке программирования Python) для цифровой реставрации объектов монументального искусства.
А. А. Грейс, И. В. Ковалев, А. А. Ворошилова   +2 more
doaj   +1 more source

Entity-level classification of adverse drug reactions: a comparison of neural network models

Труды Института системного программирования РАН, 2018
This paper presents our experimental work on neural network models for entity-level adverse drug reaction (ADR) classification. Aspect-level sentiment classification, which aims to determine the sentimental class of a specific aspect conveyed in user ...
I. S. Alimova, E. V. Tutubalina
doaj  

Deep learning-enhanced contour interpolation techniques for 3D carotid vessel wall segmentation

Научно-технический вестник информационных технологий, механики и оптики
When studying human vessels using the contour interpolation method, there is a problem of insufficient data for training neural networks for automatic segmentation of the carotid artery wall.
N. Ismail, A. S. Vatian, T. A. Polevaya, A. A. Golubev, D. A. Dobrenko, A. A. Zubanenko, N. F. Gusarova, A. G. Vanyurkin, M. A. Chernyavskiy   +8 more
doaj   +1 more source

An optimized deep learning method for software defect prediction using Whale Optimization Algorithm

Научно-технический вестник информационных технологий, механики и оптики
The goal of this study is to predict a software error using Long Short-Term Memory (LSTM). The suggested system is an LSTM taught using the Whale Optimization Algorithm to save training time while improving deep learning model efficacy and detection rate.
A. Aliyu Aihong, B. Imam Ya’u, U. Ali, A. Ahmad, M. Abdulrahman Lawal   +4 more
doaj   +1 more source