Анализ алгоритмов обнаружения дипфейков

Hypergraphs provide a natural framework for representing neurophysiological interactions distributed across sets of sensors. A key methodological question is how hyperedges should be defined from frequency-resolved electroencephalography/magnetoencephalography (EEG/MEG) data. We demonstrate a construction strategy in which hyperedges are obtained from canonical coherence (caCOH), an extension of coherence that estimates coupling between multidimensional signal spaces. To ...

Added: August 18, 2026

Global shifted potentials for moduli stacks of sheaves on Calabi-Yau four-folds

Borisov D., Katzarkov Ludmil, Sheshmani A. et al., American Journal of Mathematics 2026 Vol. 148 No. 4 P. 1075–1101

It is shown that there are globally defined Lagrangian distributions on the stable loci of derived \mathrm{Quot}-stacks of coherent sheaves on Calabi--Yau four-folds. Dividing by these distributions produces perfectly obstructed smooth stacks with globally defined -1-shifted potentials, whose derived critical loci give back the stable loci of smooth stacks of sheaves in global Darboux form. ...

Added: August 18, 2026

Localization in Medical Imaging: A Unified AI Approach for Ovaries, Follicles, and Vertebral Arteries

Moshkin A., Fedorov M., Arlazarov V. et al., Algorithms 2026 Vol. 19 No. 7 Article 523

Artificial intelligence (AI) technologies, which are being actively developed in modern medicine today, increase the speed and quality of patient care. This article mainly seeks to demonstrate the use of various options of computer analysis of clinical images to solve practical problems of increasing the efficiency of routine diagnostics using retrospective analysis, as well as ...

Added: August 17, 2026

Innovation in Medicine and Healthcare

CHEN Y., Howlett R. J., Tanaka S. et al., Springer, 2026.

The Smart Innovation, Systems and Technologies book series encompasses the topics of knowledge, intelligence, innovation and sustainability. The aim of the series is to make available a platform for the publication of books on all aspects of single and multi-disciplinary research on these themes in order to make the latest results available in a readily-accessible ...

Added: August 16, 2026

Вырождение графа, описывающего комплексную структуру

Богатырев А. Б., Математический сборник 2023 Т. 214 № 3 С. 106–119

Рассматривается клеточное разбиение пространства модулей вещественных кривых рода 2 с отмеченной точкой на единственном вещественном овале. Клетки перечисляются определенными графами, веса которых описывают комплексную структуру на кривой. Показано, что стягивание ребра графа приводит к корневой особенности естественного отображения из весов графа в пространство модулей кривых. ...

Added: August 14, 2026

Число компонент уравнений Пелля–Абеля с примитивным решением заданной степени

Богатырев А. Б., Gendron Q., Успехи математических наук 2023 Т. 78 № 1 С. 209–210

Уравнение Пелля-Абеля — это функциональное уравнение вида P²-DQ² = 1, с заданным многочленом D, свободным от квадратов, и неизвестными многочленами P и Q. Мы показываем, что пространство уравнений Пелля-Абеля с фиксированными степенями D и примитивным решением P является комплексным многообразием. Мы описываем его связные компоненты с помощью эффективно вычислимого инварианта. ...

Added: August 14, 2026

Stiefel filters

Богатырев А. Б., Transactions of the Moscow Mathematical Society 2024 Vol. 85 No. 2 P. 323–337

The best uniform rational approximation of the Sign function on two intervals separated by zero was explicitly found by E. I. Zolotarëv in 1877. The natural extension of this problem to three bands was solved by E. Stiefel in 1961. We indicate the solutions overlooked by the prominent geometer and study their properties. ...

Added: August 14, 2026

Вариационная формула в модели Шоттки римановых поверхностей

Богатырев А. Б., Успехи математических наук 2026 Т. 81 № 3(489) С. 159–160

Предложена простая и эффективно реализуемая формула для изменения абелевых интегралов (включая их периоды) при вариации образующих классической группы Шоттки, представляющей риманову поврехность. ...

Added: August 14, 2026

The space of solvable Pell-Abel equations

Gendron Q., Compositio Mathematica 2025 Vol. 161 No. 7 P. 1483–1511

A Pell–Abel equation is a functional equation of the form P^2-DQ^2=1 , with a given polynomial D free of squares and unknown polynomials P and Q. We show that the space of Pell–Abel equations with the degrees of D and of the primitive solution P fixed is a complex manifold. We describe its connected components ...

Added: August 14, 2026

Generative geospatial modelling with geometric algebra

Yu Z., Wang J., Wang Z. et al., Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 2026 Vol. 384 P. 1–16

The integration of data-driven and knowledge-driven approaches in generative geospatial modelling (GGM) is often hindered by their mathematical incompatibilities. Here, we propose a geometric algebra (GA)-based framework that employs a unified multi-vector representation to fuse heterogeneous data and diverse knowledge. The framework facilitates structured reasoning and hypothesis generation through a task-adaptable, five-stage cycle: representation, reasoning, ...

Added: August 13, 2026

Empowering Novel Geometric Algebra for Graphics and Engineering. ENGAGE 2025 (Hong Kong, July 14, 2025), Lecture Notes in Computer Science

Cham: Springer, 2026.

This book constitutes the proceedings of the 10th International Workshop Empowering Novel Geometric Algebra for Graphics and Engineering, ENGAGE 2025, held in conjunction with Computer Graphics International conference, CGI 2025, in Hong Kong, China, on July 14, 2025. The 14 full papers included in this volume were carefully reviewed and selected from 16 submissions. The papers ...

Added: August 13, 2026

Reconstruction of EEG signals using next-generation reservoir computing

Ratnikov F., European Physical Journal: Special Topics 2026 P. 1–10

EEG recordings are often affected by the loss or corruption of individual channels due to electrode detachment, poor scalp contact, or external interference. Such channels must be accurately reconstructed before further analysis. In this study, we investigate Next-Generation Reservoir Computing (NG-RC) as a data-driven approach for reconstructing corrupted EEG channels and compare its performance with ...

Added: August 12, 2026

О замыкающих ординалах инфинитарных вероятностных исчислений

Speranski S. O., Математические заметки 2026 Т. 120 № 3 С. 470–483

We show that, in terms of closure ordinals, many infinitary calculi for ‘first-order’ logics of probability (i.e., for languages similar to those in [Abadi & Halpern 1994]) are as hard as possible: the corresponding closure ordinals coincide with the least non-constructive ordinal, denoted by $\omega_1^{\mathrm{CK}}$. ...

Added: August 12, 2026

CAD2TechSpec: a framework for automating design processes within computer-aided design systems

Minets M., Krasnozhenov G., Trofimova E. et al., PeerJ Computer Science 2026 Vol. 12 Article e4063

This article presents CAD2TechSpec, a novel framework for automating design processes within computer-aided design (CAD) systems by leveraging multimodal large language models (LLMs). The framework enables the analysis and generation of detailed design specifications, including the automated creation of machining process plans. Our system architecture combines 3D model rendering, dimensionality reduction techniques, and the capabilities ...

Added: August 12, 2026

Parametric study of hand dorsal vein biometric recognition vulnerability to spoofing attacks

Мизинов П. В., Journal of Computer Virology and Hacking Techniques 2023 No. 20 P. 383–396

Biometric vein recognition systems are vulnerable to presentation attacks. Traditionally, researchers have used a near-infrared (NIR) drawing of the user’s vascular bed to create a presentation attack instrument (PAI). This paper investigates the feasibility of using free software to capture a venous pattern of the hand without NIR under normal lighting conditions and to create ...

Added: August 11, 2026

Data-Efficient Unsupervised Recalibration of Calorimeter Sensor Arrays Using Wasserstein Adversarial Learning

Ali S., Bocharnikov V., Ratnikov F. et al., Sensors 2026 Vol. 26 No. 16 Article 5024

Large distributed sensor arrays require repeated recalibration as radiation damage, material aging, gain variation, and readout drift alter channel responses. We studied a high-granularity calorimeter as a large sensor array and addressed unsupervised recalibration from two unpaired datasets: a nominal reference response and an aged response with attenuated cell-wise signals. Aging was modeled by a ...

Added: August 11, 2026

Трубочкина, Н. К. Основы технологии производства и машинное обучение : учебник для вузов / Н. К. Трубочкина. — Москва : Издательство Юрайт, 2026. — 383 с. — (Высшее образование). — ISBN 978-5-534-22010-0.

Trubochkina N. K., М.: Издательство «Юрайт», 2026.

This textbook is designed to develop students' holistic understanding of modern production processes and methods for their analysis and management using machine learning technologies. In the context of the fourth industrial revolution, where traditional engineering disciplines are inextricably intertwined with intelligent data processing methods, there is a growing need for specialists capable of integrating knowledge ...

Added: August 8, 2026

Automated detection of wolf howls using audio spectrogram transformers

Makarov N., Savchenko A., Zemtsova I. et al., Scientific Reports 2025 Vol. 15 Article 26641

The grey wolf (Canis lupus) is a pivotal species for ecological studies. As a key participant in ecosystem processes, it also serves as a model for investigating social structure formation and ecological adaptation. However, the species’ complex social behavior, spatial dynamics, and expansive habitats make monitoring and population assessments across large areas particularly challenging. In recent years, audio traps ...

Added: June 16, 2026

Artificial intelligence framework for multi-pathology risk assessment from retinal fundus images: deep learning approach to 15-disease screening

Vasilev R., Savchenko A., Blinov P. et al., Frontiers in Medicine 2026 Vol. 13 Article 1778404

Automated disease screening systems face challenges when applied to multi-class medical image analysis, particularly under severe class imbalance inherent in clinical datasets. Retinal fundus imaging enables non-invasive screening for multiple ocular and systemic diseases simultaneously, yet current automated systems typically assess risk for only a single pathology or a limited disease range. We developed a ...

Added: June 16, 2026

Online Neural Networks for Change-Point Detection

Hushchyn M., Arzymatov K., Derkach D., Machine Learning 2026 Vol. 115 Article 56

Moments when a time series changes its behavior are called change points. Occurrence of change point implies that the state of the system is altered and its timely detection might help to prevent unwanted consequences. In this paper, we present two change-point detection approaches based on neural networks and online learning. These algorithms demonstrate linear ...

Added: March 6, 2026

Image Modification Detections

Kseniia Prokudina, Mikhail Skriplyonok, Alexander Vostrikov, , in: 2026 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM).: IEEE, 2026. P. 842–847.

This article analyzes the evolution of digital image manipulation detection methods over the 2016–2026 decade. It examines the transition from classic passive methods (ELA, metadata analysis, and noise pattern analysis) to deep neural network architectures (VGG16+U-Net, ManTra-Net, SPAN, and RDS-YOLOv5) and then to multimodal systems based on large language models (ForgeryGPT and FakeShield), which provide ...

Added: February 25, 2026

Подходы 3D-реконструкции лица для обнаружения дипфейков

Pikul A. S., В кн.: Новые информационные технологии в научных исследованиях: материалы XХX Всероссийской научно-технической конференции студентов, молодых ученых и специалистов: Т.1Т. 1.: Рязань: Рязанский государственный радиотехнический университет, 2025. С. 232–233.

Современные методы генерации дипфейков достигли высокой степени реализма, что создаёт серьёзные вызовы для систем аутентификации личности и защиты медиаинформации. Большинство существующих подходов к детекции дипфейков основаны на 2D-признаках: текстуре, артефактах лица и цветовых несоответствиях. Однако подобные методы слабо устойчивы к новым генеративным моделям, которые воспроизводят реалистичную геометрию лица. В связи с этим требуется всё больше ...

Added: December 13, 2025