deep learning

Review of disease identification methods based on computed tomography imagery

Methods and approaches to computational diagnosis of various pulmonary diseases via automated analysis of chest images performed with computed tomography were reviewed. Google Scholar database was searched with several queries focused on deep learning and machine learning chest computed tomography imagery analysis studies published during or after 2017. A collection of 39 papers was collected after screening the search results. The collection was split by publication date into two separate sets based on the date being prior to or after the start of the COVID-19 pandemic.

Numerical simulation by Deep Learning of a time periodic p(x)-Laplace equation

The objective of this paper is to focus on the study of a periodic temporal parabolic equation involving a variable exponent $p(x)$.  After proving the existence and uniqueness of the solution, we provide a method for its numerical simulation using emerging deep learning technologies.

Embedding physical laws into Deep Neural Networks for solving generalized Burgers–Huxley equation

Among the difficult problems in mathematics is the problem of solving partial differential equations (PDEs).  To date, there is no technique or method capable of solving all PDEs despite the large number of effective methods proposed.  One finds in the literature, numerical methods such as the methods of finite differences, finite elements, finite volumes and their variants, semi-analytical methods such as the Variational Iterative Method, New Iterative Method and others.  In recent years, we have witnessed the introduction of neural networks in solving PDEs.  In this w

Physics-informed neural networks for the reaction-diffusion Brusselator model

In this work, we are interesting in solving the 1D and 2D nonlinear stiff reaction-diffusion Brusselator system using a machine learning technique called Physics-Informed Neural Networks (PINNs).  PINN has been successful in a variety of science and engineering disciplines due to its ability of encoding physical laws, given by the PDE, into the neural network loss function in a way where the network must not only conform to the measurements, initial and boundary conditions, but also satisfy the governing equations.  The utilization of PINN for Brusselator system is stil

Utilization of Voice Embeddings in Integrated Systems for Speaker Diarization and Malicious Actor Detection

This paper explores the use of diarization systems which employ advanced machine learning algorithms for the precise detection and separation of different speakers in audio recordings for the implementation of an intruder detection system. Several state-of-the-art diarization models including Nvidia’s NeMo, Pyannote and SpeechBrain are compared. The performance of these models is evaluated using typical metrics used for the diarization systems, such as diarization error rate (DER) and Jaccard error rate (JER).

RESEARCH OF PLANT DISEASE DIAGNOSTIC METHODS USING DEEP LEARNING

The article explores the use of convolutional neural networks (CNNs) in the diagnosis and identification of plant diseases and pests. Various methods of plant disease diagnosis, features of datasets, and challenges in this research direction are considered. The article discusses a five-step methodology for determining plant diseases, including data collection, preprocessing, segmentation, feature extraction, and classification. Different deep learning architectures enabling fast and efficient plant disease diagnosis are investigated.

INTRACRANIAL HEMORRHAGE SEGMENTATION USING NEURAL NETWORK AND RIESZ FRACTIONAL ORDER DERIVATIVE-BASED TEXTURE ENHANCEMENT

This paper explores the application of the U-Net architecture for intracranial hemorrhage segmentation, with a focus on enhancing segmentation accuracy through the incorporation of texture enhancement techniques based on the Riesz fractional order derivatives. The study begins by conducting a review of related works in the field of computed tomography (CT) scan segmentation. At this stage also a suitable dataset is selected.

Research of the models for sign gesture recognition using 3D convolutional neural networks and visual transformers

The work primarily focuses on addressing the contemporary challenge of hand gesture recognition, driven by the overarching objectives of revolutionizing military training methodologies, enhancing human-machine interactions, and facilitating improved communication between individuals with disabilities and machines. In-depth scrutiny of the methods for hand gesture recognition involves a comprehensive analysis, encompassing both established historical computer vision approaches and the latest deep learning trends available in the present day.

SYSTEM FOR DETERMINING THE SOUND SOURCE COORDINATES

The authors investigated the effect of changes in the acoustic signal propagation speed and the accuracy of sensor positioning on the accuracy of sound source localization. The mean absolute error grows with the displacement of the microphones relative to the nominal coordinates (X, Y). The same trend is observed with an increase in the actual acoustic signal velocity deviation from the velocity under normal environmental conditions.