The article describes the process of developing a volumetric display for information and communication interaction in the Arctic, where traditional means of visualization and communication face the challenges of extreme climate, isolation and limited infrastructure. An analysis of the main areas of using volumetric in the Arctic zone is carried out. The main disadvantages of methods for creating a volumetric image in existing 3D displays are considered. Taking into account the main tasks to be solved - creating the illusion of a three-dimensional object for a group of people (more than 2 people) at a wide viewing angle - a description and analysis of two main developed configurations of the optical system is given, the latter of which meets the requirements, ensuring stable operation in Arctic conditions and opening up prospects for implementation in remote and hard-to-reach regions of the Far North.

Keywords: volume display, arctic zone, 3D image, system analysis, lens, optical system, computer modeling

This article discusses the implementation features of named entity recognition models. In the course of the work, a number of experiments were conducted with both traditional models and well-known neural network architectures, a hybrid model, the features of the results, their comparison and possible explanations are considered. In particular, it is shown that a hybrid model with the addition of a bidirectional long short-term memory can give better results than the basic bidirectional representation model based on transformers. It is also shown that, improved by adding a thinning layer for regularization, a weighted loss function and a linear classifier on top of the outputs, a bidirectional representation model based on transformers can give high metric values. For clarity, the work provides graphs of model training and tables with metrics for comparison. In the process of work, conclusions and recommendations were formed.

Keywords: text analysis, artificial intelligence, named entity recognition, neural networks, deep learning, machine learning

The work is devoted to the analysis of machine learning methods for solving problems of automatic document processing. The study considers such methods as classification, information extraction, pattern recognition and natural language processing and their application in the analysis of text data. An analysis of existing algorithms and models, including linear models, decision trees, support vector methods, and a comparison of their effectiveness depending on various conditions and parameters is carried out. Particular attention is paid to the problems that specialists face when using machine learning methods in working with documents, such as data quality, the need for pre-processing and tuning of model parameters. Prospects for further research in this area and examples of possible integration of modern machine learning methods to improve the efficiency and accuracy of automatic document processing in various industries are given.

Keywords: machine learning, automatic document processing, computational experiment, artificial intelligence, classification models, software package

Currently, special attention is paid to artificial intelligence systems in transport. One of the actual directions is the development of self-driving car. However, there is also an intermediate approach. When the control is not fully automatic and automated. In such systems a human plays an important role, but the system, analyzing data from the environment, allows to form various kinds of recommendations. Moreover, such systems allow to work on the warning in some situations. In particular, some driver monitoring systems allow to detect the fact of smoking while driving, turning your eyes away from the road. In this article, special attention is paid to the system of analysis of the driver's eyes. First of all, the results of such analysis can be used to determine the fact of falling asleep. However, by analyzing, the frequency of blinks, it is possible to predict sleep. Nevertheless, computing power is needed to build such a system. In this work, the performance is achieved by using Haar cascades and the Viola-Jones method in eye detection. The eyes detected in the video are images of a much smaller size compared to the whole frame of the video sequence, due to which high performance is achieved in their processing by the convolutional network in the next step. Structurally, the system consists of two neural networks operating in parallel for the left and right eyes. The obtained values of completeness are about 90%.

Keywords: computer vision, artificial intelligence, security system, face detector, deep learning, target skipping, proportion of correct recognition, driver monitoring, eye recognition, Viola-Jones method, Haar cascades, optimization