Yemeni cities are distinguished by their ancient history and rich traditions in terms of the organization of urban recreation, which are not well studied and therefore are not used in modern city planning. The developed concept of the recreational framework of Sana'a was developed on the basis of data from a comprehensive system analysis of the planning structure of the city, the identification of the national identity of the Yemeni landscaping structure, the integration of climatic, dendrological and landscape conditions, as well as social factors influencing the organization of urban recreations of Sana'a. Based on the analysis data and identified architectural and planning opportunities, the key principles for organizing the "green" recreational frame of the city of Sana'a were proposed.

Keywords: urban planning, urban greening, sustainable development of the city, landscape design, urban environment, reconstruction

The regulation of the stress-strain state of the floor slab is considered in order to choose the optimal design solution for the frame of a unique building. Three variants of design solutions with varying reinforcement of the plate and cross sections of the vertical elements of the frame are proposed. The numerical experiment was performed by the finite element method using the Lira-CAD software package. To improve the accuracy of the results obtained, calculations were made taking into account the nonlinear operation of materials. The computational model of the floor slab includes physically nonlinear shell finite elements. Nonlinear loading was modeled taking into account the creep of concrete. Based on the results of the calculations, the analysis of the deflections of the floor slab and the consumption of materials was performed. The numerical experiment allowed us to propose an optimal design solution for the frame of a unique building.

Keywords: stress-strain state, finite element method, unique building, physical nonlinearity, deformation law, building frame

This article proposes a method for determining the emotional state of a person using a chatbot. The article defines a chat bot, justifies the choice of the type of chat bot, and defines the basic principles of their work. Based on the identified differences in the work of algorithms for determining text by chat bots, the most suitable technology for solving the task is described - working with neural networks.

Keywords: chatbot, neural network, text tone, emotions, augmented reality

A computer simulator for training operators of the technological process of granulating ammophos in a drum granulator dryer is considered. The technological object and the requirements for controlling the granulation process are briefly described. The functions of the simulator, the structure of its mathematical and algorithmic support are given. The software implementation of the simulator is made in the Visual Basic environment.

Keywords: computer simulator, mathematical model, algorithmic support, training of process operators, pelletizing, drum granulator dryer, granule diameter, ammophos pulp

The study of the problem of fretting damage to a mechanical assembly bolted in three dimensions requires the analysis of stress fields in Cartesian coordinates along the angle and radius of contact pads. It also requires determining the location of the crack initiation and propagation. In this study, we will focus on numerical simulation using ANSYS. The results obtained in the form of nodal solutions show in detail the positions of stress concentrations and the formation of the bolted assembly. The contact surface between plates (or contact elements) is characterized by contact pressure, adhesion and clearance. The results obtained made it possible to determine the stress that caused the initiation and propagation of a crack, as well as the position of the damaged area by fretting.

Keywords: bolt assembly, contact modeling, damage zone, fretting, Ramberg-Osgood law, Von Mises stresses

The paper discusses the use of machine learning in relation to natural language processing (sentiment analysis, semantic proximity analysis) to build a recommendation system for the choice of perfumery products. The topic of the work is relevant in view of the growth of the range of manufactured perfumery products and the complexity of its choice by consumers and promotion by manufacturers. The proposed approaches are relevant for solving this problem due to the accumulated textual reviews and reviews of perfumery products on various websites, including online stores.

Keywords: machine learning, natural language, sentiment analysis, distributive semantics, word2vec, recommender systems

The paper considers the problem of bringing vibrations of a flat membrane to rest, controlled by forces applied to the entire area of the membrane and limited in absolute value. Sufficient conditions are given for the initial data of the deviation and velocity of the membrane, under which a complete stop of motion in a finite time is possible. The resting time is also evaluated. The theorem on estimating the eigenfunctions of the Dirichlet problem for the Laplace equation used in the work makes it possible to refine the mentioned sufficient condition in comparison with the work of F.L. Chernousko. In this work, a similar problem is considered, and the method of expanding the unknown control and the corresponding solution in terms of eigenfunctions of the Dirichlet problem for the Laplace equation is also applied. In this paper, the problem of bringing various elastic oscillatory systems with distributed parameters (membrane, rod, plate, etc.) to a state of rest in a finite time is reduced by means of expansion into a Fourier series in the corresponding system of eigenfunctions to the study of the problem of stopping a counting system of pendulums, connected with each other only through the values of external control actions, the sum of the values of which should not exceed in absolute value some given constant. In order to fulfill this limitation, it is necessary to use estimates for the absolute values of the eigenfunctions, normalized in the mean square. In this paper, we use some estimates for the absolute values of eigenfunctions, previously obtained by Eidus D.M. This allows us to refine the results of F.L. Chernousko for sufficient conditions on the initial functions of the oscillatory system, under which we must dampen the oscillations. These conditions consist in the fact that the initial functions belong to Sobolev spaces with certain indices and in the fulfillment of some additional boundary conditions on the boundary of the domain in which the system is defined.

Keywords: control, wave equation, limited distributed force, Fourier method, counting system of harmonic oscillators

The problem of atmospheric air pollution in the regions is considered. Attention is paid to the development and implementation of automated air pollution control systems. The developed information and analytical system has a two-level system and consists of two subsystems: a city information system and a regional information system. The proposed software allows you to perform calculations of surface concentrations of pollutants with the formation of a data bank, as well as the construction of maps of pollution in the region and histograms of the distribution of the level of adverse effects of atmospheric pollution on humans.

Keywords: atmospheric air, pollution, monitoring, information and analytical system, maps of the pollution of the region

The article discusses the stages of entity allocation for constructing an ANN description language that simplifies the exchange of ANN between people. The developed language reduces the task of migrating the ANN between different hardware and software technologies to the task of converting a text description to the required platform, which is much easier to develop intelligent models. As a result of minimizing the set of entities, a language consisting of a dozen and a half tags was obtained that allow describing the most popular ANN models used for classification and pattern recognition tasks.

Keywords: artificial neural networks, neuron, synapse, multilayer perceptron, INSML, forward calculation, mathematical modeling

The article deals with the solution of the problem of unilateral frictional contact on the example of an arched culvert in the embankment. Unilateral contact is modeled as a linear complementarity problem, which is solved using the Lemke method. The features of solving such problems are shown. A comparison with modern approaches is given, the advantages and disadvantages of the proposed method are indicated.

Keywords: constructive nonlinearity, frictional contact, unilateral constraints, linear complementarity problem, numerical models, finite element method, load increment

Compaction is one of the most important technological processes in in the asphalt (AC) pavement construction. Joint management of asphalt pavers and several rollers, allowing each roller to seal the road layer most efficiently with optimal compaction modes to ensure the required compaction quality, is an unsolved problem. To solve this problem, on the basis of modern achievements of scientific and technological progress, a cyberphysical system is proposed as an organizational and technical concept of information flow management. The structure of the system for monitoring and controlling the compaction of AC mixtures with a set of pavers – road rollers is proposed. The development of a cyberphysical road construction system makes it possible, based on digitalization, to effectively manage several road vehicles on the construction sites of road transport infrastructure projects for joint and adaptive compaction.

Keywords: compaction of asphalt mixtures, real-time quality control, road vehicles, cyber-physical system, control system

The paper considers a model for managing the reliability of an intelligent video surveillance system of a protected object. To build a model of the operation of a security television system with video analytics modules, a scheme of a multiphase queuing system was used. The process of constructing a computer model for evaluating the quality indicators of processing information entering the system is described. The given computer model provides an opportunity to assess the reliability of the system in question in a wide range of parameters and can be used in the design, operation and modernization of intelligent video surveillance systems to increase their reliability and ensure the possibility of making effective management decisions.

Keywords: intelligent video surveillance, integrated security, reliability, multiphase queuing system, protected facilities of the Penal System

In a number of branches of agricultural production, including agriculture, land reclamation, etc., there are problems, the solution of which requires the use of artificial intelligence. In particular, the assessment of the reclamation state of agricultural fields in large areas is a very time-consuming task, even with the use of unmanned aerial vehicles. To automate these intelligent approaches, it is effective to use artificial neural networks (INS) implemented in the form of computer programs. The use of software as a service (SaaS) is a modern approach to computer support of various intelligent production processes, including agricultural. Agriculture is a promising industry for the introduction of such technologies. The aim of the study is to develop a methodology and create a cloud-based SaaS system for identifying defective areas of agricultural fields based on INS. The development of neural network technologies and cloud services makes it possible to process a large amount of information in the cloud and provide user access to computing power. The article describes the methodology of building a service architecture for recognizing problem areas of cultivated agricultural fields, data preparation, network training, development of client and server parts. Such implementation is possible with the use of such technologies and tools as CUDA, CNN, PyTorch. As a result, the strengths and weaknesses of their use for solving the problem of image recognition on the example of problem areas of agricultural fields were identified. It has been established that classification-type INS are capable of solving problems of recognizing the reclamation state of fields, and modern information technologies make it possible to transfer calculations to the cloud, while the cloud service can be monetized as a SaaS model.

Keywords: agriculture, color images, SaaS system, artificial neural network, image classification

Artificial intelligence methods can be used to solve the problems of agricultural production. Assessing the condition of crops in large areas, even with the use of unmanned aerial vehicles, is a time-consuming task. The peculiarities of the task of such an assessment are the multifactorial nature of the analyzed structures, which require the use of a systematic approach at all stages of the study from the formation of a database of color images to the intelligent solution of problems of their analysis. The results of the analysis of the U-net architecture of the INS and its limitations for the problem of image segmentation are presented. The purpose of the study is to substantiate the architecture of the segmentation artificial neural network (INS) to identify problem areas of agricultural fields. The hypothesis of the segmentation network advantage was tested on the DeepLabV3 ResNet50 architecture. Numerical experiments have established that the increase in the accuracy of segmentation of images of agricultural fields is constrained by the limited resolution and accuracy of manual markup dataset. The built architectures can be used as an algorithmic core for creating SaaS systems, while the performance of the used configuration of the INS can be crucial.

Keywords: color images, segmentation task, agropole plots, deep neural network, INS architecture, convolutional layers

A review of publications by Russian and foreign researchers on the issues of modeling the process of assessing the degree of security of individual components of an informatization object (automated system) is presented. The main factors influencing the level of security are analyzed. The types of objects of unauthorized influence are given. The choice of the “information carrier” as the main generalized object and the list of actual threats to it are substantiated, their brief analysis is given. As the output (dependent) variable of the developed regression model, the level of information carrier security is determined. The input (independent) variables are the degree of danger of threats: illegal access to protected information; unauthorized copying of protected information; overcoming physical protection; loss of carriers of information. The developed model has the form of a regression equation and can be used to predict the level of security of information carriers.

Keywords: information security, informatization object, automated system, information carriers, information security threats, security level, regression model, expert information, adequacy criteria