The article analyzes the wind directions and speeds typical for compact and linear cities over 5 years using the example of Stavropol and Volgograd, respectively. The results of the analysis allowed us to state that the wind direction and speed can be considered as random variables. Based on this approach, the regularities of the repeatability of wind speeds depending on the direction and time of day are investigated.

Keywords: linear city, cities of compact configuration, wind speed and direction, wind rose, distribution laws, atmospheric air, climatic parameters, Weibull's law, logarithmically normal law, mixed Gaussian distribution

The article deals with the distribution of air flow velocities for cities of compact configuration on the example of the city of Stavropol. The verification of the implementation of Weibull's law for different wind flow velocities in its various directions has been carried out.

Keywords: wind flow direction and velocity, atmospheric air, distribution law, Weibull's law, mixed Gaussian distribution, change in air flow velocities, time of day, compact city

This study analyzes classical machine learning methods applied to the prediction of corporate bond yield spreads. Both linear methods, such as Principal Component Analysis and Partial Least Squares, and nonlinear methods, such as copula regression and adaptive regression splines, are examined. The study also explores the potential application of Random Forest models and classical neural networks. It includes a description of the data used for forecasting and presents some results of the empirical analysis. The findings have the potential to significantly impact practitioners and the scientific community striving to improve forecasting accuracy and optimize investment strategies.

Keywords: Machine Learning, Financial Engineering, Stock Market Modeling, Bond Market

During the production of delicatessen canned fish, the control system should ensure a gentle heat treatment regime with a decrease in the degree of temperature exposure to the product. Changing the modes requires reconfiguration of the type and parameters of temperature regulators in the autoclave, carried out based on the results of processing modeling. The software complex for modeling the object and control system during pasteurization provides for calculating the degree of sterilizing effect. The complex contains system and application softwares. The application modules implement the functions of a graphical interface, a virtual controller, numerical simulation of product temperature changes and data transmission. The virtual controller allows select controllers: positional, proportional-integral-differential, and states. The novelty of the model lies in the display and the possibility of changing both the parameters of the regulator and the coefficients of the desired polynomial, taking into account the sign of the derivative of temperature during heating and cooling. The practical value of the work is to reduce the time for reconfiguring the autoclave control system, ensuring a reduction in the degree of temperature exposure when a given sterilizing effect is achieved by selecting the type and parameters of temperature control rules.

Keywords: software complex, modeling, control system, pasteurization, canned fish, regulator, temperature

The step-by-step construction of a computer model of the process of long-angle drawing of profile pipes is considered. The minimum dimensions of the blanks have been determined, the use of which ensures the necessary dimensions of the finished product. The scheme of applying a deforming force with size adjustment in the current state during step-by-step deformation is taken into account. Geometric and finite element models have been obtained that make it possible to find all the parameters of the deformation site during the drawing process.

Keywords: dimensions of the workpiece, profile pipe, boundary conditions, load application, physical model, finite element grid

Modernization of university campuses in the context of the development of domestic higher education and science to increase the technological sovereignty of the country is one of the pressing problems of modern domestic architecture. The article examines the features of the modern scientific and educational process in higher education and, on their basis, defines the architectural aspects of modernization of existing university campuses.

Keywords: modernization, university campus, modern educational process, university campus model

The issue of development and practical application of the developed methodological support for grinding control based on automated assessment of the dynamic quality of the machine tool based on integral estimates of the autocorrelation function of oscillations and its relationship with the quality of processing of bearing ring raceways is considered.

Keywords: grinding control, vibroacoustic oscillations, automated measurements, stochastic characteristics, dynamic quality of the machine, bearing rings, quality of processing

Modern simulation model design involves a wide range of specialists from various fields. Additional resources are also required for the development and debugging of software code. This study is aimed at demonstrating the capabilities of large language models (LLM) applied at all stages of creating and using simulation models, starting from the formalization of dynamic systems models, and assessing the contribution of these technologies to speeding up the creation of simulation models and reducing their complexity.The model development methodology includes stages of formalization, verification, and the creation of a mathematical model based on dialogues with LLMs. Experiments were conducted using the example of creating a multi-agent community of robots using hybrid automata. The results of the experiments showed that the model created with the help of LLMs demonstrates identical outcomes compared to the model developed in a specialized simulation environment. Based on the analysis of the experimental results, it can be concluded that there is significant potential for the use of LLMs to accelerate and simplify the process of creating complex simulation models.

Keywords: Simulation modeling, large language model, neural network, GPT-4, simulation environment, mathematical model

The article discusses the application of neural network autoencoder in the problem of monochrome image colorization. The description of the network architecture, the applied training method and the method of preparing training and validation data is given. A dataset consisting of 540 natural landscape images with a resolution of 256 by 256 pixels was used for training. The results of comparing the quality of the outputs of the obtained model were evaluated and the average coefficients of metrics as well as the mean squared error of the VGG model outputs are presented.

Keywords: neural networks, machine learning, autoencoder, image quality analysis, colorization, CIELAB

Within the framework of the urban environment, the laws of distribution of the concentration of fine dust PM2.5, PM10 along road sections have been obtained. These data are necessary to assess the probability of exceeding the maximum permissible concentrations and to improve monitoring and control systems for atmospheric air. The analysis of the key factors influencing the content of PM2.5 and PM10 particles in the air of the territories adjacent to the roads has been carried out. Regression equations for total dust, PM2.5 and PM10 dust were obtained, allowing us to conclude that the concentration of PM2.5 and PM10 depends on total dust. The analysis showed that the mass content of PM10 in total dust pollution ranges from 73 to 81%, and the concentration of fine dust PM2.5 varies within two narrow ranges of about 11.6 and about 7 microns. A study of the proportion of PM2.5 of the total concentration showed that it is on average about 20%.

Keywords: dust, emissions, concentration, atmospheric air, roadway, climate, linear city, correlation coefficient, influencing factors

The article analyses the current state of automated control systems for street lighting: advantages and disadvantages, problems faced by manufacturers and operators of such systems. The article describes the basic principles of automated control systems, such as the use of motion sensors, light sensors and communication technology to optimise the operation of street lighting. The article also discusses the features and problems of designing street lighting based on automated lighting control systems, and possible problems associated with their implementation and operation.

Keywords: lighting control, digital twin, automation, sensor, light sources, LED lighting fixture

The article provides a brief description of the existing methods of vectorization of texts in natural language. The evaluation is described by the method of determining the similarity of words. A comparative analysis of the operation of several vectorizer models is carried out. The process of selecting data for evaluation is described. The results of evaluating the performance of the models are compared.

Keywords: natural language processing, vectorization, word-form embedding, semantic similarity, correlation

The article offers a variant of the development of lighting design projects for outdoor architectural lighting. Based on the modeling of light distribution in the DIALux 4.13 program, brushes have been created using specific lighting devices that simulate lighting effects from real lighting devices. A variant of the sketch of outdoor architectural lighting using Adobe Photoshop has been created with the implementation of local lighting techniques using the example of a drama theater building. Using a three-dimensional model of the object, a light design project was created in the DIALux EVO program. The proposed method of creating sketches is useful in professional activities related to the development of sketches of lighting design projects based on their high-quality photographs without the need to develop three-dimensional models, for conceptual proposals of fragments of the urban light environment and landscape territories. Having developed a base of brushes (based on real light distributions of lighting devices), it is possible to create sketches of architectural lighting of buildings that implement various lighting techniques.

Keywords: adobe photoshop, dialux 4.13, dialux evo, sketch, brush, building facade, outdoor architectural lighting, lighting effect, lighting technique, architectural lighting concept

The purpose of this work is to study the applicability of the U-Net architecture for automatically determining the contours of natural skins using the TensorFlow and Keras libraries in Python. A software application has been developed based on methods including OpenCV libraries, as well as a model for implementing a deep convolutional neural network. The dataset for training and testing the network was created using augmentation. Training was carried out using the stochastic gradient descent method after splitting the data sample into training and test images. In the future, the results obtained will be used to create an automated system that will make it possible to determine the contours of the skin and its defects, which in turn will open up the possibility of calculating the useful area of ​​the skin and creating an automated layout of patterns taking into account the identified defects.

Keywords: computer vision, edge detection, natural skin, machine learning, convolutional neural networks, U-Net architecture, deep learning

As the space industry accelerates the trend to reduce development and production costs and simplify the use of space hardware, small spacecraft, including CubeSats, have become popular representatives of this trend. Over the last decade, the development, production and operation of small spacecraft has become in demand because of a number of advantages: simplicity of design, short design and production times, and reduced development costs. The main problem in the design of CubeSats is their miniaturisation. This paper presents the results of the development of the optical cell of collecting and processing video information for remote sensing systems of the CubeSat 3U format satellite, with the aim of obtaining the maximum possible image characteristics, taking into account the strict physical limitations of the CubeSat unit. In the course of the work, using computer-aided design systems Altium Designer and Creo Parametric, the structural diagram, electrical circuit diagram, topology, 3D model, as well as the design of the housing of the cell of collection and processing of video information were developed. PCB size: 90x90 mm, PCB thickness: 1.9 mm, number of PCB layers: 10, accuracy class: 5, cell height: 20 mm, cell weight: 110 grams.

Keywords: space hardware, Earth remote sensing, small spacecraft, nanosatellite, printed circuit board, small satellite development trend, printed circuit board topology, CubeSat