The article is devoted to the application of modern methods of generative image compression using variational autoencoders and neural network architectures. Special attention is paid to the analysis of existing approaches to image generation and restoration, as well as a comparative assessment of compression quality in terms of visual perception and metric indicators. The aim of the study is to systematize deep image compression methods and identify the most effective solutions based on the variational Bayesian approach. The paper considers various architectures, including conditional autoencoders and hypernetwork models, as well as methods for evaluating the quality of the data obtained. The main research methods used were the analysis of scientific literature, a comparative experiment on the architectures of generative models and a computational estimation of compression based on metrics. The results of the study showed that the use of variational autoencoders in combination with recurrent and convolutional layers makes it possible to achieve high-quality image recovery with a significant reduction in data volume. The conclusion is made about the prospects of using conditional variational autoencoders in image compression tasks, especially in the presence of additional information (for example, metadata). The presented approaches can be useful for developing efficient systems for storing and transmitting visual data.

Keywords: variational autoencoders, generative models, image compression, deep learning, neural network architectures, data recovery, conditional models

The issue of developing a prototype for an unmanned aerial vehicle (UAV) and creating a control system based on a computer-aided design (CAD) model as part of a project for inspecting construction sites is under consideration. Special attention has been paid to constructing a computer model of a quadcopter. Based on existing methods, energy calculations have been performed and a process for synthesizing controllers in orientation and positioning control circuits has been proposed, considering the sampling rate of the sensors utilized. The outcomes obtained through modeling confirm the suggested algorithm for adjusting controllers. The solution can be utilized by students and professionals in the development of autonomous UAVs or their computer models.

Keywords: quadcopter, computer modeling, PD controller synthesis, UAV design, stereo camera, room inspection

This article reveals the features of the operation of information and measuring systems during gas transportation. The issues reflected in the article are particularly relevant in the context of the need to achieve the efficiency of information and measuring systems in the oil and gas industry. The purpose of the scientific research is to develop an approach to information and measuring systems in oil and gas organizations based on the digital twin model. To achieve this goal, the article analyzes practical cases of information and measuring systems in oil and gas organizations, reflects the features of certification of information and measuring systems used in oil and gas organizations, and presents the results of developing an approach to information and measuring systems in oil and gas organizations based on the digital twin model.

Keywords: information and measuring systems; oil and gas industry; certification; digital twin model; gas transportation; approach; work efficiency

The article discusses the use of a recurrent neural network in the task of predicting pollutants in the air based on simulated data in the form of a time series. Neural recurrent network models with long Short-Term Memory (LSTM) are used to build the forecast. Unidirectional LSTM (hereinafter simply LSTM), as well as bidirectional LSTM (Bidirectional LSTM, hereinafter Bi-LSTM). Both algorithms were applied for temperature, humidity, pollutant concentration, and other parameters, taking into account both seasonal and short-term changes. The Bi-LSTM network showed the best performance and the least errors.

Keywords: environmental monitoring, data analysis, forecasting, recurrent neural networks, long-term short-term memory, unidirectional, bidirectional

The importance of recycling construction waste for the development of closed-loop economy technologies in the construction industry is considered. The effect of replacing high-quality granite and limestone crushed stone with secondary aggregate obtained by crushing concrete scrap on the strength properties of geopolymer concrete was investigated. It was established that such a replacement does not lead to a decrease in the strength of such concrete, and the impact resistance increases significantly.

Keywords: demolition waste, concrete scrap, recycling, geopolymer concrete, blast furnace granular slag, crushed stone crushing screening, closed-loop economy technologies, secondary aggregate, strength, impact resistance

Deviation of forestry equipment from the designated route leads to environmental, legal, and economic issues, such as soil damage, tree destruction, and fines. Autonomous route correction systems are essential to address these problems. The aim of this study is to develop a system for deviation detection and trajectory calculation to return to the designated route. The system determines the current position of the equipment using global positioning sensors and an inertial measurement unit. The Kalman filter ensures positioning accuracy, while the A* algorithm and trajectory smoothing methods are used to compute efficient routes considering obstacles and turning radii. The proposed solution effectively detects deviations and calculates a trajectory for returning to the route.

Keywords: deviation detection, route correction, mobile application, Kalman filter, logging operations

The annual growth of the load on data centers increases many times over, which is due to the growing growth of users of the information and telecommunications network Internet. Users access various resources and sources, using search engines and services for this. Installing equipment that processes telecommunications traffic faster requires significant financial costs, and can also significantly increase the downtime of the data center due to possible problems during routine maintenance. It is more expedient to focus resources on improving the software, rather than the hardware of the equipment. The article provides an algorithm that can reduce the load on telecommunications equipment by searching for information within a specific subject area, as well as by using the features of natural language and the process of forming words, sentences and texts in it. It is proposed to analyze the request based on the formation of a prefix tree and clustering, as well as by calculating the probability of the occurrence of the desired word based on the three sigma rule and Zipf's Law.

Keywords: Three Sigma Rule, Zipf's Law, Clusters, Language Analysis, Morphemes, Prefix Tree, Probability Distribution

The paper discusses the use of the M/M/n mass service model to analyze the performance of cloud storage systems. Simulations are performed to identify the impact of system parameters on average latency, blocking probability, and throughput. The results demonstrate how optimizing the number of servers and service intensity can improve system performance and minimize latency. The relevance of the study is due to the need to improve the performance of cloud solutions in the context of growing data volumes and increasing load on storage systems.

Keywords: cloud storage, mass service theory, M/M/n model, Python, modeling, performance analysis

Software has been developed to evaluate the surface characteristics of liquids, solutions and suspensions in the Microsoft Visual Studio environment. The module with a user-friendly interface does not require special skills from the user and allows for a numerical calculation of the energy characteristics of the liquid in a time of ~ 1 second: adhesion, cohesion, wetting energy, spreading coefficient and adhesion of the liquid composition to the contact surface. Using the example of a test liquid - distilled water and an initial liquid separation lubricant of the Penta-100 series, an example of calculating the wetting of a steel surface with liquid media is demonstrated. Optical microscopy methods have shown that good lubrication of the steel surface ensures the formation of a homogeneous, defect-free coating. The use of the proposed module allows for an express assessment of the compatibility of liquid formulations with the protected surface and is of interest to manufacturers of paint and varnish materials in product quality control.

Keywords: computer program, C# programming language, wetting, surface, adhesion

The article presents the results of the analysis of the architecture of robotic technologies used in warehouse logistics. The following methods of architecture optimization are identified: multifunctionality, modularity, swarm intelligence, and the implementation of several operating modes. Based on the analysis, a conceptual model of a robot for inventory of warehouse premises was created. The main advantages of the model are: the possibility of using the robot outside working hours due to the presence of an autonomous operating mode; application for inventory and for joint work with other robots (coordination of the movement of ground robots); the presence of an interchange algorithm that ensures fault tolerance and a partial solution to the problem of the limited operating time of the robot from the battery.

Keywords: robotic technologies, drones, modularity, swarm intelligence, fault tolerance, warehouse logistics

The article discusses the process of formation of cavitation bubbles. One of the effective designs of regulating equipment is an axial type valve, for which a mathematical description of the process of formation of cavitation bubbles has been developed. This description allows you to evaluate the bubble structure depending on the main operating and design dimensions of the valve.

Keywords: valve, cavitation bubbles, probability, functions

The paper presents an analysis of existing issues in the subject area, upon which research findings are formed to enhance the quality of the tourist experience through the implementation of a software-mathematical complex aimed at generating personalized recommendations. The task of managing tourist resources is addressed by considering the decision support process through the introduction of multi-criteria optimization and fuzzy logic. Such mechanisms significantly improve the accuracy of forming personalized recommendations that meet individual user requests. As an individual algorithm, a method is proposed for introducing ontological hierarchical types of connections that capture generic and object-oriented relationships of tourism categories, characterizing the influence on tourist objects. In addition, to accommodate flexible, poorly formalized user requests, fuzzy logic mechanisms are introduced by implementing fuzzy evaluation scales. The paper presents a description of the implementation of the recommendation algorithm, which possesses scientific novelty and practical significance. A class diagram details the structure of the ontological hierarchical model presented in the work. Based on the provided research results, the effectiveness of the algorithm is tested through test calculations.

Keywords: tourism, tourism optimization, recommendation systems, fuzzy logic, multi-criteria optimization, mobile development

The article presents the results of a study devoted to the development of an identification subsystem for an industrial process operator in a mobile simulator used for training and monitoring professional skills. The functional requirements for the operator identification subsystem based on neural network technologies, the processes of user interaction with the personality recognition subsystem, and loading a reference image for further identification of the operator during training and monitoring on the simulator are formalized using visual models in UML notation. A prototype of the subsystem has been developed based on the Kotlin programming language and the TensorFlow library. The developed image analysis subsystem has a high speed of face detection and initialization, reaching less than 0.5 s, which makes it especially effective for real-time tasks where performance plays a key role. Local data processing on mobile devices ensures protection of user privacy by eliminating data transfer to remote servers, which minimizes the risks of information leaks. Optimization of power consumption ensures long-term operation on devices with limited battery capacity, which makes the system convenient and practical to use. The considered subsystem is planned to be adapted for monitoring the formation of skills for working on equipment during operator training on mobile simulators. The subsystem, based on VR/AR technologies, as well as a trained neural network, will analyze data on user reactions in real time.

Keywords: mobile simulators, neural networks, user identification, professional training, UML diagrams, TensorFlow

The article discusses the use of recycled materials obtained during the dismantling of facilities during renovation in St. Petersburg. The districts of St. Petersburg with "problematic" houses, such as panel "Khrushchev" and "ships" of the first type, are highlighted. Data on the types of waste, volumes of concrete scrap, features and applications of secondary rubble are presented. Examples of organizations in St. Petersburg dealing with waste recycling are given. The purpose of the work is to study the possibilities of recycling construction waste for reuse in construction and landscaping of the region.

Keywords: secondary materials, dismantling, renovation, concrete scrap, construction waste, recycling, crushed stone, sustainable development, St. Petersburg, ecology

The article is devoted to the design of a test automation system for the DBaaS Postgres Pro cloud database management manager. New approaches, concepts and definitions of the theory of test automation are formulated and old ones are updated. An analysis of modern tools widely used in commercial software development is carried out. The features of the system under test were studied, including the specifics of working with cloud computing and the Postgres DBMS. Based on the data obtained, an optimal technology stack was formed that is planned to be used in development, and functional requirements for the test automation system were developed. In practical terms, the use of this system on a DBaaS project will reduce labor intensity and speed up work at the testing and development stages, increase the efficiency of testing and the quality of the software product.

Keywords: software testing automation, DBaaS, cloud database, Postgres DBMS, GO programming language