The article explores modern approaches to the integration of image processing algorithms and sensor equipment onboard unmanned aerial vehicles (UAVs) for monitoring and mitigation of emergencies affecting railway infrastructure. The research focuses on methods for efficient interaction with high-resolution optical cameras, LiDAR systems, and GPS modules, as well as on the use of distributed and cloud computing technologies for rapid data processing. Special attention is given to adaptive data compression techniques, caching strategies, and asynchronous message queues, which ensure reliable transmission under limited or unstable communication channels.
The work demonstrates practical integration scenarios using the DJI Mini 4 Pro UAV and the WebODM photogrammetric platform, showing a reduction of preliminary processing time from 45 to 6 minutes and an improvement in georeferencing accuracy from 7.8 m to 1.3 m through the use of GPS-EXIF metadata. Point cloud optimization methods, such as Voxel Grid filtering and Statistical Outlier Removal, are shown to decrease file size from 1.2 GB to 210 MB and reduce processing time from 52 to 17 minutes with minimal loss of accuracy.
The study highlights that combining onboard sensors with advanced processing pipelines significantly improves the timeliness, reliability, and accuracy of railway infrastructure assessments after emergencies. The proposed solutions enable automation of geospatial data workflows, enhance operational decision-making, and optimize resource allocation for recovery operations. The findings are relevant for the development of UAV-based monitoring systems in transportation, urban planning, and critical infrastructure protection.

Keywords: UAV, data transfer, distributed computing, LiDAR, WebODM, DJI Mini 4 Pro, infrastructure monitoring, adaptive compression, message queue

The paper discusses the issues of multi-criteria optimization of planning the loading of technological equipment at a machine-building enterprise within a calendar year. Planning and optimizing the loading of technological equipment is one of the key tasks of operational calendar planning at engineering enterprises. The paper presents a model for optimizing the load of technological equipment used in the production process. Within the optimization model, three groups of target indicators were identified: the performance indicator of the group of technological equipment within the calendar year; indicator of uniformity of process equipment group loading within the calendar year; the amount of losses from downtime of a group of process equipment within a calendar year. The paper presents the results of optimizing the load of the fleet of machine tools used within the framework of the machining workshop. Load optimization was carried out for certain groups of technological equipment: a group of lathes, a group of milling machines, a group of grinding machines. Equipment load optimization was carried out by redistributing the total labor intensity of the work performed for the corresponding groups of technological equipment between periods of the calendar year. The Pareto optimization method was used to determine the optimal option for loading groups of process equipment. The following optimization strategy has been defined: minimizing the total amount of losses from downtime of process equipment. The paper presents graphs of Pareto fronts for targets for turning group machines. As a result of optimization, the total amount of losses for certain groups of process equipment resulting from downtime decreased by 6.8% -10.2%. Thus, the use of the developed model to solve the problem of optimizing the load of the fleet of machine-tool equipment made it possible to increase the efficiency of the operational scheduling process at machine-building enterprises.

Keywords: scheduling, multi-criteria optimization, machine stock, targets, losses, process loading

The article is devoted to the analysis of methodological approaches to the definition and assessment of the psychofunctional state of a person. In connection with the need to improve the reliability of human-machine systems, the study of the psychofunctional state of a person controlling a dynamic object is of scientific interest, since to create reliable human-machine systems it is necessary to take into account the reliability factors of technical means and the human factor as well. The analysis of methodological approaches showed that to solve problems dedicated to increasing the reliability of "human-machine" systems, it is advisable to use a systems approach that considers a person not as an independent subject, but as an element of the system. The systems approach has a broad methodological base, allows us to study the psychofunctional state of a person in dynamics.

Keywords: psychofunctional state, functional state, systems approach, energy approach, behavioral approach, phenomenological approach, structural-integrative approach, electrophysiological methods, control of a dynamic object

This paper presents an adaptive pipeline architecture designed to enhance both throughput and reduce latency in real-time stream data processing within single- and multi-processor systems. Unlike predominantly conceptual models or narrowly focused algorithms, the practical impact of this architecture is demonstrated by achieving measurable performance gains through reducing redundant data copying and synchronization costs or by providing flexible control over input and output data ordering. The architecture employs shared memory to eliminate buffer duplication, uses data transfer channels that adapt based on the need for order preservation, and supports the replication of processes within or across CPU cores. Experimental results indicate that the proposed architecture delivers both high throughput and low latency while introducing minimal overhead for data transmission and process synchronization. By offering a flexible and scalable foundation, this architecture can be applied to a wide range of real-time applications, from video surveillance and robotics to distributed platforms for processing large data sets. It demonstrates versatility and robustness in adapting to varying computational demands, thereby ensuring both efficiency and reliability in high-performance environments.

Keywords: parallelism, multiprocessor computing, computational pipeline, performance scaling, queues, shared memory

The work is devoted to the problems of assessing and predicting the reliability of photovoltaic generation devices. The purpose of the work is to identify factors affecting the volume of electricity generation, as well as to build models and procedures for predicting the reliability of the panels during their use depending on these factors. An overview of the types of solar power plants and the photovoltaic panels used is given. An analysis of the factors affecting their reliability is performed, on the basis of which a hierarchy of fuzzy factors related to each other by fuzzy production rules is built. It is proposed to use a statistical two-parameter Weibull model to predict the reliability of the panels. An algorithm for neuro-fuzzy tuning of the reliability forecasting model depending on the factors considered is developed and software implemented, which can be used to create information and analytical systems for decision support in the design and operation of solar power plants.

Keywords: solar energy, photovoltaic panel, reliability prediction, statistical model, neuro-fuzzy network

Integration of heterogeneous field data and remote sensing information is a key and necessary step in modern geological exploration. This article proposes a method based on the creation of a regular spatial grid, which enables the efficient interpolation and integration of point, linear, and polygonal data represented in both vector and raster formats. The primary objective is to generate a structured and enriched dataset suitable for training predictive models, including neural networks. The proposed approach involves transforming geospatial data to ensure their accuracy and consistency within GIS environments. This method provides a reliable foundation for identifying prospective areas with high mineral potential and highlights the importance of rigorous data preparation in spatial modeling and analysis processes.

Keywords: reservoir exploration, data integration, interpolation, spatial grid, geochemistry, spatial modeling process, remote sensing, GIS

This study is devoted to the analysis of decision-making models in ensuring the protection of public order. The results obtained will allow us to formulate a new mathematical model of decision-making, which will allow us to obtain objective management decisions to ensure the protection of public order in the territory of the Republic of Tajikistan with the possibility of simulation. The object of the study is the process of ensuring the protection of public order. In the scientific literature and in open sources of information, there is a large number of works describing models and algorithms developed on the basis of various mathematical tools. The analysis of a number of papers on this topic will allow us to formulate a new mathematical model of decision-making, which will optimize and improve the quality of prepared decision-making projects while ensuring the protection of public order. The study revealed that the basis for improving the effectiveness of ensuring the safety of citizens during mass events is an effective management decision. 1) Based on this, an analysis of decision-making models is presented, the purpose of which is to determine the need to create a decision-making model while ensuring the protection of public order in the Republic of Tajikistan. 2) A model of decision-making in ensuring the protection of public order in the Republic of Tajikistan is proposed. The model is implemented based on the synthesis of mathematical modeling methods, including cluster analysis, pairwise comparison method and Petri nets. The model allows you to divide committed events, i.e. crimes into clusters according to previously defined criteria. At the final stage, the model allows you to simulate each event, thereby predicting the possible development of the event under study. The presented results of the analysis of decision-making models made it possible to formulate a new mathematical model of decision-making in ensuring the protection of public order in the interests of the Republic of Tajikistan.

Keywords: public order protection, mathematical model, cluster analysis, pairwise comparison method, expert assessments, Petri nets

This article presents an analysis of corporate network traffic over the SMTP protocol to identify malicious traffic. The relevance of the study is driven by the increasing number of email-based attacks, such as the distribution of viruses, spam, and phishing messages. The objective of the work is to develop an algorithm for detecting malicious traffic that combines traditional analysis methods with modern machine learning approaches. The article describes the research stages: data collection, preprocessing, model training, algorithm testing, and effectiveness analysis. The data used were collected with the Wireshark tool and include SMTP logs, message headers, and attachments. The experimental results demonstrated high accuracy in detecting malicious traffic, confirming the potential of the proposed approach.

Keywords: SMTP, malicious traffic, network traffic analysis, email, machine learning, Wireshark, spam, phishing, classification algorithms

The article presents the application of fuzzy modeling to solve the systemic task of qualitative assessment of the properties of land plots by an expert method using fuzzy modeling. The set of factors by which the suitability of the plot is estimated depends on the goals of the development project. The technique includes the decomposition of the model into additive models of internal and external factors and a combining multiplicative model, which reduces the dimensionality of the task of assessing the properties of the plot. At the second stage, a fuzzy model of expert assessment of the properties of land plots is formed. It includes a fuzzyification block using linear membership functions, max-min fuzzy inference technology, and defuzzification using the height method, which most adequately translates fuzzy expert assessments into clear numerical (point) values. At the third stage, the contribution coefficients of each factor in the assessment of the properties of plots are determined using the hierarchy analysis method and the fuzzy pairwise comparison scale.

Keywords: land plot, individual assessment, expert method, fuzzy modeling

This article presents a conceptual framework for assessing the maturity of construction control and supervision systems at construction sites. A multi-level assessment model has been developed, integrating the Analytic Hierarchy Process (AHP) and fuzzy comprehensive evaluation method. A five-level taxonomic system for grading the maturity of regulatory mechanisms in the construction industry is proposed. The procedures for forming a hierarchical structure of assessment indicators, constructing judgment matrices, determining weight coefficients, and applying the fuzzy comprehensive evaluation method to quantify the maturity level of supervision systems are described in detail. The developed methodology represents a universal tool for conducting comparative analysis of construction control and state supervision systems in various national and regional jurisdictions based on objective quantified criteria.

Keywords: construction control, state supervision, maturity model, Analytic Hierarchy Process, fuzzy comprehensive evaluation, quantification, assessment indicators

Optimization of automated management systems for facility protection complexes remains relevant today. This research paper provides an overview of the tools for implementing separate monitoring processes: device polling, processing of the received data, and transferring data to the graphic user interface. Based on the analysis of the reviewed information, a basis of solutions for developing management system of the technical means complex is planned to be formed. During the research, it was found that the combination of multi-threading architecture and adaptive polling algorithm allows to implement a large-scale polling; the clustering algorithm and special settings of frameworks for processing large-scale datasets can enhance job performance; WebSocket protocol has proved its efficiency for transferring the real-time data. The result of the evaluation of solutions was a set of tools for implementation of a hardware-software complex.

Keywords: sensor, management system, monitoring, SNMP manager, clustering, Hadoop, MapReduce, Spark, Apache Kafka, WebSocket

The paper examines the current state of the industrial Internet of Things market in Russia and around the world, the main areas of its application, as well as the prospects and challenges that businesses and industrial enterprises will face in implementing this technology. Special attention is paid to the advantages of implementing IIoT, such as increased productivity, reduced costs, improved security and transparency of processes. The barriers specific to the Russian market are discussed, including cybersecurity, hardware compatibility, and significant initial costs. Examples of successful implementations of IIoT technologies in various industries such as the oil and gas industry, logistics and chemical production are given. The emphasis is placed on the need for government support and adaptation of the regulatory framework to accelerate implementation. The article highlights the importance of an integrated approach to IIoT implementation, including using international experience and consolidating efforts to develop the digital economy in the face of global and local challenges.

Keywords: industrial Internet of Things, IIoT, industry 4.0, 5G, production automation, digital transformation

The widespread use of social media platforms has led to the accumulation of vast amounts of stored data, enabling the prediction of rare events based on user interaction analysis. This study presents a method for predicting rare events using graph theory, particularly graphlets. The social network VKontakte, with over 90 million users, serves as the data source. The ORCA algorithm is utilized to identify characteristic graph structures within the data. Throughout the study, user interactions were analyzed to identify precursors of rare events and assess prediction accuracy. The results demonstrate the effectiveness of the proposed method, its potential for threat monitoring, and the possibilities for further refinement of graphlet-based prediction models.

Keywords: social media, security event, event prediction, graph theory, graphlet, interaction analysis, time series analysis, correlation analysis, data processing, anomalous activity

In modern conditions of digital transformation, companies are actively implementing customer Relationship Management systems (CRM systems) to manage customer relationships. However, the issues of data protection, confidentiality and transparency of interaction remain critically important. This article explores the possibilities of using blockchain technology to enhance the security of CRM systems and improve trust between businesses and customers. The purpose of the work is to analyze the potential of using blockchain in data protection of CRM systems, as well as to assess its impact on the transparency of customer transactions. The paper examines the main threats to data security in CRM, the principles of blockchain technology and its key advantages in this context, including decentralization, immutability of records and protection from unauthorized access. Based on the analysis, promising areas of blockchain integration into CRM systems have been identified, practical recommendations for its application have been proposed, and the potential effectiveness of this technology has been assessed. The results of the study may be useful to companies interested in strengthening the protection of customer data and increasing the transparency of user interaction processes.

Keywords: blockchain, CRM-system, security, data protection, transparency, customer interaction

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 article considers issues related to making management decisions when ensuring safety in emergency situations. It reflects the features of making management decisions in emergency situations, when achieving a guaranteed level of safety is not always possible. The control loop is presented and the connections between the elements of the first and second stages are analyzed. It is shown that uncertainty in making management decisions arises due to a lack of information about the control object or is caused by unprofessional actions of the decision maker. It is proposed to create and use in practice a digital twin of safety in an emergency situation to eliminate uncertainties in making management decisions. Decomposition of the task into subtasks allows for the process of collecting and analyzing aggregate information about the control object to eliminate uncertainties and minimize risks in the development, adoption and implementation of management decisions in an emergency situation when ensuring safety.

Keywords: control model, control loop, uncertainty, risk, digital twin, decomposition, emergency safety

The article explores the application of a systems approach and machine learning methods to forecast psychoemotional states based on digital activity in social networks. The study addresses the urgent need to assess the psychological impact of increasing user engagement with digital platforms by using quantitative and algorithmic tools instead of subjective expert assessment.
The main objective of the research is to identify patterns in the relationship between time spent on social networks and self-reported indicators of mental well-being, including symptoms related to ADHD, anxiety, self-esteem, and depression.
Data was collected through an anonymous survey administered via the LMS platform of SUAI. The sample included 473 participants, with 75% under the age of 35. Preprocessing steps involved cleaning outliers, imputing missing values, and formatting the data for analysis. Correlation matrices and heatmaps were created, followed by clustering using the k-means method. A stacked meta-model based on logistic regression and Gaussian Naive Bayes with a random forest as the final estimator was used for classification.
The study revealed distinct user groups with varying levels of vulnerability to the influence of social media. The results can be used to develop intelligent systems for monitoring mental health risks and delivering personalized digital recommendations.
The article is relevant to researchers in system analysis and applied machine learning.

Keywords: system analysis, digital activity, social networks, machine learning, clustering, correlation analysis, digital addiction, psycho-emotional state, information mining

The article is devoted to the creation of a highly specialized automated information system for automated processing of orders for the production of abrasive tools. The development of such software products will improve production efficiency through the transition from order-based production to batch production.

Keywords: automated information system, production order processing system, Rammler-Breich diagram, role-based data access system

The article is the result of an analytical study on the topic of risk management in the creation and modernization of business processes. The article proposes risk management methods using the organization's human resources and methods for training personnel taking into account trends in the labor market. The effect of implementing risk management measures and the method for assessing the effectiveness of the implemented training are separately noted.

Keywords: risk management, human resources, employee training, experts, SWOT analysis

 The assessment of the properties of urbanized territories or plots is necessary to determine the most effective use of them and to determine the cadastral or market price. A comprehensive model for assessing the properties of urbanized territories is presented, which is a multiplicative model consisting of two models: an additive model for assessing the properties of the plot under consideration and an additive model for assessing the influence of external factors determined by the adjacent territory. This multiplicative combination of additive models allows for the differentiated determination of the best alternative for different types of plot use based on the influence of internal and external factors when comparing multiple plots at different stages of a development project. To do this, the preference coefficients are calculated using the ratio of the integral estimates of the compared areas. If there are several areas, they can be selected using pairwise comparisons and the analysis hierarchy method.

Keywords: urbanized territory, property valuation, internal and external factors, additive and multiplicative models, development project

The article considers the issues of imitation modeling of fibrous material mixing processes using Markov processes. The correct combination and redistribution of components in a two-component mixture significantly affects their physical properties, and the developed model makes it possible to optimize this process. The authors propose an algorithm for modeling transitions between mixture states based on Markov processes.

Keywords: modeling, imitation, mixture, mixing, fibrous materials

This article explores the opportunities and challenges of integrating cloud, fog, and edge computing in the context of digital transformation. The analysis reveals that the synergy of these technologies enables optimization of big data processing, enhances system adaptability, and ensures information security. Special attention is given to hybrid architectures that combine the advantages of centralized and decentralized approaches. Practical aspects are addressed, such as the use of the ENIGMA simulator for modeling scalable infrastructures and the EC-CC architecture for smart grids and IoT systems. The role of specialized frameworks in optimizing routing and improving infrastructure reliability is also highlighted. The integration of these technologies drives advancements in key industries, including energy, healthcare, and the Internet of Things, despite challenges related to data security.

Keywords: cloud computing, fog computing, edge computing, hybrid architectures, Internet of Things, digital transformation, big data, decentralized systems, computing integration, distributed computing, data security, resource optimization, data transfer speed

The article considers the solution of the problem of making managerial decisions when performing special aviation operations in emergency situations caused by landscape fires. In order to improve management decision-making, the optimal use of meteorological information by decision makers is considered. The probability of performing special aviation work is used as a criterion for choosing the optimal solution. The objective function is represented by the number of formulations of weather forecast phases, the probabilities of weather forecast formulations, and the probability of performing special aviation operations during the corresponding weather phase. The sensitivity of the mathematical model of the control problem is analyzed for various input parameters, and the characteristic dependence of the values of the objective function on the number of elementary periods is presented. The results obtained are proposed to be used in the planning and organization of aviation flights when performing special aviation operations in emergency situations during the elimination of landscape fires.

Keywords: management, meteorological information, objective function, dynamic programming, special aviation operations, aircraft

The article is devoted to the topic of improving the environmental characteristics of construction sites through the introduction of the principles of "green" construction through a comprehensive assessment of various criteria. Compliance with environmental standards contributes to the creation of a favorable urban environment and ensures comfortable living conditions for residents. The introduction of such approaches is becoming extremely important for sustainable development and the preservation of the natural balance.

Keywords: Green construction, ecological construction, life cycle, construction, multi-criteria decision-making.

This article will present the mlreflect package, written in Python, which is an optimized data pipeline for automated analysis of reflectometry data using machine learning. This package combines several methods of training and data processing. The predictions made by the neural network are accurate and reliable enough to serve as good starting parameters for subsequent data fitting using the least-mean-squares (LSC) method. For a large dataset consisting of 250 reflectivity curves of various thin films on silicon substrates, it was demonstrated that the analytical data pipeline with high accuracy finds the minimum of the film, which is very close to the set by the researcher using physical knowledge and carefully selected boundary conditions.

Keywords: neural network, radiography, thin films, data pipeline, machine learning