Fire detection is an important task in the field of safety and emergency prevention. In recent years, deep learning methods have shown high efficiency in solving various computer vision problems, including detecting objects in images. In this paper, monitoring wildfires was considered, which allows you to quickly respond to them and prevent their spread using deep learning methods. For the experiment, images from the satellite and images from the FireWatch sensor were taken as initial data. In this work, the deep learning algorithms you only look once (YOLO), convolutional neural network (CNN), and fast recurrent neural network (FastRNN) were considered, which makes it possible to determine the accuracy of a natural fire. As a result of the experiments, an automated fire recognition algorithm using YOLOv4 deep learning methods was created. It is expected that the results of the study will show that deep learning methods can be successfully applied to detect fire in images. This may lead to the development of automated monitoring systems capable of quickly and reliably detecting fire situations, which will help improve safety and reduce the risk of fires.

This article is devoted to the study of decision-making problems of hydrotreating process control in the production of high-quality gasoline under conditions of scarcity and fuzziness of the initial information, ultimately developing an approach to solve them. A systematic method is proposed that makes it possible to develop a package of mathematical models of a complex of interconnected units of chemical-technological systems based on available information of various types. Using the proposed system method, a package of models of the main interconnected units in which the hydrotreating process took place was developed. A decision-making problem was formulated to control the hydrotreating process in a fuzzy environment based on the developed system of models. By modifying the Pareto principle of optimality for fuzzy conditions, a heuristic method for solving the given decision-making problem was developed to control the hydrotreating process in a fuzzy environment. The novelty of the proposed heuristic method lies in the full use of the collected fuzzy information, which represents the knowledge, intuition and experience of the decision makers and experts. Accordingly, the proposed heuristic decision-making method makes it possible to achieve a high adequacy and efficiency of decisions made when solving production problems in a fuzzy environment. The results obtained were applied in practice to solve decision-making problems for hydrotreating process control at the Atyrau refinery. The results obtained show the advantages of the proposed heuristic method for solving decision-making problems of hydrotreating process control over known methods.

The rapid growth of internet of things (IoT) devices generate highly variable and self-similar traffic patterns, creating challenges for maintaining quality of service (QoS) in modern telecommunication networks. Accurate short-term forecasting of such traffic is essential for efficient resource allocation, yet its fractal characteristics and long-range dependence complicate prediction. This study investigates the use of simple exponential smoothing for short-term forecasting of self-similar IoT traffic by evaluating three smoothing coefficients (a=0.1, 0.5, and 0.9). The Hurst exponent (H=0.5) confirms the presence of self-similarity in the observed traffic. Experimental results show that a=0.1 provides the highest prediction accuracy, achieving a mean absolute percentage error (MAPE) of 25.82% when forecasting traffic values within a 32-minute horizon. The method effectively captures underlying trends while reducing noise sensitivity. These findings demonstrate that exponential smoothing offers a lightweight, interpretable, and practical solution for real-time IoT traffic forecasting, supporting dynamic network load management under highly variable traffic conditions.

One of the actual problems for the theory and practice of control of dynamic objects is the development of methods for research and synthesis of control systems of multidimensional objects. The paper proposes a universal approach to construct Lyapunov vector functions directly from the equation of state of control system and a new gradient-speed method of Lyapunov vector functions to study aperiodic robust stability of linear control system with m inputs and n outputs. The study of aperiodic robust stability of automatic control systems is based on the construction of Lyapunov vector functions and gradient-speed dynamic control systems. The basic statements of Lyapunov's theorem about asymptotic stability and notions of stability of dynamic systems are used. The representation of control systems as gradient systems and Lyapunov functions as potential functions of gradient systems from the catastrophe theory allow to construct the full-time derivative of Lyapunov vector functions always as a sign-negative function equal to the scalar product of the velocity vector on the gradient vector. The conditions of aperiodic robust stability are obtained as a system of inequalities on the uncertain parameters of the automatic control system, which are a condition for the existence of the Lyapunov vector-function. A numerical example of synthesis of aperiodic robustness of a multidimensional control object is given. The example shows the main stages of the developed synthesis method, the study of the system stability at different values of the coefficients k, confirming the consistency of the proposed method. Transients in the system satisfy all requirements

В статье представлен подход машинного обучение к моделированию реакторно – регенераторного блока установки каталитического крекинга нефтеперерабатывающего завода. Для повышения эффективности процесса исследованы влияние основных параметров процесса крекинга на количество и качество вырабатываемой продукции. В статье был проанализирован методы машинного обучения и определено, какой подход лучше всего подходит для исследования. С помощью метода машинного обучения SVM было исследовано влияние температуры продукта на блок керкинга. По результатам исследования и обработки собранной количественной и качественной информации с помощью модели машинного обучения были созданы регрессионные алгоритмы и изучено влияние температуры на выходной продукт.

Short-Wave Infrared (SWIR) remote sensing plays a significant role in environmental monitoring, agricultural analysis, and nanosatellite-based Earth observation applications. Existing remote sensing frameworks suffer from limitations such as inefficient spectral band selection, high computational complexity, and lack of intelligent optimization techniques for compact nanosatellite payload systems. This study aims to develop an intelligent filter selection system for a four-band SWIR optical payload using multispectral satellite imagery and deep learning (DL)-based optimization techniques. The proposed framework focuses on improving spectral feature extraction, environmental condition classification, and nanosatellite payload efficiency. A multispectral field image dataset was utilized for experimental analysis, where preprocessing techniques, including atmospheric correction and Z-score normalization, were applied. Mutual Information (MI)-based optimal band selection and SWIR filter mapping were performed to identify the significant spectral bands B05, B08, B11, and B12. Feature extraction was conducted using raw SWIR band values and spectral band ratios. A Vision Transformer (ViT) model was employed for environmental condition classification while the Whale Optimization Algorithm (WOA) was integrated to optimize model parameters and improve convergence performance. The proposed ViT–WOA framework achieved superior classification performance with 96.93% accuracy, 97.19% precision, 96.93% recall, 96.92% F1-score. and a Kappa coefficient of 0.9540. The framework effectively classified cloudy, rainy, and sunny environmental conditions with reduced classification loss and improved spectral feature learning efficiency. The proposed system demonstrated reliable SWIR spectral analysis and intelligent payload optimization for nanosatellite remote sensing applications. The integration of transformer-based learning and metaheuristic optimization provided an effective solution for efficient Earth observation and environmental monitoring systems.