Abstract. The article sets the main goal of improving the quality of medical care for the population with diseases of the musculoskeletal system, using the example of MRI diagnostics of the knee joint. MRI technology is systematically considered in the article as an integrated cyberspace of augmented reality containing physically measurable indicators and calculated virtual risk parameters. The medical care system in the research tasks is represented by a composition of a vertical integration vector and a horizontal vector. The vertical integration vector is a systemic hierarchical inter-level structure, an organizational and technical link with the lower operational and technological level. The organizational and technical criterion for the systemic quality of the vertical vector is proposed to use the level of digital maturity, which is a fuzzy composition of weighted support agents: technical support; information analytical support; mathematical support; metrological support; personnel support; software. For a quantitative assessment of the level of digital maturity, a model and an algorithm based on fuzzy principles have been developed. The horizontal operational and technological vector aggregates the procedures of mandatory clinical and laboratory examination and additional ones based on radiography and ultrasound diagnostics. The working technology at the lower system level is MRI diagnostics. At this level, the main scientific and practical attention is focused on the formalization of the processes of quantitative assessment of operational risks of control and making diagnostic decisions under conditions of parametric uncertainty of control agents. For this purpose, probabilistic, simulation, statistical models and expert approaches have been developed. The adequacy of theoretical hypotheses to practical results is assessed by computer modeling, for which software applications in the Python language have been developed.
Keywords: MRI technology, system, digital maturity, fuzziness, modeling, control risks.
Abstract. The aim of the study is to develop and evaluate machine learning models for detecting cyber threats in aviation communication and navigation systems. Modern aviation infrastructures, including ADS-B and ACARS protocols, are vulnerable to attacks such as GPS spoofing, DoS, and false message injection. The study uses a combined dataset of 50,000 records, of which 30% simulate attacks and 70% represent normal system operation.
The methodology includes the use of Random Forest, SVM, and autoencoder models. After normalisation and dimensionality reduction (to 10 PCA components), the models were trained and tested using 5-fold stratified cross-validation. Random Forest showed the best classification accuracy — 96.4%, with an F1-measure of 94.9%, Recall 95.1% and Precision 94.7%. SVM demonstrated 91.2% accuracy, while autoencoder achieved 92.3% successful attack detection with a false positive rate of no more than 4.1%. According to ROC analysis, the Random Forest model had an AUC = 0.98, and Precision-Recall analysis showed an AP = 0.96.
The scientific novelty lies in the systematic comparison of models with and without a teacher in terms of their applicability to real aviation scenarios, taking into account the specifics of protocols and temporal features.
The practical significance lies in the possibility of integrating the trained models into air traffic monitoring systems and digital onboard systems for early threat detection, minimising the risk of failures and improving flight safety.
Keywords: aviation cybersecurity, machine learning, intrusion detection, ADS-B, GPS spoofing, autoencoder, Random Forest.
Abstract. Accurate and rapid assessment of turbulent flows in turbine working channels remains one of the key challenges in computational gas and fluid dynamics, especially under conditions of high demands on the efficiency and reliability of turbomachinery. Traditional approaches, such as Reynolds-based simulation (RANS) or large eddy simulation (LES), although providing acceptable accuracy, are associated with high computational resource and time costs. This paper proposes an alternative approach based on the use of convolutional neural networks (CNN) as a surrogate model for reproducing three-dimensional velocity and pressure fields in turbulent flows. The developed architecture is based on a modified version of U-Net and adapted for three-dimensional input data. A comparison with LES results showed that the proposed model is capable of reproducing key flow characteristics, including vortex structure and pressure gradients, with a high degree of accuracy. At the same time, a significant acceleration of calculations is achieved — up to 10³ times compared to classical numerical methods. The proposed neural network model demonstrates stability to changes in geometric parameters and can be easily reconfigured for other channel configurations. The results obtained highlight the potential of deep learning in turbulent flow modelling and open up prospects for the integration of such models into real-time engineering calculations.
Keywords: turbulent flow modeling, convolutional neural networks (CNN), U-Net architecture, surrogate modeling, Large Eddy Simulation (LES), turbomachinery, data-driven computational fluid dynamics (CFD).
Abstract. Integration of machine learning systems into information systems for recognizing objects using unmanned aerial vehicles (UAVs) can be applied in many areas of life, including farming, military operations, and environmental monitoring. The purpose of this work is to develop an information system with the integration of machine learning for recognizing objects using UAVs in order to facilitate human labor and promote environmental protection by identifying various types of waste. This system is in demand because drones with cameras collect large volumes of data, and with the help of complex functions, their processing occurs faster. The work also opens up new opportunities for our country, due to many new functions and innovative solutions. Using the analysis of existing systems and functions, requirements for a new system were identified. Such as image recognition techniques, navigation of unmanned aerial vehicles, neural networks in the detection and distribution of objects, algorithms for planning the trajectory of the formation of UAVs. The tasks are to develop a system combined with deep learning technologies and using unmanned aerial vehicles. The system is equipped with an instant notification mechanism that responds to the detection of new objects and sends notifications to the user. A user-friendly interface is provided for control, receiving notifications, as well as storing images and data on previously recognized objects. The data obtained during the flight is transmitted to the information system for processing, recognition and classification of objects. The architecture of the solution ensures operation in real time. The user interface makes the system management intuitive and ensures long-term storage of information. As a result of the work, it can be used in various areas, such as security, finding the largest place of accumulation of waste, monitoring the environment. After the results were obtained, testing was carried out, which confirmed the accuracy of recognition and adaptability in real time.
Keywords: machine learning, unmanned aerial vehicles, object recognition, neural networks, deep learning, real-time processing, computer vision, data transmission.
Abstract. This article presents a model of a compact adaptive gear variator designed for use in space technology and high-tech systems. Reducing the mass of spacecraft, increasing efficiency, and ensuring reliability are among the most relevant challenges in modern science and engineering. In this context, gear variators especially adaptive types are of great interest due to their ability to efficiently control motion and adapt to system conditions. The article describes the structural features of an advanced gear variator based on an adaptive transmission mechanism. Its operating principle is visualized using a 3D model and animation created in SolidWorks. The drive automatically adjusts the gear ratio between the input and output shafts, enabling parameter changes in response to external loads. These features make the device particularly suitable for use in orbital spacecraft, solar panel orientation systems, maneuvering propulsion systems, and other complex mechanisms. The results of the study confirm the model’s compactness, energy efficiency, and high reliability through analytical calculations and numerical simulations. Furthermore, this research builds upon the theoretical foundations of adaptive mechanisms and expands their potential application in aerospace engineering. The proposed improved model may serve as an innovative solution in the design of next-generation engineering systems. The purpose of the article is to create a simple and compact variator model for the space industry.
Keywords: adaptive gear, variator, kinematic chain, SolidWorks model, space technology, compact drive systems, energy efficiency, automatic control, gear ratio.
Abstract. Graphene, owing to its unique physicochemical properties, finds wide application in various fields of science and technology. This article examines the use of graphene in aerospace technologies, including the creation of lightweight and durable materials, heat-dissipating coatings, and its potential application in solar panels, electronic devices of spacecraft, and radiation protection systems. An in-depth analysis shows that the integration of graphene nanomaterials can significantly enhance structural performance, increase reliability, and improve resistance to extreme conditions. Experimental studies using the chemical vapor deposition (CVD) method confirm the efficiency of high-quality graphene synthesis. This work demonstrates the potential of graphene for the development of innovative aerospace systems capable of ensuring an optimal balance between mass and strength, as well as resistance to thermal and mechanical loads. The results of the study may contribute to further technological improvement and broader practical application of graphene in modern aerospace projects. The obtained data open up new opportunities to enhance structural efficiency, promote the advancement of cutting-edge materials science, and provide a competitive advantage in the aerospace industry. This is a promising area. In addition, the article highlights modern approaches to the synthesis of graphene nanostructures, including single-step and multi-step methods, features of interaction with metal substrates, and crystallinity control. Particular attention is given to the scalability of CVD processes for industrial applications. Experimental data are presented on the morphology, thermal conductivity, and tribological characteristics of the obtained materials. The results emphasize the relevance of developing functional graphene coatings to improve the durability and energy efficiency of aerospace systems under high temperatures and mechanical stress.
Keywords: graphene, carbon nanomaterials, aerospace technologies, thermal conductivity, composite materials, radiation protection.
Abstract. Modern armed conflicts and their consequences have significantly increased the number of mined areas worldwide, posing a threat to civilians and hindering the restoration of affected regions. This article reviews the global experience in the development and application of robotic complexes for mine detection and neutralization. It analyzes modern technologies, including artificial intelligence, multisensor systems, unmanned aerial vehicles (UAVs), and ground platforms, which enhance the efficiency of demining operations.
Special attention is given to the potential of deep learning algorithms for mine and unexploded ordnance (UXO) detection, as well as the integration of autonomous systems for operation in complex environments. Key challenges such as the high cost of equipment, the need to reduce false alarms, and the adaptation of technologies to various military and humanitarian scenarios are discussed.
Promising solutions, including the development of swarm robotic systems and the combination of different sensor technologies, are examined. The implementation of these technologies can significantly improve the safety and efficiency of humanitarian demining, reduce risks for sappers, and accelerate recovery efforts.
Keywords: demining, robotic complexes, UAVs, deep learning, multisensor systems, artificial intelligence.
Abstract. The paper proposes an algorithm for planning routes for overflighting agricultural fields with obstacles to solve precision farming problems. The algorithm can be applied in both processing and field monitoring tasks. Unlike classical methods, which are limited to simple zigzag traversal (Zamboni) and elementary perimeter traversal of obstacles, this algorithm takes into account the presence of a fleet of heterogeneous drones (different type, range, cost, speed) and a moving ground platform that provides energy and necessary resources for the process of overflight. The drones take off and land at various points along a road that typically wraps around a field. The key innovation is a two-stage optimization procedure: first, a random set of field partitions is generated into several sub-multiples with specified area fractions (taking into account internal obstacles), and then, for the optimal partition, a genetic algorithm is run to optimize the overflight parameters (flight angle, entry point, composition and order of drone launches, and platform route). Optimization is achieved through a more localized traversal of certain parts of the field (each area is served by a suitable type of drone), as well as flexible movement of the ground platform, reducing useless flights. Numerical experiments show that, depending on the size of the obstacle and the size of the field, a 12-15% reduction in the cost of overflights is achieved. The final part of the paper discusses the prospects of the solution development, including consideration of 3D terrain, dynamic factors (changing weather conditions, drone stopping for technical reasons) and automatic collision prevention on intersecting route sections.
Keywords: Coverage algorithm, drones, genetic algorithm, flight planning, artificial intelligence.
Abstract. In an era marked by global supply chain disruptions, optimizing risk management processes in logistics is essential for improving operational resilience and decision-making efficiency. This paper investigates the implementation of digital technologies—specifically predictive analytics, digital twins, and AI-driven risk assessment models—in the identification, evaluation, and mitigation of risks in logistics. A case study based on a mid-sized logistics provider operating in Central Asia is presented to demonstrate the quantitative impact of digital integration. The study employs a hybrid methodology combining Failure Mode and Effects Analysis (FMEA) with Monte Carlo simulation to assess the probabilistic consequences of supply delays, vehicle breakdowns, and warehouse bottlenecks. The findings indicate a 37% reduction in risk exposure and a 21% increase in supply chain responsiveness after the deployment of an AI-powered predictive platform. Additionally, the average delay time per delivery was reduced from 3.5 to 2.2 hours, and the Risk Priority Number (RPN) for key logistical hazards dropped from 216 to 136. This demonstrates the significant value of digitization in enhancing the accuracy of risk assessments and optimizing logistics operations under uncertainty. The study concludes with strategic recommendations for integrating digital tools into logistics workflows, emphasizing scalability and adaptability for companies facing complex risk environments.
Keywords: risk management, logistics, digital technologies, predictive analytics, digital twin, Monte Carlo simulation, supply chain optimization.
Abstract. In the context of the development of the economic activity of enterprises, it is very important to choose the right strategy and identify your place in the market. One of the priorities of every enterprise is to reduce costs. A properly developed logistics strategy allows you to reduce stocks, transportation costs, improve relationships with suppliers, distributors and end users. This in turn will lead to the functioning of enterprises and ensure competitiveness in the market. In this article, a special place is allocated to the strategic plan of logistics in the enterprise, the processes and components of the logistics strategy in the enterprise are highlighted. The functional responsibilities of management in the process of strategic planning at the enterprise in market
conditions are considered. The purpose of this scientific work is to determine the theoretical and practical aspects of the business strategy in the enterprise and highlight the features of the functioning of the logistics strategy as a whole in modern conditions. Research methods are focused on a narrow subject area, narrowly focused, but sufficient to fulfill the stated purpose of the article. The article uses theoretical-empirical methods to explain and highlight the components.
Keywords: strategy, strategic management, management, logistics, logistics strategy, business strategy, competitiveness, transportation, supply, costs.
Abstract. In September 2013, Chinese President Xi Jinping launched the «One Belt, One Road» initiative, proposing to combine land and sea trade routes to ensure fast and economical delivery of goods to countries in Southeast Asia, Africa, the Middle East, and Europe. As part of this initiative, it is planned to integrate two projects—the Silk Road Economic Belt, which covers several economic corridors, and the 21st Century Maritime Silk Road. To date, more than 150 countries have already concluded cooperation agreements with China on this program [1]. Given its advantageous geographical location and the urgency of reviving the historic Great Silk Road in a modern format, Kazakhstan has actively engaged in competition for transit from China and is striving to take a key position in implementing the Silk Road Economic Belt project. To increase export and transit potential, KTZ is systematically working on infrastructure development since the growth in cargo transportation volumes requires a constant increase in the capacity of railway sections.
This article focuses on the technical effectiveness of the project aimed at increasing the capacity of the Almaty Freight Transportation department. This is due to the fact that the key transit routes of the Belt and Road Initiative pass through this branch. The location and prospects for developing the infrastructure of Kazakhstan’s largest freight office are important factors for the active participation of the Almaty office in implementing transport projects within the framework of the «One Belt—One Road» initiative.
Keywords: transport, transportation, logistics, infrastructure, transport corridors, one belt, one road, transit potential.
Abstract. This article discusses the process of developing an automated spot irrigation system for plants, including the use of computer vision and robotic systems. One of the most advanced systems today is the FPV agro-robots operating with the Raspberry Pi 4 mini-computer and a web camera. This system allows real-time monitoring and analysis of visual data for accurate irrigation of plant roots. The optimal choice for software and hardware development is the RaspController web application, which enables remote control via local and global Internet networks. This application provides access to GPIO pins and images from the web camera. Control of the robot’s movement is carried out by encoding the control pins of the L298N chip. A key feature of controlling the FPV agro-robot is the intelligent recognition of the white lines of the movement trajectory to the irrigation point and horizontal white strips that determine the watering dose for each plant, using computer vision. The prototype of the agro-robot has passed testing and has enabled the creation of a working semi-industrial model, and the use of the spot irrigation method contributes to saving over 50% of water.
Keywords: Spot irrigation, agro-robots, computer vision, neural networks, agriculture, Raspberry Pi, IOT.