Purpose of research. Evaluation of the effectiveness of the UAV automatic landing system on a mobile platform using an infrared beacon based on criteria for landing accuracy and maneuver success at various altitudes.

   Methods. Modeling the process of movement of a complex object (UAV) in the Gazebo environment using the ROS ecosystem. The positioning of the UAV is based on a mathematical model of an infrared beacon consisting of four pairs of emitters. The landing algorithm includes adaptive PID controllers for the X and Y coordinates and a logo polynomial controller to ensure the descent of the UAV along the Z axis.

   Results. The UAV landing was tested 50 times from heights of 5 m, 10 m and 15 m. At a height of 5 m, the landing time was 9.04 seconds (0.504 sec deviation), the error was 0.18 m (0.035 m deviation), the success rate was 100  %. At 10 m, the time increased to 19.17 seconds (1.78 sec deviation), the error was 0.19 m (0.036 m deviation), the success rate remained 100 %. At 15 m, the time increased to 40.45 seconds (5.502 seconds deviation), the error was 0.21 m (0.046 m deviation), the data distribution became wider, outliers appeared, the success rate decreased to 92 %, which is due to signal losses, their attenuation and the need to correct the trajectory. Increasing the height of the landing process testing is impractical due to a decrease in the probability of a successful landing.

   Conclusion. The study showed that the infrared beacon system works effectively for landing UAVs on a mobile platform at altitudes up to 10 m, providing the necessary stability and accuracy. At altitudes above 10 m, problems arise with loss of signals, increased landing time and errors, which require improvements to ensure the reliability of landing.

   Purpose of research. The purpose of this study is to construct approximation grid nodes in the measurement-polynomial processing of input data of a computer system in the coefficient inverse problem for an algebraic polynomial, including for the equation of beam deflections when solving the inverse Cauchy problem.

   Methods. The main scientific methods used in this study are methods of regularization, measurement reduction, linear Lagrangian approximation, and numerical methods. Since when deriving explicit formulas in the radicals of the roots of the resolving equations for the optimal design of the approximation grid nodes according to Abel’s theorem, a limitation is imposed on the degree of the equations, in this article, in solving the problem for an algebraic polynomial with a prescribed coefficient of the second lowest term, it is proposed to use the Chebyshev alternance of extremal polynomials.

   Results. The result of the study is a technique for optimizing the approximation grid, minimizing the influence of the input data error with a uniform continuous norm of absolute errors on the accuracy of solving the problem by minimizing the Lebesgue function. The proposal to apply a modification of Chebyshev polynomials to the optimal approximation grid is substantiated.

   Conclusion. This article proposes a formalization of the problem of minimizing the influence of the input data error on the accuracy of calculating the coefficients of an algebraic polynomial in a measurement and computing system by selecting the nodes of the approximation grid through the Chebyshev alternance.

   Purpose. In this paper we study degenerate bifurcations and merging bifurcations of chaotic attractors in a pulse-width modulated control system, the behavior of which is described by a bimodal piecewise linear continuous mapping. It is well known that in piecewise linear maps, classical bifurcations such as period doubling, transcritical and pitchfork, become degenerate, combining the properties of classical smooth bifurcations and border collision bifurcations.

   Methods. First we describe а technique for obtaining of a piecewise linear mapping from a vector field with a discontinuous right-hand side using the method construction of the Poincare map. Then are investigated degenerate period -doubling bifurcations by methods of the theory of critical lines for non-invertible maps.

   Results. We found that the considered mapping has an unusual property, which is as follows. At the flip bifurcation point for a fixed point, an interval I appears, on the boundaries of which two points of the period doubled cycle lie. Moreover, any point of this interval is a periodic point with a period of two. We have proved that periodic points with a period of two lying on the boundaries of this interval coincide with two switching manifolds. As a specific example of a real physical system, we consider a power converter system with pulse width modulated control, which is modeled by a piecewise linear mapping. Moreover, we experimentally show a fixed point, a 2-cycle and chaotic oscillations.

   Conclusion. Finally we have studied degenerate period-doubling bifurcations and merging bifurcations of cyclic chaotic attractors. Such bifurcation is also known as a merging crisis. At the bifurcation point, an unstable fixed point with a negative multiplier collides with the boundaries of a chaotic attractor. It is well known, that the boundaries of a chaotic attractor are formed by the so-called critical points and their images. At the moment of bifurcation, a homoclinic orbit arises. Due to the fact that the considered mapping is piecewise linear, the equations of bifurcation boundaries are obtained analytically, the solutions of which are either analytically or numerically.

   Purpose of research. Improving the effectiveness and reliability of management decisions based on a comprehensive analysis of the subject area under study and the development of a formal model of the situation describing the decision-making process and including cognitive technologies.

   Methods. The article analyzes the concept of "decision", shows a cybernetic approach to the process of making a managerial decision. As a result of the analysis, it was revealed that in many subject areas (especially social and other sciences engaged in the study of human behavior) difficulties arise in the formal description of decision-making processes. The paper proposes an approach to the development of management decisions based on the use of cognitive technologies, which currently represent a rapidly developing branch of modern science. One of the elements of cognitive technologies used in the work is cognitive maps.

   Results. The paper considers three classic decision-making situations (under conditions of certainty, risk and uncertainty), the last two of which are due to incomplete information about the described object and its external environment. To formalize the processes of managerial decision-making, it is proposed to use cognitive technologies, in particular, one of the options for constructing a fuzzy cognitive map of managerial decision-making is proposed, which allows identifying stable and unstable development trends, emerging situations, as well as conducting a factor analysis of the effectiveness of managerial decisions.

   Conclusion. As a result of the study, it was shown that the use of cognitive technologies is an adequate tool for making managerial decisions. The expediency of constructing fuzzy cognitive maps in the formation of a management decision is shown, which will ensure an increase in their quality and effectiveness.

   Purpose of research. This paper investigates the effectiveness of different missing value handling methods in dataframes for data preprocessing tasks in predictive analytics. Three open datasets containing information on building characteristics, meteorological conditions, and energy consumption are used as test data.

   The goal of the study is to identify the most effective method for data preprocessing in the ETL process for solving predictive analytics problems.

   Methods. The paper combines dataframes from each dataset and analyzes standard methods of the Pandas module, a high-level library of the Python language, such as direct assignment, the use of indexers, and the fillna method with a dictionary. In addition, a module in Cython, a C-like programming language, is developed to optimize the process of filling missing values, and the performance of each method is evaluated.

   Results. The results demonstrate that direct assignment is the most effective method in terms of performance in Pandas. Using Cython, although theoretically capable of speeding up calculations, in this case showed a significant decrease in performance due to the overhead of data transformation and interaction between Python and Cython. Code profiling confirmed that the place with insufficient performance is Pandas operations, not Cython code execution.

   Conclusion. Thus, for most ETL tasks, it is recommended to use optimized Pandas methods, and Cython should be used only in cases of critical need for performance improvement and with careful optimization of the code to minimize overhead, since writing code similar to Pandas will require significant resources, including for its optimization, which in most cases is redundant.

   Purpose of research of this work is the development and evaluation of control models for autonomous underwater and surface vessel using fuzzy logic and neural network technologies.

   The influence of different approaches on the control accuracy and motion stability of uncrewed, autonomous vessels is investigated.

   Methods. In this work, we used the fifth-order Rung-Kutta method for numerical modeling of the dynamics of an autonomous vehicle. This method allows to accurately calculate the state of the AV in time, taking into account the various parameters of its motion. The method used was fuzzy modeling, which includes the development of fuzzy controllers. These controllers take into account the peculiarities of AV dynamics and provide robustness under changing environmental parameters. Fuzzy modeling allows the use of linguistic variables to describe the different states of the system and takes into account the uncertainties that may arise in the control of the AV. Method of neural network technology in AV control. The use of neural networks provides the possibility of automatic training and adjustment of control parameters based on the results.

   Results. The simulation results showed that the use of fuzzy models significantly improves the control performance of AV compared to mathematical models. The implementation of neural networks achieved the best RMS error rate (REM) compared to both other models, which confirms the effectiveness of this approach. In particular, for the X direction, the RMSE for the neural network was 6.4321, which is the best among all models.

  Conclusion. Research has shown that integrating fuzzy logic and neural network technology into AV control results in significant improvements in control accuracy and stability in complex environments. Neural networks provide additional adaptability, allowing the system to respond effectively to changes in the external environment and improving the overall performance of the BEC.

   Purpose of research. Improving the accuracy of forecasting by identifying logical connections in unstructured datasets and forming a multi-tiered structure of a specialized neural network computing system.

   Methods. A parallel algorithm for determining the fragmented structure of the training sample is proposed, which is used to isolate fragments containing training data based on the logical dependencies of the sample. Based on the generated fragmented sample, a method for assembling neural networks has been developed, which is used to form an effective structure of a cascade forecasting system.

   Results. Forecasting the results of the unofficial team competition of the International Student Sports Festival 2023 was chosen as the main experiment. A fragmented training sample has been formed on the basis of which a cascade of neural network modules has been built. Four cascade variants were tested in experiments, which showed a significant increase in prediction accuracy compared to single-module analogues. To significantly improve the performance of a neural network system with ultra-short-term forecasts, the hardware implementation of cascades based on the decisive field of FPGA is considered. The structure of the complex with the possibility of its reconfiguration is proposed.

   Conclusion. The use of artificial neural networks in forecasting is promising, but it may face problems of inaccuracy of results due to insufficient computing power and collisions in training samples. One of the proposed solutions to the problem is cascading specialized neural network modules. Positive results were demonstrated by both the software and hardware implementation of the system based on the proposed cascade. The evaluation of the hardware implementation demonstrates the possibility of acceleration, compared with the software implementation, which may be necessary when conducting ultra-short-term forecasts. The proposed methods and algorithms have demonstrated their correctness.

   Purpose of research. Development of an ontological model for managing the waiting time for traffic light signals by road users in a pedestrian crossing zone, with the capability to count the number of pedestrians and vehicles at the intersection and regulate the timing intervals of traffic light signals based on their quantity.

   Methods. The database for the ontological model is collected using a computer vision system. A cognitive decision-making model is used to determine object boundaries. Object classification is performed using the YOLO algorithm. The counting of pedestrians and vehicles is carried out within a mathematical model for counting detectable objects in an image. The calculation of time for regulating the duration of traffic light signals is achieved through a mathematical model of intelligent traffic light control. The proposed ontological model includes several stages: data collection, image preprocessing, object boundary detection, classification of road users into classes and subclasses, counting the number of pedestrians and vehicles, and calculating the time required to adjust the duration of intelligent traffic light signals.

   Results. A specialized software model has been developed, which enables the detection of object classes and the calculation of delay times for traffic light signals to regulate an intelligent traffic light. The state registration certificate for the computer program "Program for Detecting Objects at a Pedestrian Crossing and Determining Traffic Light Signal Delay Times" is numbered 2024662790. Additionally, a patent for the invention "Traffic Light Control Device Based on Fuzzy Logic" (No. 2827781) has been obtained, allowing for the generation of control signals for an intelligent traffic light.

   Conclusion. The results of experimental studies have demonstrated the high efficiency of the developed ontological model for managing the waiting time for traffic light signals by road users in a pedestrian crossing zone.

   Purpose of research. The aim of this work is to develop an approach to constructing intelligent systems based on a replenished semantic network and a multi-agent environment with agents of various types: cognitive and deductive reactive.

   The architecture of a multi-level intelligent system is proposed and substantiated, which uses cognitive and reactive intelligent agents that differ in composition and number of implemented cognitive and deductive presumptions.

   Methods. Knowledge about the subject area is formalized both using the modal version of the first-order predicate calculus for describing cognitive agents and in terms of classical non-modal versions of predicate calculus and deductive inference mechanisms for reactive agents. The operation of an intelligent system is described by an incompletely defined semantic network represented by a conceptual graph and a system of production rules.

   Results. A functional architecture of an intelligent agent-based system is proposed. At the conceptual level, the architecture of an intelligent agent-based system is proposed to be represented by three sublevels. Cognitive agents
use knowledge and beliefs that follow from epistemic logic systems. Cognitive presumptions of these agents include beliefs, goals, intentions, and desires of agents and are modeled within the framework of BDI logic.

   Conclusion. The conducted study shows the importance of BDI logic for cognitive agents, although it was used insignificantly in solving the task at hand, at the level of the content-conceptual description of the intelligent system. The extended functions of cognitive agents include the execution of input, registration, transmission and comparison of lists of objects and relations between them. The goals for the subsequent interpretation of cognitive agents are defined.

   Purpose of research is to develop a new high-speed method for searching for trapping sets, and a new method for estimating the probability of errors caused by these trapping sets for quasi-cyclic codes with a circulant size that is not a prime number.

   Methods. The proposed method for searching for trapping sets uses the algebraic properties of quasi-cyclic codes on graphs. Using the graph lifting and projection operations, the problem of searching for trapping sets is transferred to a higher-dimensional space, where trapping sets are more distinguishable. The proposed method for estimating the probability of errors based on selection by importance, in comparison with the previously proposed Cole method, allows parallelization of calculations without the need to duplicate tables. This approach reduces the amount of required memory many times and allows calculations to be performed using separated indices.

   Results. The proposed method of searching for trapping sets is convenient for hardware implementation, in particular, on accelerator boards using FPGAs. For its implementation, less than half of the SLR (super logic regions) chiplet of the BittWare XUP-P3R accelerator (in a configuration with 128 GB of DDR4 RAM) or the AMD Alveo U200/VCU1525 accelerator (64 GB of DDR4 RAM) is sufficient. This, combined with reduced requirements for RAM volume, allows placing 5 execution units on the AMD Virtex UltraScale+ XCVU9P FPGA [51] crystal instead of 2x, required for the modified Cole method. At the same time, the search acceleration for a matrix with a circulant size of 128 will be 2.5 times. The application of the proposed method for estimating the probability of errors caused by trapping sets provides a 5.3-fold acceleration compared to the Cole method for a quasi-cyclic code with a circulant size of 2048. The proposed method allows one to estimate the noise immunity of the code over the entire range of the signal-to-noise ratio.

   Conclusion. The proposed method of searching for trapping sets has high performance and ensures completeness of the search. The proposed method of estimating the probability of errors caused by these trapping sets also has high performance.