Кафедра авіаційних комп'ютерно-інтегрованих комплексів (НОВА)
Permanent URI for this communityhttp://er.nau.edu.ua/handle/NAU/58724
News
Відповідальний за розділ: Провідний фахівець кафедри авіаційних комп'ютерно-інтегрованих комплексів інституту інформаційно-діагностичних систем Шугалєй Людмила Петрівна. E-mail: shugaley2005@ukr.net
Browse
Browsing Кафедра авіаційних комп'ютерно-інтегрованих комплексів (НОВА) by Title
Now showing 1 - 20 of 418
- Results Per Page
- Sort Options
Item A Comprehensive Framework for Underwater Object Detection Based on Improved YOLOv8(National Aviation University, 2024-03-29) Sineglazov, Victor; Синєглазов, Віктор Михайлович; Savchenko, Mykhailo; Савченко, Михайло ВолодимировичUnderwater object detection poses unique challenges due to issues such as poor visibility, small densely packed objects, and target occlusion. In this paper, we propose a comprehensive framework for underwater object detection based on improved YOLOv8, addressing these challenges and achieving superior performance. Our framework integrates several key enhancements including Contrast Limited Adaptive Histogram Equalization for image preprocessing, a lightweight GhostNetV2 backbone, Coordinate Attention mechanism, and Deformable ConvNets v4 for improved feature representation. Through experimentation on the UTDAC2020 dataset, our model achieves 82.35% precision, 80.98 % recall, and 86.21 % mean average precision at IoU = 0.5. Notably, our framework outperforms the YOLOv8s model by a significant margin, while also being 15.1% smaller in terms of computational complexity. These results underscore the efficiency of our proposed framework for underwater object detection tasks, demonstrating its potential for real-world applications in underwater environments.Item A system for generating training samples in semi-supervised learning tasks based on generative-competitive networks(National Aviation University, 2023-12-27) Trotsiuk, Denys; Троцюк, Денис ОлександровичIn today's world of rapid technological development, artificial intelligence (AI) is taking a special place, being implemented in various areas of human activity, ranging from industrial automation to creative professions. Among the areas of AI research, generative adversarial networks (GANs) have proven to be a promising tool for generating new data that mimics real-world patterns. GANs play a key role in the development of machine learning, in particular, in image synthesis, natural language processing, music creation, and other tasks. The relevance of the research topic is due to the rapid development of neural networks and the need to create efficient and reliable systems that can adapt to changing production conditions and market needs. Despite the large number of studies in this area, the structural-parametric synthesis of ANNs still requires in-depth study to optimize the network training process and improve the quality of the generated data. The purpose of this master's thesis is to develop structural-parametric synthesis methods for optimizing GANs, which will improve the accuracy and diversification of the generated data. As part of the work, the author of the master's thesis investigated the following aspects: analysis of existing GAN architectures, development of new methods of structural synthesis and parametric optimization, experimental verification of the developed methods on real data. The object of research is generatively adversarial networks, and the subject is methods of their structural and parametric synthesis. In the course of the work, the author used such research methods as analysis of scientific literature, computer modeling, experimental methods, and statistical data processing. As a result of the work, it is expected to obtain a model of GAN with improved characteristics, which will expand the possibilities of their practical use in various fields, such as visual art, design automation, game development, and other areas where it is necessary to generate high-quality content.Item About Algorithms of Target Positioning(National Aviation University, 2022-06-24) Hley, Oleg; Глей, Олег Сергійович; Sineglazov, Victor; Синєглазов, Віктор МихайловичSoftware has been developed for the system most suitable for wind shear detection. The formulation of the target designation problem is presented. The features of modern radars are considered. The aim of the work is to find the most suitable system for detecting wind shear and to develop software for this system that offers the pilot a turnkey solution for flying through the danger zone of wind shear. The paper presents the definitions of wind shear, statistics of air crashes caused by this phenomenon. The systems for determining wind shear are described and the most suitable system is selected. The principle of operation and the algorithm of operation of the Doppler radar station are given. A simulation of the detection of a dangerous wind shear zone was carried out. The pilot uses the proposed software solution. Thus, the task of determining the wind shear zone and the decisions proposed on this basis to fly around the dangerous zone have been completed. The results show that introducing random noise into labeled samples degrades the accuracy of the model, while introducing random noise into unlabeled data can, on the contrary, increase the accuracy of the model.Item About working set for dynamic memory allocation(Osvita Ukrainy, 2016-03) Yurchenko, Alexander; Юрченко, Олександр Сергійович; Kozlov, Anatoliy; Козлов, Анатолій ПавловичA New approach to dynamic allocation of memory paging is described. The approach is distinguished for a choice of the dynamic allocation of memory paging algorithm parameters during a computation process for achieving maximum loading of the central processor.Item ACCURACY RESEARCH METHOD OF THE MODIFIED ALGORITHM FOR DETECTING LINEAR LANDMARKS(Київ «Освіта України», 2018-06) Mukhina, M. P.; Tkachenko, O. Yu.; Barkulova, I. V.A search algorithm for the most extended landmark by which unmanned aerial vehicle can be followed by and implemented flight correction was proposed. The software was developed based on the Python language. The functionality of this software is to detect the linear landmarks from images of geophysical field, received from unmanned aerial vehicle in real time. Images were processed by Hough Line Transform method. As a result, obtained visualization of the object detection with the greatest length, as linear landmark, which allows to estimate unmanned aerial vehicle location. The visual analysis of the effectiveness of this algorithm for inertial navigation system correction shown that the algorithmic software is appropriate for use on unmanned aerial vehicle board and due to applying computer vision systems, gives as correct results of location determining as possible.Item ACHIEVEMENTS IN THE FIELD OF CREATION SOLAR POWER STATION (analytical review)(Київ «Освіта України», 2018-09) Sergeyev, I. Yu.; Protsenko, O. B.An overview of publications in the field of creating power plants using solar radiation energy - solar stations is given. It is shown that solar energy is the source of energy of the future, an exceptionally clean, simple and natural way of generating electricity, which is very little associated with biological danger. Solar energy practically does not cause any harm to the environment, is an environmentally friendly source, does not expend mineral resources and does not violate the thermal balance of the planet. In the next decade, solar energy will become commercially viable. In the future, solar energy may become the main source of continuously renewable energy in the Earth’s biosphere.Item Adaptive Control of Manipulator Robots in a Dynamic Environment Using Neural Networks(National Aviation University, 2024-06-26) Sineglazov, Victor; Синєглазов, Віктор Михайлович; Khotsyanovsky, Volodymyr; Хоцянівський, Володимир ПетровичThe purpose of the study is to develop an approach to planning the trajectory of the manipulator robot using an intelligent system based on neural networks. For this purpose, the work considered the processes of planning and deploying the movement of the robot. The analysis of existing methods of planning the movement of manipulator robots and the review of intelligent control systems made it possible to obtain a complete picture of the current state of this issue. A system is proposed that can perceive the environment and control the movement of the robot by generating the correct control commands. For this, 3 tasks were solved, namely: analysis of the environment in order to determine its features, determination of the trajectory in order to neutralize the collision and determination of controlled influences for the executive authorities in order to implement the movement. The functionality and structure of the neural network for solving each of the tasks are proposed.Item Adaptive high speed measuring converter of average voltage values(National Aviation University, 2020-03-24) Sergeyev, Igor; Сергеєв, Ігор ЮрійовичThe analysis of the measuring converter of average value voltage using the iteratively integrating method of conversion and its comparison with the analysis the generalized block diagram of the iteratively integrating measuring converter were performed. As a result of comparing the circuit of the measuring converter of average voltage values, which implements the iteratively integrating conversion method, with the generalized structural diagram of the iteratively integrating measuring transducer, the basic equations describing this device are obtained. As a result of the analysis of the generalized structural diagram of the iteratively integrating measuring transducer, an engineering solution is proposed that improves the parameters of the measuring converter of average voltage values by adapting it to the influence of changes in the input voltage frequency. This allows us to improve the dynamic characteristics of the converter of average voltage values when the input voltage frequency changes, which is directly related to the increase in the speed of the converter in the given frequency range of the input voltage or, which is equivalent in this case, to the extension of the frequency range of the input voltage, while maintaining the specified performance. It is proposed to adapt the considered converter of average voltage values to a change in the frequency of the input voltage periodically with a predetermined one, based on a priori information about the nature of the frequency change, periodically or occasionally, as the frequency changes.Item Adaptive modeling and forecasting of nonlinear nonstationary processes(National Aviation University, 2020-03-24) Bidyuk, Petro; Бідюк, Петро Іванович; Sineglazov, Viktor; Синєглазов, Віктор МихайловичThe study is directed towards development of adaptive decision support system for modeling and forecasting nonlinear nonstationary processes in economy, finances and other areas of human activities. The structure and parameter adaptation procedures for the regression and probabilistic models are proposed as well as respective information system architecture and functional layout are developed. The system development is based on the system analysis principles such as adaptive model structure estimation, optimization of model parameter estimation procedures, identification and taking into consideration of possible uncertainties met in the process of data processing and mathematical model development. The uncertainties are inherent to data collecting, model constructing and forecasting procedures and play a role of negative influence factors to the information system computational procedures. Reduction of their influence is favorable for enhancing the quality of intermediate and final results of computations. The illustrative examples of practical application of the system developed proving the system functionality are provided.Item Adaptive Stabilization Systems of Dynamic Objects(National Aviation University, 2022-12-27) Ablesimov, A. K.; Аблесімов, Олександр Костянтинович; Konovalyuk, I. A.; Коновалюк, Ілля Олександрович; Zavhorodnii, R. V.; Завгοрοдній, Ρуслан ΒοлοдимирοвичThere are a large number of dynamic objects, for the management of which it is advisable to apply the principles of adaptation. The reasons for applying the principles of adaptation can be combined into two main groups: the variability and complexity of the characteristics of objects and the environment; growing requirements for accuracy and technical and economic characteristics of systems. The difference between adaptive systems and optimal ones is that while in optimal systems the quality indicator is provided for certain parameters of the object, in adaptive systems - for various parameters due to the action of additional elements of adaptation. The choice of one or another approach is determined by preliminary information about the object (process) or the accepted quality criterion. The article presents the main approaches to the selection of possible variants of adaptive systems with stabilization and optimization of the quality of control of systems for stabilizing dynamic objects, based on the type of extremal characteristic of the criterion for assessing their quality.Item ADAPTIVE TESTING SYSTEM BASED ON THE FUZZY LOGIC(Київ «Освіта України», 2018-06) Sineglazov, V. M.; Kusyk, A. V.In this articl, the system analysis of the subject area of the evaluating the test results problem is performed, as a result of which it is classified into clear and fuzzy concepts and relations of the problem, which allowed choosing the fuzzy logic apparatus as the main formalism of the problem solution. Scaling for all linguistic variables of the problem, which allowed to determine their term set reasonably was performed. The fuzzy logic structure was given. The structure of fuzzy logic inference was considered. The principle of constructing fuzzy rules, which allowed to develop production rules for assessing the trainee’s knowledge level using specified input and output linguistic variables is considered. The stages of usage fuzzy logic in the knowledge assessment adaptive testing system was considered. Structure of the knowledge assessment system with fuzzy logic was given. The scheme for submitting questions to the trainee is considered. The structure of adaptive testing system using fuzzy logic is developed.The results of applying adaptive testing in the knowledge assessment of the experimental and control groups of trainees are presented. Based on the obtained results, the effectiveness of adaptive testing based of the fuzzy logic in the process of trainee’s knowledge assessment is shown.Item Aeroelastic vibrations calculation for wind power plants rotors(Osvita Ukrainy, 2015-12) Sineglazov, Viktor; Синєглазов, Віктор МихайловичThe problem of wind turbines aeroelastic rotor vibrations calculation is considered. It shows that the analysis of the elastic blade aero stability in this case differs from the classical approach.Item Aircraft Fuel Measurement System Based on Hydrostatic Pressure Sensor(National Aviation University, 2023-09-29) Smirnov, Oleg; Смірнов, Олег Ігорович; Filyashkin, Мykola; Філяшкін, Микола КириловичThe construction of an aircraft fuel-measuring system based on hydrostatic pressure sensors is considered, which makes it possible to determine the fuel residue in the aircraft tanks during its evolutions. With the evolution of aircraft, measuring the fuel residue in existing fuel metering systems using float and capacitive fuel level sensors has a rather complex electromechanical design and significant weight and size characteristics. This together affects the reliability of such systems as a whole and leads to significant methodological errors in determining the remaining fuel during maneuverable flight. The proposed system using hydrostatic pressure sensors and a computer can significantly increase the efficiency of existing fuel metering systems, and can also be used for calibration tests both on the ground and in flight.Item Aircraft fuel measuring system based on pressure sensors(National Aviation University, 2024-06-13) Duka, Yrii Serhiyovych; Дука, Юрій СергійовичThe use of a hydrostatic sensor in the fuel measuring system during maneuvering of the aircraft made it possible to achieve more accurate and reliable measurements in contrast to other methods of estimating the remaining fuel. The developed system allows you to effectively take into account the influence of various factors, such as pressure, temperature, flight altitude, changes in the position of the aircraft during movement on the determination of the remaining fuel. The results of the work can be used in the practical activities of airlines to optimize the fuel measuring system and improve flight safety. Further research can be aimed at improving technical solutions and expanding the capabilities of the system in different operating conditions of the aircraft.Item ALGORITHM OF FORMING AND SELECTING OF INFORMATIVE FEATURES IN CORRELATION EXTREME NAVIGATION SYSTEM DATABASE(Kyiv, “Osvita Ukrainy”, 2016-03) Mukhina, Maryna; Мухіна, Марина Петрівна; Prymak, Artem; Примак, Артем Петрович; Babeniuk, Anna; Бабенюк, Анна МиколаївнаHierarchical approach to data fusion in complex navigation system is proposed. Low level of data processing in correlation extreme navigation system includes forming and selecting the most infor- mative relevant features. Advanced algorithm is therefore developed based on weighting correlation sampling of template features. Practical efficiency of algorithm is researched based on Speed-Up Robust Feature method of feature points detection and description. Minimization of feature points number in template without decreasing the quality of matching is observed along with reduction of computational costs.Item ALGORITHM OF MORPHOLOGICAL CORRELATION-EXTREME NAVIGATION SYSTEM(Kyiv, “Osvita Ukrainy”, 2016-06) Mukhina, Maryna; Мухіна, Марина Петрівна; Kuzmenko, Anastasia; Кузьменко, Анастасія ОлександрівнаThe paper deals with correlation-extreme navigation to define coordinates of unmanned aerial vehicles more precisely. Normalized morphologic correlation coefficient was chosen as criterion function. Images were processed with the help of intensity based and auto tracking methods. The comparison of these methods by their robustness and normalized morphological correlation coefficient assessment was done on the series of test images with different informative levels.Item ALGORITHM OF VARIATIVE FEATURE DETECTION AND PREDICTION IN CONTEXT-DEPENDENT RECOGNITION(Київ «Освіта України», 2018-03) Mukhina, M. P.; Barkulova, I. V.Application of context-dependent classification for recognition tasks is proposed. In the context-free classification, the starting point was the Bayesian classifier. Morphological features such as object form, area, and eccentricity were considered through context-dependent classification. As result, dependences which can be used for object recognition have been obtained, and further they can be used together with interesting point detectors. The procedure of prediction of object variative features was developed.Item Algorithm of wind turbine combined rotor aerodynamics calculation(Osvita Ukrainy, Kyiv, 2016-09) Sineglazov, Viktor; Синєглазов, Віктор Михайлович; Ziganshin, Anwar; Зіганшин, Анвар Абдуллович; Vasylenko, Mykola; Василенко, Микола ПавловичThe paper is devoted to the vertical axis wind turbines with combined rotors aerodynamical modelling. It includes the analysis of existing wind turbine types, their advantages and disadvantages. The article includes reasoning for combined rotor with vertical axis of rotation building and includes new aerodynamic calculation method.Item Algorithmic software of the fire monitoring system(Osvita Ukrainy, 2014-12) Sineglazov, Viktor; Синєглазов, Віктор Михайлович; Kupriyanchyk, Volodymyr; Купріянчик, Володимир Леонідович; Stepanenko, Illia; Степаненко, Ілля ОлександровичProgram and algorithmic software of information fire monitoring system is developed. The simulation results are presented.Item Algorithmic support of the visual navigation system(National Aviation University, 2019-12-26) Sineglazov, Viktor; Синєглазов, Віктор Михайлович; Ischenko, Vitaly; Іщенко, Віталій СергійовичArticle discusses the implementation of software architecture and algorithmic support for a visual navigation system on-board computer, which imposes restrictions on computing power in the implementation. Partitioning algorithms by logic is proposed, thus logic splitting by layers and can be processed separately on different hardwares. Also in this papper overview of obtaining gps coordinates from pixel shifting is presented. Simple runtime processes and diagnostic operational visual navigation system module is given.