Наукові публікації та матеріали кафедри авіаційних комп'ютерно-інтегрованих комплексів (НОВА)

Permanent URI for this collectionhttp://er.nau.edu.ua/handle/NAU/58730

Browse

Browsing Наукові публікації та матеріали кафедри авіаційних комп'ютерно-інтегрованих комплексів (НОВА) by Subject "004.8 (045)"

Filter results by typing the first few letters
Now showing 1 - 9 of 9
  • Thumbnail Image
    Item
    COMPARATIVE CHARACTERISTICS OF KERAS AND LASAGNE MACHINE LEARNING PACKAGES
    («Освіта України», 2017-09) Sineglazov, V. M.; Omelchenko, M. O.; Hotsyanivskyy, V. P.
    A comparative analysis of the Lasagne and Keras computer libraries has been performed to construct convolutional neural networks used in image processing systems. The carried out researches have allowed to define their advantages and disadvantages that will allow to make to researchers the correct choice at the decision of applied problems.
  • No Thumbnail Available
    Item
    CONCEPTUAL DESIGN OF SOLAR UNMANNED AERIAL VEHICLE
    (Київ «Освіта України», 2018-06) Karabetsky, D. P.
    In this paper, emphasis was placed on the fact that a solar unmanned aerial vehicle, should be used in the context of certain missions, taking into account this, the general structure of the aircraft's internal systems was presented. The criterion for continuous flight during the day is analyzed. Based on this, an approach is presented for calculating and modeling the characteristics of a unmanned aerial vehicle, with the possibility of recharging during a daylight solar cycle. The main parameters of the aircraft were the wingspan and aspect ratio of the wing and the capacity of the batteries.
  • Thumbnail Image
    Item
    Hybrid energy storage system design
    (National Aviation University, 2020-07-06) Sineglazov, Victor; Yudenko, Igor; Синєглазов, Віктор Михайлович; Юденко, Ігор Олександрович
    The necessity of hybrid energy storage system design is shown. It is considered the main components of hybrid energy storage systems and their features. It is shown that these systems are characterized by a beneficial coupling of two or more energy storage technologies with supplementary operating characteristics. The hybrid energy storage systems may include super capacitors, flywheels, superconducting magnetic energy storage, lithium-ion batteries, fuel cells. It is analyzed the use of every possible component as a part of the hybrid energy storage system in different operating conditions. It is considered a sizing methodology optimization for hybrid energy storage systems based on blast algorithm and hybrid neural networks.
  • Thumbnail Image
    Item
    IMAGE PROCESSING OF CT WITH HELP OF A CONVOLUTIONAL NEURAL NETWORK
    (Kyiv, “Osvita Ukrainy”, 2016-12) Sineglazov, Viktor; Синєглазов, Віктор Михайлович; Omelchenko, Maxym; Омельченко, Максим Олегович
    The methods of learning Artificial Neural Network to analyze computed tomography images and identify them on the disease.
  • Thumbnail Image
    Item
    IMAGE PROCESSING WITH LIVER MRI CONVOLUTIONAL NEURAL NETWORK
    (Kyiv, “Osvita Ukrainy”, 2016-12) Sineglazov, Viktor; Синєглазов, Віктор Михайлович; Hotsyanivskyy, Vladimir; Хоцянівський, Володимир Петрович
    The methods of learning machine learning models to analyze magnetic resonance imaging images and identify them on the disease.
  • Thumbnail Image
    Item
    Intelligent System of Personnel Management
    (Київ «Освіта України», 2019-03) Sineglazov, V. M.
    It is considered the problem of Human Resources Management with help of Artificial Neural Networks in area of desired job search and help of recruiters that use this resource to find the best candidate for a given job. It is proposed to use neural networks for view CVs, ranking candidates according to their skill level and create machine learning algorithms to automate processes for checking resumes. The convolutional neural network is used for the problems solution. As a learning algorithms is used a genetic algorithm. It is developed an approach for chromosome structure optimal choice.
  • Thumbnail Image
    Item
    INTELLIGENT WEATHER FORECAST SYSTEM
    (Київ «Освіта України», 2018-03) Sineglazov, V. M.; Omelchenko, M. O.; Hotsyanivskyy, V. P.
    It is considered the creation of intelligent weather forecast system in traditional statement as the prediction of time series For the solution of this problem it is chosen a random forest algorithm. Examples of program implementation of the algorithm are given using libraries for the python programming language, namely Pandas and Skicit-learn. It is considered a problem solution for a number of real examples and corresponding results are given.
  • Thumbnail Image
    Item
    INVESTIGATION OF BLADE ATTACK ANGLE VALUE ON VERTICAL AXIAL WIND POWER PLANT
    (Київ «Освіта України», 2018-06) Sineglazov, V. M.; Shvaliuk, I. S.
    In this paper, the efficiency of the vertical-axial wind power plant at various wind speeds depending on the angle of attack of the rotor blades was investigated. The object of the investigation was a three-bladed Darrieus rotor. During the modeling we used the viscous gas flow model with averaging of turbulent characteristics (Reynolds-averaged Navier–Stokes equations for an incompressible fluid. These investigations would allow us to develop new principles for constructing vertical-axial wind turbines with a variable angle of attack of the blades in order to increase the energy efficiency of vertical-axis wind turbine.
  • No Thumbnail Available
    Item
    Maximum power point tracking for photo modules
    (National Aviation University, 2020-03-24) Sineglazov, Viktor; Синєглазов, Віктор Михайлович; Karabetsky, Denis; Карабецький, Денис Петрович; Klanovets, Oleksandr; Клановець, Олександр Володимирович
    It is considered the problem of maximum power point tracking for photovoltaic modules. The solution of this problem is based on a static parametric meta-optimization for swarm intelligence algorithms. For the problem solution Particle Swarm Optimization algorithm meta-optimized with Bat Search algorithm is proposed. The basic idea for the algorithms is that they consist of the base algorithm, which is used to solve the main optimization problem and the meta-algorithm used to find an optimal strategy for the base one. The object function for the base algorithm is an object function of the general optimization problem. The meta-algorithm evaluates the meta-function defined at each generation and tries to minimize it by searching for better strategies for the base algorithm. It is considered the example of its application.