Кафедра медіасистем та технологій (МСТ)

Постійний URI для цієї колекції

https://openarchive.nure.ua/handle/document/57

Перегляд

Перегляд Кафедра медіасистем та технологій (МСТ) за автором "Al-Sharo Yasser Mohammad"

Зараз показано 1 - 3 з 3
  • Зображення мініатюри
    Публікація
    Generalized Procedure for Determining the Collision-Free Trajectory for a Robotic Arm
    (IRAQI, 2023) Al-Sharo Yasser Mohammad; Abu-Jassar Amer Tahseen; Sotnik S.; Lyashenko V.
    Robotic systems play an important role in the development and modernization processes of production, facilitation of labor, and human life. The robotic manipulators are outstanding among such systems. Such robots can be used for various spheres of their application. In this case, there is the manipulator’s effective control problem in the working area, of which there may be various obstacles. Therefore, a procedure is required to find the optimal path for moving the robotic arm. To develop such a procedure, the literature was reviewed, and the structural diagram of the ontrol system of such a robot and its components was summarized. It proposed a mathematical formalization of the search for the optimal path to move the robot arm, an algorithm based on a modified method of navigation graphs, to realize the more natural movement of the robot arm. Experimental studies were conducted with different numbers of objects on the path of robot arm movement, which were combined into groups. The temporal results of this process are presented in a diagram.
  • Зображення мініатюри
    Публікація
    Neural Networks As A Tool For Pattern Recognition of Fasteners
    (Seventh Sense Research Group, 2021) Al-Sharo Yasser Mohammad; Abu-Jassar Amer Tahseen; Sotnik, S.; Lyashenko, V.
    The work is devoted to the study of pattern recognition features of industrial parts in individual fasteners' forms. The main types of neural network architectures and their features are considered. Neural networks are classified into separate categories for ease of perception and analysis. An approach to recognition of hardware products such as fasteners using neural network, which is implemented in Python using Keras machine learning library, is proposed. The main generators are described: for training data, testing, and validation. Codes fragments of corresponding programs for implementation of the proposed approach to pattern recognition of fasteners are presented
  • Зображення мініатюри
    Публікація
    Some Features of Classifiers Implementation for Object Recognition in Specialized Computer systems
    (TEM Journal, 2021) Abu-Jassar Amer Tahseen; Al-Sharo Yasser Mohammad; Lyashenko, V.; Sotnik, S.
    Generalized formalization of recognition algorithm for specialized computer systems is presented in this paper. The structure features of image recognition methods, which have to be taken into account when developing classifiers for object recognition in specialized computer systems, are described. The fundamental types of images characteristics-features, which are used in various methods of image recognition, are discussed. Approaches to development of classifiers for recognizing robotization objects, which are implemented on basis of Haar classifiers, are discussed. The issues of using machine learning algorithm of adaptive gain AdaBoost for development of such classifiers are also considered. Utilities have been developed for implementation of classifiers for object recognition in specialized computer systems.