Перегляд за Автор "Tyschenko, O."

Зараз показуємо 1 - 6 з 6
  • Ескіз
    Документ
    An Approach to Using MobileNet CNN-model for Gesture Recognition
    (2024) Mazurets, O.; Zalutska, O.; Tyschenko, O.; Bohdanova, A.; Мазурець, Олександр Вікторович
    As a result of the work performed, one of the types of MobileNet architecture of CNN artificial neural networks was applied in practice to solve the problem of gesture recognition in real time. The obtained results are important not only in the scientific sense, but also for practical application, because neural networks help people with various diseases, such as Parkinson's disease, speech or hearing impairment, tunnel syndrome, to facilitate their interaction with the computer, to carry out effective studying in schools and universities and, of course, socializing. So, these are just the first steps to simplify people's lives as much as possible and make it bright, despite certain limitations
  • Ескіз
    Документ
    Datalogic Relation Model for Automated Evaluating the Semantic Integrity of Test Tasks Sets by Machine Learning Means
    (2024) Мазурець, Олександр; Hardysh, D.; Mazurets, O.; Tyschenko, O.
    Datalogic relation model for automated evaluating the semantic integrity of test tasks sets was designed. The developed intelligent system has significant potential for use in educational institutions and organizations where assessing the alignment of test tasks with educational materials is critical. By automating this evaluation process, the system ensures objectivity and reliability in the results.
  • Ескіз
    Документ
    Intelligent System for Automated Assessment of Test Tasks Sets Conformity to Semantic Structure of Educational Materials
    (2024) Мазурець, Олександр; Hardysh, D.; Tyschenko, O.; Mazurets, O.
    Intelligent system for testing knowledge level and analyzing test representativeness of tests was designed and practically implemented in the form of a web platform, which provides the possibility of effective assessment of users' knowledge and skills. The generalized scheme, database datalogic model and component interaction diagram of intelligent system for testing the level of knowledge and analyzing the representativeness of tests were designed. Practical use of the developed platform as tool for self-testing and learning is proposed, which will allow users to check their knowledge, track progress in learning and analyze the representativeness of tests to educational materials.
  • Ескіз
    Документ
    Intelligent System for Determining the Object Attributes Values by Neural Networks Means by Graphic Images in Databases
    (2024) Mazurets, O.; Uspenska, K.; Vit, R.; Tyschenko, O.; Мазурець, Олександр Вікторович
    The created method for determining the values of object attributes is designed to convert input data in the form of a video stream and a fixation frequency indicator into output data in the form of a list of values of actual object attributes in the database by obtaining a frame for processing from the video stream, receiving an object image for recognition from the frame, and determining the value of the object attribute from the image.
  • Ескіз
    Документ
    Method for Neural Network Detecting Changed Images of People's Faces Using CNN
    (2024) Мазурець, Олександр Вікторович; Pokhytun, A.; Mazurets, O.; Molchanova, M; Tyschenko, O.
    Method for detecting altered human face images using neural network technologies was proposed to process the input data, which is represented by a training set of face images for the training stage, a test set of images for verification, and a working face image for classification. The method includes the steps of training and evaluating the neural network using the training set of face images, as well as the process of detecting changes in the working face image. The created method for detecting modified images of human faces is designed to transform the input data in the form of a dataset of modified images of human faces and working images for classification into output data with the conclusion whether the photo is modified, as well as the types of modifications used.
  • Ескіз
    Документ
    Semantic search of relevant images using vector databases
    (2025) Ostapchenko, N.; Tyschenko, O.; Denysenko, B.; Mazurets, O.; Мазурець, Олександр Вікторович
    This paper presents a method for semantic image search using vector databases, enabling efficient retrieval of relevant visual content based on textual or visual queries. The proposed approach leverages state-of-the-art embedding models, such as OpenCLIP, to convert both images and queries into high-dimensional vector representations. These vectors are stored and compared in a vector database to determine semantic similarity. The system supports both text-to-image and image-to-image search, significantly enhancing the precision of results by focusing on content-level meaning rather than keywords. The solution is applicable in various domains requiring fast and accurate access to large-scale image repositories.