Browsing by Author "Kynabay B."

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Development of Artificial Intelligence algorithm for deaf-and-dumb students to enhance education equity in Kazakhstan
    (2020) Kynabay B.
    This research work proposes the solution of academic inequity problems of students with specific disabilities like deafness. The main task is to construct a system that will ease the communication between deaf and dumb students and the environment by integrating an algorithm that transforms hand gestures into text, speech into text and etc. Proposed system converts multilingual speech into text. The novelty and originality of the work is that this system works for Kazakh language, realized on Telegram bot and it is free of charge. Conversion is realized by extracting information from speech signals. The system is developed in Python language by using Al techniques and Machine Learning (ML) algorithms. The main focus of the work is to implement it in educational sphere, specifically in lectures of universities and colleges what plays a significant role in achieving inclusion and education equity in the country.
  • Thumbnail Image
    ItemOpen Access
    DEVELOPMENT OF IMAGE CAPTIONING MODEL BY USING DEEP LEARNING TOOLS
    (СДУ хабаршысы - 2019, 2019) Kynabay B. ; Aldabergen A. ; Shamiluulu S.
    Abstract. Automatic formation of image description is one of the most challenging and popular topics in the field of deep learning (DL) for nowadays. In this work image captioning convolutional neural network model (VGG16) is developed by implementing deep learning tools and techniques. Specifically, this work’s resulting product can be implemented in a system that answers to the question, based on the image given. Image captioning includes two main sub-processes: image processing and natural language processing. The model was constructed from 16 layers and it uses Flicker 8K data-set of images for captioning. The model was evaluated by using BLEU metric and its value was nearly 0.75, it takes one image as an input and returns one description for that image.