Search academic texts

Information × Registration Number 0223U002334, 0121U110668 , R & D reports Title Theoretical bases of information technology for recognizing the psycho-emotional state of students of the distance learning system popup.stage_title Head Tereikovska Liudmyla О., Registration Date 15-02-2023 Organization Kyiv National University of Construction and Architecture popup.description2 The purpose of the work is the development and research of a neural network model designed to detect the borders of a person's face on raster images and adapted to the conditions of use in a distance learning system. As a result of the analysis of literary sources in the field of pedagogy and in the field of creating information systems, the need to expand the functional capabilities of distance learning systems by introducing means of automatic recognition of the listener's emotional state is substantiated. With the use of the conceptual model for recognizing the psycho-emotional state of the listener of the distance learning system developed at the first stage of this research work, the expediency of using means of recognizing the listener's emotions based on the image of his face is shown. It was determined that known recognition tools have shortcomings associated with the imperfection of neural network models designed to detect facial boundaries on bitmap images, which are insufficiently adapted to the conditions of use in emotion recognition systems of listeners of distance learning systems. An approach to determining the most effective type of neural network model for facial boundary detection is proposed, which involves expert evaluation of the effectiveness of acceptable types of models and conducting computer experiments to make a final decision. As a result of the conducted research, it was determined that among the types of neural network models tested in the task of segmentation of raster images, the U-Net model is the most effective for detecting facial borders on small raster images. Using U-Net provides a mask selection accuracy of 0.88. The necessity of improving the mathematical support, which is used to determine the accuracy of border detection, is determined. Ways of further research are related to the development of methods and means of recognizing the psycho-emotional state of students of the distance learning system. Product Description popup.authors Tereikovska Liudmyla О. popup.nrat_date 2023-02-15 Close