Structural and functional model for developing students’ compositional skills in teaching the fundamentals of graphic composition based on hybrid artificial intelligence

- Краєвська, Олена (orcid.org/0000-0002-8460-958X) and Шеліхова, Інеса (orcid.org/0000-0002-5637-1850) (2026) Structural and functional model for developing students’ compositional skills in teaching the fundamentals of graphic composition based on hybrid artificial intelligence Information Technologies and Learning Tools, 4 (114). pp. 150-169. ISSN 2076-8184

Text Олена Краєвська.pdf - Published Version Download (1MB)

Abstract

The article presents and substantiates a structural and functional model for learning and automated assessment of compositional skills in a VR environment based on hybrid artificial intelligence. The model is conceptualized as an integrated system combining the target, content‑technological, procedural, and control‑result components. Its functioning is ensured through the interaction between the VR environment and an analytical module powered by hybrid AI, which integrates rule‑based analysis of classical compositional principles with data‑driven computer vision algorithms. The technical logic of the model is based on a multilevel analysis of scene parameters, which enables formalized calculations of the center of visual weight, symmetry, and geometric balance of elements, as well as the identification of compositional patterns derived from training data. The scientific novelty lies in the creation of a comprehensive model capable of performing automated verification of 3D scene parameters in real time and generating individualized intelligent feedback for students. The practical significance of the proposed approach was confirmed by a pedagogical experiment (N=39) conducted with the use of digital learning resources and learning analytics. Statistical processing of the results using Pearson’s χ² criterion demonstrated a statistically significant (p < 0.05) increase in the level of compositional skills formation in the experimental group compared to the control group, while the automated assessment algorithms showed high accuracy in comparison with expert evaluations of instructors. The obtained results confirm the effectiveness of the proposed model and highlight the potential of integrating hybrid intelligent systems to enhance the quality of training future specialists in computer graphics, digital design, and engineering visualization.

Item Type:	Article
Keywords:	virtual educational environment; artificial intelligence; learning model; graphic composition; digital educational technologies; automated assessment.
Subjects:	Science and knowledge. Organization. Computer science. Information. Documentation. Librarianship. Institutions. Publications > 00 Prolegomena. Fundamentals of knowledge and culture. Propaedeutics > 004 Computer science and technology. Computing. Data processing > 004.9 Application-oriented computer-based techniques > 004.94 Simulation Science and knowledge. Organization. Computer science. Information. Documentation. Librarianship. Institutions. Publications > 3 Social Sciences > 303 Methods of the social sciences Science and knowledge. Organization. Computer science. Information. Documentation. Librarianship. Institutions. Publications > 3 Social Sciences > 37 Education > 37.01/.09 Special auxiliary table for theory, principles, methods and organization of education > 37.09 Organization of instruction Science and knowledge. Organization. Computer science. Information. Documentation. Librarianship. Institutions. Publications > 3 Social Sciences > 37 Education > 378 Higher education. Universities. Academic study
Divisions:	Institute for Digitalisation of Education > Generic resouse
Depositing User:	Алла 1 Алла Почтарьова
Date Deposited:	31 Oct 2026 15:47
Last Modified:	31 Oct 2026 15:47
URI:	https://lib.iitta.gov.ua/id/eprint/750642

Downloads

Actions (login required)

View Item