Russian Federation
The issue of effective testing of the quality of students’ knowledge is relevant and significant in the field of education. It is necessary to improve the practice of assessing students’ knowledge in order to achieve maximum quality and efficiency. However, the educational process should be not only effective but also maximally adapted to each student. The paper presents a system for optimizing the quality control of students’ knowledge, depending on their personal characteristics. This task will be solved on the basis of intelligent methods of modeling, optimization and decision making. As one of the ways to test the quality of knowledge, a control work was chosen, performed both individually and in small groups. This article is devoted to the issue of the optimal distribution of students for work in groups or individually. The developed adaptive system performs optimization based on several optimality criteria and taking into account the normalized personal characteristics of students. As an optimization method, a genetic algorithm was chosen, the chromosomes of which are encoded in accordance with the personal characteristics of students. The best options for combining the personal qualities of students when divided into groups are determined. Pareto-optimal sets for a multi-criteria objective function are obtained taking into account the criteria importance coefficients. The developed system will allow not only to reduce the teacher’s time spent on the process of dividing into groups, but also to make this process the most effective for students by taking into account their personal qualities.
knowledge quality control, multicriteria optimization, genetic algorithm, Pareto set, decision making system
1. Kurapova T. Yu. Kriterii uspeshnosti obucheniya uchashchikhsya obshcheobrazovatel'nykh shkol // Psikhologiya v Rossii i za rubezhom : materialy I Mezhdunar. nauch. konf.- SPb. : Renome, 2011. - S. 106-109. URL: https://moluch.ru/conf/psy/archive/32/1092/ (data obrashcheniya: 27.01.2022).
2. Bakoush M. Evaluating the role of simulation-based experiential learning in improving satisfaction of finance students // The International Journal of Management Education, 20 (3), 100690.
3. Dogadina, E.P.; Smirnov, M.V.; Osipov, A.V.; Suvorov, S.V. Formation of the Optimal Load of High School Students Using a Genetic Algorithm and a Neural Network. Appl. Sci. 2021, 11, 5263.
4. Fredriksdotter H., Norén N., Bråting K. Investigating grade-6 students’ justifications during mathematical problem solving in small group interaction // The Journal of Mathematical Behavior, 2022, 62, 100972.
5. Guarino A., Malandrino D., Zaccagnino R. Adaptive talent journey: Optimization of talents’ growth path within a company via Deep Q-Learning // Expert Systems with Applications, 2022, 209, 118302.
6. Luo X., Sun Y., Liu Y. Course timetable optimization for a university teaching building considering the building energy efficiency and time-varying thermal perception of students // Building and Environment, 2022, 219, 109175.
7. Rashid M., Mathew J., Raja K. Optimization of backpack loads using gait parameters in school boys // Journal of Bodywork and Movement Therapies, 2020, 25, pp. 174-182.
8. Xu Y., Yan Ch., Jiang Y. A three-stage optimization method for the classroom envelope in primary and secondary schools in China // Journal of Building Engineering, 2022, 52, 104487.
