A COMPARATIVE ANALYSIS OF APPROACHES TO THE DEFINITION OF USER INTEREST TO LEARNING MATERIALS IN ADAPTIVE LEARNING SYSTEMS

Authors

  • Є. Б. Артамонов

DOI:

https://doi.org/10.18372/2310-5461.32.11180

Keywords:

adaptive training, learning system, fuzzy sets, interest rate, software

Abstract

This article considers the problem of approaches to automatically definition of the interest rate to elements of e-learning systems. Interest rate is used as one of the key parameters that characterize the quality of the perception of educational material if you are working without the direct feedback from the teacher. Based on the assessment of the quality of perception and a number of other options can be adaptive formation of information resources that will automatically build a flexible system of e-learning system content. The main problem of assessment interest is as follows: 1) the lack of ready mathematical models describing the relationship interest and users reactions to educational materials, 2) the absence of a statistical sample of the evaluation relations material-interest- student, 3) some of the parameters of the user reactions estimates are non-numeric character. The article presents a comparative analysis of the following methods: Bayes, the phase interval, of logical inference, neural networks, fuzzy sets. It is shown that the fuzzy logic is the most perspective mathematical apparatus to develop a system of determining the interest rate of user in learning materials.

References

Evidence-Based Educational Methods / J. M. Da-niel, W. M. Richard, D. R. Roger and others; Edited by J. M. Daniel and W.M. Richard. — Elsevier Science & Technology Books, 2004. — 408 р.

Cristea A. Adaptive Hypermedia and Adaptive Web-Based Systems / Cristea Alexandra, Aroyo Lora // Second International Conference, May 29–31, 2002, Málaga, Spain. — P. 122–132.

Artamonov E. B. Concept of creating a software environment for automated text manipulation // E. B. Artamonov, O. O. Zholdakov. — Scientific journal “Proceedings of the National Aviation University”. — K. : NAU. — 2010. — Вип. 3 (44). — P. 111–115.

Дуда Р. Распознавание образов и анализ сцен / Р. Дуда, П. Харт; пер. с англ. — М. : Мир, 1976. —511 с.

Козелецкий Ю. Психологическая теория решений / Ю. Козелецкий. — М. : Прогресс, 1979. — 504 с.

Ротштейн А. П. Прогнозирование надежности алгоритмических процессов при нечетких исходных данных / А. П. Ротштейн, С. Д. Штовба // Кибернетика и системный анализ. — 1998. — №4. — С. 85–93.

Литвиненко А. Е. Определение класса истинности логических формул методом направленного перебора / А. Е. Литвиненко // Кибернетика и системный анализ. — 2000. — № 5. — С. 23–31.

Осуга С. Обработка знаний / С. Осуга; пер. с япон. — М. : Мир, 1989. — 292 с.

Назаров А. В. Нейросетевые алгоритмы прогнозирования и оптимизации систем / А. В. Наза-ров, А. И. Лоскутов. — СПб. : Наука и техника, 2003. — 394 с.

Тененёв В. А. Гибридный генетический алгоритм с дополнительным обучением лидера / В. А. Те-ненёв, Н. Б. Паклин // Интеллектуальные системы в производстве. — 2003. — № 2. — С. 181–206.

Published

2016-12-19

Issue

Section

Information and Communication Systems and Networks