REPRESENTATION OF KNOWLEDGE IN LEARNING SYSTEMS BASED ON THE THEORY OF FUZZY SETS
Abstract
Using of information technologies and e-learning systems increases opportunities of teachers and learners in reaching their studying process goals. It takes into account the individual characteristics of each and provides opportunities for e-learning. But e-learning systems using is limited despite of many researchers and the obvious advantages of such systems. One of the main reasons of such limitation is the usage of precise quantitative techniques in a hard-structured and fuzzy area as a learning process. In designing of information learning systems developers are faced with the problem of modeling knowledge which can be divided into two categories conventionally: personal and subject. Subject knowledge is defined education program and represents expert knowledge (the teacher) about the composition and structure of the subject. Personal knowledge can determine the level of the material studied by learner. This kind of knowledge is dynamic, changing in the educational process and designed to adapt e-learning systems to the particular learner. There are a large number of knowledge representation models. Commonly used models are logical, productional, network, frame-based and mathematical models. The main advantage of the mathematical model is the accuracy, abstraction processing, communication logically uniform way. Mathematical model of knowledge representation based on the theory of fuzzy sets take into consideration the semantic ambiguity expert assessment (teacher) degree of preparation to learner.
About the Authors
Y. B. Popova
Belarusian National Technical University, Minsk
Belarus
Belarus
Yuliya B. Popova, PhD, Associate Professor at the Software Department
A. I. Burakovski
Belarusian National Technical University, Minsk
Belarus
Belarus
Alexander Burakovski received the graduate degree in software engineering from the Belarusian National Technical University in 2012 and the Master’s degree in system analysis and control of information processing in 2013. He is currently working on PhD degree program.
References
1. Burakovskij, A. I. Mathematical models of users in adaptive learning systems / A. I. Burakovskij, Y. B. Popova // Informacionnye tehnologii v obrazovanii, nauke i proizvodstve : materialy MNTIK. — Rezhim dostupa: http://www.bntu.by/news/67-conferencemido/1545–2014–11–22–12–18–35.html.
2. Brusilovskij, P. L. Adaptive and intelligent technologies in network learning / P. L. Brusilovskij // Novosti iskusstvennogo intellekta. – 2002. – № 5. – P. 25–31.
3. Brusilovskij, P. L. Intelligent tutoring systems / P. L. Brusilovskij // Informatika. Informacionnye tehnologii. Sredstva i sistemy. – 1990. – № 2. – P. 3–22.
4. Savel’ev, A. Ja. Automated Training System CONTACT based on ES computers: version KONTAKT/OS. Vyp.2 / A. Ja. Savel’ev ; pod red. L. V. Niceckogo. – Riga : RPI, 1979. – 67 p.
5. Garret, B. The value of intelligent multimedia simulation for teaching clinical decision-marking skills / B. Garret, D. Callear // Nurse Educ Today. – 2001. – № 21. – P. 382–390.
6. Spicyn, V. G. Knowledge representation in information systems. / V. G. Spicyn, Ju. R. Coj. – Tomsk : Izd-vo Tomskogo politehnicheskogo universiteta, 2008 – P. 8.
7. Polani, M. Personal knowledge / M. Polani. — M. : Progress, 1985. – 103 p.
8. Popov, Je. V. Iskusstvennyj intellect : spravochnik. Kn. 1. The communication systems and expert systems / pod red. Je. V. Popova. – M. : Radio i svjaz’, 1990. – 464 p.
9. Klykov, M. S. Fundamentals of Management : uchebnoe posobie / M. S. Klykov, N. P. Grigor’ev, T. I. Balalaeva. – Habarovsk : Izdatel’stvo DVGUPS, 2007. – P. 2.
10. Bershtejn, L. S. Functional-structural research of situational framing network operating system with fuzzy logic / L. S. Bershtejn [i dr.] // Izv. AN. Ser. Tehnicheskaja kibernetika. – 1994. – № 2. – P. 120–124.
11. Golovchiner, M. N. Introduction to knowledge system : kurs lekcij / M. N. Golovchiner. – Tomsk, 2011. – P. 20.
12. Korobova, I. L. Methods of knowledge representation / I. L. Korobova. – Tambov : Izdatel’stvo TGTU, 2003. – P. 10–13.
13. Borisov, A. N. Processing fuzzy information in decision-making systems / A. N. Borisov [i dr.] – M. : Radio i svjaz’, 1989. – P. 304.
14. Karelin, V. P. Models and methods of knowledge representation and decision-making in intelligent information systems with fuzzy logic / V. P. Karelin // Vestnik Taganrogskogo instituta upravlenija i jekonomiki. – 2014. – № 1 (19). – P. 75–83.
15. Belous, V. A. Modern knowledge representation models in training systems / V. A. Belous, E. S. Kudinov, M. Je. Zhelnin // Uchenye zapiski. Jelektronnyj nauchnyj zhurnal Kurskogo gosudarstvennogo universiteta. – 2010. – № 1. – P. 9–14.
16. Denisova, I. Ju. Mathematical models of expert knowledge representation in e-learning system / I. Ju. Denisova, M. V. Bakanova // Izvestija Penzenskogo gosudarstvennogo pedagogicheskogo universiteta. PGU. – 2011. – P. 360–361.
Review
For citations:
Popova Y.B., Burakovski A.I. REPRESENTATION OF KNOWLEDGE IN LEARNING SYSTEMS BASED ON THE THEORY OF FUZZY SETS. «System analysis and applied information science». 2016;(2):58-65. (In Russ.)
Views:
956
Email this article 