Smirnov Viktor
Faculty Computers Sciences and Technologies
Department Automated Control Systems
Speciality «Information Control System»
Adaptive architecture development for remote learning system
Scientific adviser: Fonotov Anastas
Abstraction
Content
Introduction
The technique of teaching with use of technologies of remote learning essentially differs from traditional technologies of learning and basically leans on independet studying of a course by the student, and the considerable part of work of the teacher is translated on the computer. Actually learning systems acquire knowledge of the expert-teacher and prove them to the student. Therefore it is possible to ascertain that the basic feature of remote formation is granting to students of possibility independently to receive necessary knowledge, to use modern information technologies. Possibility of an individualization of training is one of the major advantages of use of information technology in educational process. At an essential difference in level of base preparation and individual abilities of students the plan of the educational process assumed as a basis in traditional systems of remote training (LMS) identical to all, is optimum at the best only for 15-30 % of students: for one it too strained, for others, on the contrary, insufficiently intensive [6]. As a result intellectual and material resources as individual, and a society are not effectively used. The review of the most known systems widely used in modern remote training classical approaches, such as ANGEL, BlackBoard, Desire2Learn, ILIAS, Lotus LearningSpace, Moodle, WebCT, has shown that, as a rule, the training course presented in the environment of LMS, represents a set of static hypertext documents. All students receive an identical material for studying without their specific features. The student cannot receive the operative help from the teacher or other student as it occurs in a usual educational class. A new research direction in sphere of remote learning on a Web-platform are adaptive and intellectual technologies in training. The problem of this direction of researches - to include in remote training systems of possibility of an individualization [1]. By means of adaptive and intellectual technologies the training system considers individual abilities of the student, its previous knowledge, abilities. On the basis of this data about the student training process passes for it an optimum way. All it promotes that today there is a problem of maintenance of the individualised training in remote formation which consists in working out of methods, technologies and software of creation of adaptive systems of remote learning on the basis of intellectual Internet technologies [2].
In modern conditions of a labour market there was obvious a necessity of perfection of a professional training for system of multilevel continuous formation. There is an education system reforming, transition to multilevel structure of preparation the bachelor/master on the basis of the competent approach. Formation key becomes an educational institution main objective.
In higher educational institutions, students with various initial level of preparation - received the general average, the initial and average vocational training, works having a certain experience on manufacture and combining it with study come. In this connection it is represented inexpedient to conduct their training under the uniform curriculum. At someone from them can be insufficiently generated necessary for the competence; and for someone knowledge can appear superfluous that involves loss of time and means.
The basic feature of the modern education system solving described problems, training possibility on an individual educational trajectory is, is more and more attractive recently.
The practical importance of research is defined by that circumstance that the advanced architecture adaptive LMS is of interest for expert systems of learning.
The review of researches on a theme
Difference of adaptive hypermedia-systems from simply hypermedia-systems consists available at the first model of the user on which basis adaptation is under construction. To construct and support actual model of the user adaptive system collects the data from the different sources, including implicit supervision over actions of the user both obvious poll and introduction of the data by it. The model of the user and adaptation are two parties of one process. The quantity and quality of the information presented to models of the user, depends on type of adaptable effect which the system [3] aspires to give.
The basic characteristics which are modelled and used by adaptive Web-systems, knowledge, interests, the purposes, preconditions, specific features and a context of work of users is. Each adaptive system, as a rule, uses some subset of the given set.
The model of the user depends on a way of modelling of subject domain in system. The model of knowledge of the user can be scalar, representing level of knowledge of the pupil in subject domain a unique value on some scale - quantitative (for example, from 0 to 5) or qualitative (for example, it is excellent, good, satisfactory, unsatisfactory). The Most widespread is the overlay model of knowledge of the pupil. It represents knowledge of the pupil as a subset of model of subject domain which in turn reflects knowledge of a subject in level of the expert [5]. The overlay model keeps for each fragment of knowledge of subject domain some estimation of knowledge of the user by the given fragment. There is also a model on the basis of errors which represents both correct knowledge of the student, and false. Modelling of interests of the user - a new direction, characteristic for Web-systems. Interests of the user hypertext systems of news, electronic shops, museum guides and other systems in which access to the information is based on interests [7] get great value for adaptive hypermedia-systems in connection with increase in volume of the information and growth of popularity of such types of the information-focused systems as encyclopaedias. It is necessary to notice that these tendencies, and also constructivism popularisation in training have influence and on educational services and consequently demand more attention to model of interests of the user in an educational context. For information retrieval and information-filtering systems construction of model of interests on the basis of keywords is characteristic. But adaptive hypermedia of system adapted the approach on the basis of semantic concepts for modelling of interests [11]. In this case the model of interests becomes very similar to overlay model of knowledge of the user. Synthesis of approaches on the basis of keywords with the approach on the basis of concepts for model of interests of the student is perspective.
The purposes and problems represent the nearest purpose of work of the user in adaptive system. As a rule in training systems in this model the educational purpose is represented. Achievements of the educational purpose dares automatic planning and definition of sequence of a training course. The purposes of the pupil can be modelled by means of the catalogue of the purposes. This approach is a little similar to overlay model. Its basis is in advance certain catalogue of the possible purposes of the pupil which the system should be able to distinguish.
Preconditions of the user concerning its previous experience out of key subject domain of system. Here it is necessary to carry a trade, functions, experience in the connected areas and even a specific sight of the user at subject domain [9]. We will notice that similar characteristics are important in a context of continuous training, however till now they were used in few systems.
The model of specific features submits characteristics which represent individuality of the user. Psychological and personal features, cognitive
styles and factors and educational style here concern.
Rather new direction is modelling of a context of work of the user. Here it is necessary to carry representation of a hardware-software platform of the user, its geographical position and an emotional condition.
Conclusion
The review of the basic technologies of adaptive and intellectual learning systems allows to draw conclusions concerning features of application of such technologies in a context of continuous formation. It is possible to express one of problems of many systems as a principle of "a full intellectual management» - complete control tendencies over educational process. System, being teaching conscious, tries to make all for the user and tends to take of a position of the full power over educational process. The approach by a principle of "intellectual partnership» when system, having pedagogical consciousness sees expedient, directs the user in the spirit of the adviser and gives it ample opportunities for independent adaptation of the training. It allows to use «for the help to artificial intelligence» systems natural intelligence of the pupil that, undoubtedly, becomes the powerful contribution to learning efficiency and strongly enough democratises the educational process corresponding to requirements of continuous training.
1. Касьянов В.Н., Касьянова Е.В. // Методы и средства адаптивной гипермедиа. Вычислительные технологии. — 2004. — Т.9, Часть 2. — С. 333-341. 245
2. Peter Brusilovsky, Sergey Sosnovsky, Michael Yudelson, Amruth Kumar, Sharon Hsiao. // User Model Integration workshop. 5th International conference on Adaptive Hypermedia and Adaptive Web-Based Systems. ? Hannover, 2008. P. 1?9.
3. Desmond Elliott, Frank Hopfgartner, Teerapong Leelanupab, Yashar Moshfeghi, Joemon M. Jose. // An Architecture for Life-long User Modelling. — 2009.
4. Loc Nguyen, Phung Do. // Learner Model in Adaptive Learning. ? 2008.
5. Гагарін О.О., Титенко С.В. Дослідження і аналіз методів та моделей інтелектуальних систем безперервного навчання // Наукові вісті НТУУ "КПІ". – 2007. – № 6(56). – С. 37-48.
6. Федорук П. И. //Использование адаптивных и интеллектуальных технологий в системах
дистанционного обучения УСиМ, № 5 - 2006.
7. Brusilovsky, P. and Millan, E. (2007) User models for adaptive hypermedia and adaptive educational systems. In: P. Brusilovsky, A. Kobsa and W. Neidl (eds.): The Adaptive Web: Methods and Strategies of Web Personalization. Lecture Notes in Computer Science, Vol. 4321, Berlin Heidelberg New York: Springer-Verlag, pp. 3-53.
8. Brusilovsky, P. and Henze, N. (2007) Open corpus adaptive educational hypermedia. In: P. Brusilovsky, A. Kobsa and W. Neidl (eds.): The Adaptive Web: Methods and Strategies of Web Personalization. Lecture Notes in Computer Science, Vol. 4321, Berlin Heidelberg New York: Springer-Verlag, pp. 671-696.
9. Conlan, O., O'Keeffe, I., Tallon, S.: Combining adaptive hypermedia techniques and ontology reasoning to produce dynamic personalized news services. In: Wade, V., Ashman, H., Smyth, B. (eds.) Proc. of 4th International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems (AH'2006). Lecture Notes in Computer Science, Vol. 4018. Springer Verlag (2006) 81- 90
10. Brusilovsky, P. and Cooper, D. W.(2002) Domain, Task, and User Models for an Adaptive Hypermedia Performance Support System. In: Gil, Y. and Leake, D. B. (eds.) Proc. of 2002 International Conference on Intelligent User Interfaces, San Francisco, CA, ACM Press 23-30.
11.Vassileva, J., A task-centered approach for user modeling in a hypermedia office documentation system, User Modeling and User-Adapted Interaction, 6 (2-3)/1996
12. Brusilovsky, P., Karagiannidis, C., and Sampson, D. (2004) Layered evaluation of adaptive learning systems. International Journal of Continuing Engineering Education and Lifelong Learning 14 (4/5), 402 - 421.
While writing the given abstract the master's work has not been completed yet. The work completed is December, 2011. The text of master's work and materials on this topic can be received from the author or her research guide after the indicated date.
