EVALUATION OF FUZZY COMPUTING AS A TECHNIQUE TO PROVIDE LEARNING OBJECTS ADAPTABILITY IN AN M-LEARNING ARCHITECTURE
Universidade de São Paulo (BRAZIL)
About this paper:
Appears in: EDULEARN10 Proceedings
Publication year: 2010
Conference name: 2nd International Conference on Education and New Learning Technologies
Dates: 5-7 July, 2010
Location: Barcelona, Spain
Abstract:M-learning is a new education’s paradigm which encompasses the use of mobile technologies with some data processing capacity as cellular phones, PDAs, notebooks, and wireless Internet access enabling students to access learning materials for your courses anywhere, anytime, even while in movement.
The learning materials may be in the form of learning objects in several formats and media that include content and evaluation activities.
These learning objects can be selected considering several elements of adaptation, such as the characteristics of the mobile device; the learning styles; the students performance; the knowledge acquired by students and the content associated with a course. Considering these elements, it was proposed an adaptive M-learning architecture which also considers the teacher's and student's preferences concerning a learning object, and the student interaction both with the mobile device and the learning object as well.
Aiming to provide adaptation, the architecture has been elaborated in modules: some modules on the server, a module responsible for the management of learning objects and three modules for the mobile device.
The search space of the best learning object to be presented to the student is multidimensional in which some dimensions provide only qualitative preference indications.
Fuzzy computing is a Computational Intelligence technique that uses imprecise linguistic statements to perform the computation. In this sense, fuzzy systems use the fuzzy sets theory to treat and represent the inaccuracy or uncertainty expressed in natural or symbolic language.
This work presents the adaptive M-learning architecture and its modules, and makes an assessment of the Fuzzy Computing technique to be used in the server module to implement adaptability, therefore providing the selection of the best learning object.
Keywords: m-learning, fuzzy cumputing, learning objects, adaptation, learning styles, students performance, m-learning architecture, soft computing.