Abstract:

Adaptive and Intelligent Learning Systems analyze the individual profile of each student to select the learning content appropriate the characteristics and students requirements by use of artificial intelligence theories, considering, for example: previous knowledge, preferences, learning objects, learning styles and cognitive skills.

In these systems, there is the Adaptive Educational Hypermedia Systems (AEHS), oriented systems for the internet, which can generate and provide personalized learning experiences for the student.

Related to this line of research, was proposed the AdaptMLearning Architecture based on AHAM reference model to AEHS Adaptive Systems, composite of: knowledge space, user model, observation and adaptation model, as to logical definition these systems.

The AdaptMLearning Architeture was designed to be a learning infrastructure for mobile and nonmobile platforms, provides a selection of learning objects that takes into account as adaptation criteria the following data: the mobile device's technological specification; the student's learning style information, his/her performance and spent time associated to the student's interaction with the learning object; previously acquired knowledge by the student related to the course's content. In addition, it also allows the teacher to interfere in the adaptation criteria used during the study simulation, and allows the student to indicate his/her preferences for media types.

In the AdaptMLearning Architecture, associated to student's learning styles, was used the Felder-Silverman learning style model (FSLSM). The IEEE 1484 Standard (Learning Object Metadata, LOM) considered for cataloging learning objects and some of its categories and attributes associated with dimensions of learning styles FSLSM model. A simulator for the AdaptMLearning Architecture was developed with algorithms that promote the adaptability and fuzzy logic theory that contains your intelligence to provide the suitable presentation of learning objects to the analyzed criteria. However, this simulator was designed with a manual data input associated to the LOM standard of a learning object, which difficult the real tests with objects containing XML metadata with LOM standard. In this work, the development of a tool to be coupled to the AdaptMLearning simulator that realizes the learning object metadata loading, characterized by LOM XML file, is shown.

Initially, was developed a tool, separated of AdaptMLearning simulator with the objective of realize the input validation of the XML files, associated to learning objects metadata in LOM standard. In modeling, was used Unified Modelling Language (UML) and in development were used XML and Java technologies. Individual tests were made for application validation. To these tests were used learning objects created by University of Girona at Spain for the UML course.
At the moment, this work is in phase of coupling the tool to load learning objects with the AdaptMLearning architecture simulator.

Keywords:

Adaptive and Intelligent Learning Systems, LOM standard, automatic load, Learning Objects.