The Standards-based Architecture of the Adaptive Learning Environment aLFanet (original) (raw)

aLFanet (IST-2001-33288) aims to build an adaptive eLearning management system that provides personalised eLearning based on the combination of different types of adaptation (e.g. learning routes, interactions in services, peer-to-peer collaboration, presentation, questionnaires). It integrates new principles and tools in the fields of Learning Design and Artificial Intelligence, following existing standards in the educational field (IMS-LD, IMS-CP, IEEE-LOM, IMS-LIP, IMS-QTI), multi-agents systems (FIPA) and multi-platform communications (SOAP, XML, WebDav). This intensive use of standards makes aLFanet reusable in terms of contents, functionality, pedagogical designs and learners' profiles. On the one hand, this system is designed in a flexible and modular way, which facilitates the integration of third parties developments. On the other hand, despite the static adaptation specified by the course authors at design time, dynamic adaptation is also provided by the system on runtime. To achieve this, aLFanet includes a two level hierarchy of multi-agent architectures that works autonomously to solve the adaptation tasks required. It implements a hybrid approach to build the models needed for the adaptation tasks. This approach combines knowledge-based methods and machine learning techniques in a multi-agent architecture.