Knowledge mobilizationarchitectures, models and applications

Zusammenfassung

Mobile network technologies are representative of a paradigm shift from classical desktop applications to highly-distributed nomadic systems, Mobile technologies make it possible to deliver information anywhere at anytime, and provide nomadic users with up-to-date information ready for decision-making processes. Nevertheless, the management of structured information (i.e. knowledge) for delivery to mobile users poses several challenges. Besides the limited computational capabilities of mobile devices, mobile systems face specific problems that cannot be solved by traditional knowledge management methodologies and tools, and thus require creative new solutions. Knowledge Mobilization is an innovative approach that integrates contributions from several areas such as Knowledge Engineering, Distributed Artificial Intelligence, Soft Computing, and the Semantic Web, to develop effective knowledge-intensive mobile applications. In this doctoral thesis we explore possible computational solutions for problems of knowledge distribution and information overload in Knowledge Mobilization systems. More precisely, we describe a new architecture for Knowledge Mobilization systems (based on the multi-agent paradigm) and an innovative context-aware knowledge representation model (which relies on Description Logics ontologies). Both elements provide support for effectively delivering knowledge obtained from large, heterogeneous information sources to nomadic users. The architecture and knowledge representation model were used to design and implement a Knowledge Mobilization system in the domain of Healthcare. The system creates and distributes to nomadic doctors summaries of the clinical histories of their patients. The prototype thus implemented achieves the level of adequacy necessary to meet Knowledge Mobilization requirements.