Fuzzy Logic Based self-switching multi-strategic pedagogical agent

Abstract

The Self-Switching Multi-Strategic Pedagogical Agent is designed following the Autonomic Computing and the Component-Based Agents approaches. It is comprised of two sub-components: Manager (MrSS) and Managed (MdSS) Sub-Systems. These sub-systems are built independently, but they constantly interact with one another. The Multiple Pedagogical Strategies (MPSs) that are used by the system are implemented by MdSS. While the Switching Logic (SL), that is used to (re)conFigure the MdSS, is implemented by the MrSS as an Autonomic Control Loop (ACL). The MPSs and the SL permit to trigger the appropriate PS regarding the crisp values of the Student Knowledge Level (SKL). However, the SKL is characterized by a high degree of uncertainty. To overcome this deficiency, we integrate fuzzy control in the MrSS to handle the uncertainty and consequently improve the strategy selection process. Fuzzy MrSS links the different context parameters and SKL through fuzzy rules taking into account the system’s fuzziness and uncertainties. We will present experiments carried with the Math sub-domain.