Fuzzy Logic for Modeling the Knowledge of Users in PARSAT AR Software

This chapter of the book centers on the application of fuzzy logic for modeling students’ knowledge, with a primary focus on enhancing spatial ability training through personalized and adaptive learning experiences. The chapter begins with an overview, emphasizing the utility of fuzzy logic in capturing and adapting to students’ knowledge levels. It underscores the significance of tailoring learning activities to individual students’ needs. The core components of the fuzzy logic algorithm are elaborated upon in detail. This includes an explanation of how fuzzy logic handles imprecise and uncertain knowledge through linguistic variables and fuzzy sets. The initialization process is discussed, outlining how the model is set up to capture students’ knowledge levels at the outset of training, underscoring the importance of accurate initialization for effective adaptation of learning activities. The concept of fuzzy sets and their role in representing linguistic variables is explored, shedding light on how they measure the degree of membership or fuzzy truth values associated with various knowledge levels. The construction of the fuzzy rule base is explained, detailing how rules are defined to link linguistic variables and their corresponding fuzzy sets to appropriate learning activities, emphasizing the rule-based decision-making nature of fuzzy logic. Mamdani’s inference system, a crucial component of the fuzzy logic model, is examined in terms of how it combines fuzzy rules to determine adaptive learning activities based on students’ knowledge levels. The process of defuzzification is described, highlighting its role in converting fuzzy outputs into actionable decisions. The chapter concludes by illustrating how fuzzy weights obtained through the fuzzy logic model are employed for real-time adaptation of learning activities, influencing the selection and customization of learning materials.