Designing the input/output membership function is the first major step in the three steps processes of a fuzzy logic controller. The process involves determining the most suitable fuzzy logic algorithm capable of transforming the crisp data entering the fuzzy controller and assigning appropriate fuzzy terms and their corresponding degree of membership in the categories. The shape of a membership function graph can take various representations such as trapezoidal, triangular, bell curves, singleton or any form that accurately enables the distribution of information within the system, in as much as the shape provides a region of transition between adjacent membership functions. The main goal of this paper is to propose the design of fuzzy membership functions that represent the distribution and prediction of student’s knowledge performance in an Intelligent Tutoring System (ITS).
展开▼