An Efficient Adaptive Fuzzy Learning Diagnosis Method for E-Learning

Abstract

Most e-Learning systems are required to establish a flexible content structure and provide suitable learning path, content, or interface by extracting meaningful learning behavior of students for adaptive learning. However, recognizing the students' learning behavior, teaching material, and personal degree are still a challenge that needs to be resolved. In this paper, we propose an efficient fuzzy algorithm using in similarity measurement for selecting suitable content and exams for students, which has been applied to the e-Learning system called Fuzzy Adaptive Learning Diagnosis System (FALDS). The proposed system computes the relationship between exam items and teaching materials depending on the results of practice and then exams to automatically select and marks important paragraphs for the learners. In addition, an efficient system for classifying students into groups so that information for selecting appropriate items for the learners can be provided is proposed. To evaluate the performance, a total of 200 fourth-grade students from six classes participate in the experiment for a school term. The results indicate that by using FALDS to diagnose and assist learning, students in the experimental group outperform those not in the group.