Intelligent System E-Learning Modeling According to Learning Styles and Level of Ability of Students

Abstract

Presenting learning materials that suited to learners is very important in e-learning. This is due to e-learning now provides the same learning materials for all learners. This study built intelligent system models that can detect learning styles and ability levels of learners. Categorizing and identifying styles are important to map abilities in accordance to provide learning material that matches preferences of the learners. There are many methods used to detect characteristics of learners this research used Felder Silverman Learning Style Model (FSLSM) which proven to be suitable for application in an e-learning environment. In addition to learning style, other elements that are required is to determine the level of abilities. The level of abilities is categorized into three categories known as Beginner, Intermediate, and Advanced which will be determined through an evaluation with Rasch Model (Model Rasch). To determine the suitability of learning materials with learning styles and ability level used artificial intelligence techniques that are rule-based. This research produces adaptive e-learning model that can present learning materials in accordance with learning style and ability level, to be able to improve the ability of learners.