Adaptive e-learning system based on learning style and ant colony optimization

Many e-learning systems don't consider learners' individual difference. However, learners have different needs and characteristics such as previous knowledge, motivation, and learning styles. Providing courses which fit learners' individual characteristics makes learning easier for them as well as increasing their learning progress. In this paper, we will benefit from Felder-Silverman learning style model to classify the learner's learning style. Our system will be able to provide to learners a learning content that fit their preferences. This approach will be base on ontologies with artificial agents. In order to expand the functionality of our system we will use one of the most recent techniques for approximate optimization in e-learning Ant colony optimization (ACO). It will help learners to find an adaptive learning object more effectively in order to have an optimal learning path. The solution will provide an adaptive and personalized learning path which will give flexibility and adaptability to our system.