An adaptive HMM based approach for improving e-Learning methods

The evolution of web based interaction and information processing has provided an important platform to conduct e-learning activities. However, most of the current e-learning platforms provide static content without considering learning requirements of all its users. These users may have varying Visual, Auditory and Kinesthetic (VAK) oriented learning curves based on their mental abilities and these individual curves may also change during the course of education. Maladaptive e-Learning systems cannot impart quality content for each student as the users observe the information based on their exclusive learning traits. To address this problem and to enhance the e-learning experience, adaptive methods to impart e-learning contents are of prime interest. This research presents a novel approach to design an e-learning platform with adaptive content delivery. The model proposed in this research is based on clustering of students using K-means algorithm and the course of content delivery is adaptively characterized for each student using Hidden Markov Models. Both techniques are used to devise an adaptive algorithm which efficiently manages the clustering of students based on their VAK aptitudes and predicts the future e-learning framework for these students. This adaptive algorithm can thus be applied to any e-learning platform for optimal content delivery to its users in real-time.