An enhanced Rough Set Based Technique for Elucidating Learning styles in E-Learning System

Rough set theory is considered as the most essential strategy significantly suitable for illustrating distinctive sorts of learning styles controlled by the learners during e-learning process through feature information selection. The Rough set hypothesis is likewise utilized for effectively finding relations with conflicting or fragmented information which is incomplete in nature. Be that as it may, when harsh set hypothesis is consolidated, they are not sufficiently effective to evaluate ideal subsets. Hence, this paper provides a comparison of various rough set based techniques for adapting learning styles. The paper provides the analysis of rough set based clustering methods in terms of two parameters cohesion and coupling. In addition, the paper also proposes an enhanced methodology based on normalized score value for finding the deviation between data’s through the equivalence property of rough set theory. The experimental results show that the proposed algorithm maximizes the stated metrics.