OPAESFH: Ontology-based personalized adaptive e-learning system using FPN and HMM

Abstract

Nowadays, often it is found that the developed elearning systems for Web 2.0 are based on the one-size-fits-all content delivery approach whereas we require personalized, adaptive, upgraded e-learning content delivery approach for evolving Web 3.0. Therefore, we require studying few aspects example adaptive learning style, background knowledge, student ability and knowledge level, Learning Path Sequence (LPS), and personalization for improving e-learning system. In this paper, we have proposed an Ontology-based Personalized Adaptive E-learning system using FPN and HMM (OPAESFH). Ontologies are machine-readable and used to provide semantics to e-learning course content for sharing and reusing. The course content store in ontology given appropriate LPS using the FPN and HMM algorithm is to tackle the problem of procedural learning by making it adaptive. OPAESFH use Petri Net for modeling e-learning course content and HMM algorithm for adaptability of course content according to the learner's performance in pre-test/post-test. This LPS adjusts itself according to the learner's performance in pre-test/post-test for the e-learning course content. The proposed e-learning system demonstrates that the personalized and adaptive LPS can enhance a learning experience. We evaluate OPAESFH with respect to an experimental and control group and the results that are obtained from the experimental group are better than the results from the control group.