Intelligent Multi State Markov Assumption Model for Discovering Cognitive Learning Traits in E-Learning System

Abstract

In the e-learning arena, the felicitators and learners are struggling to acclimatize themselves into the learning management system in correspondence to their teaching and learning styles. This paper is prepared to put forward a probabilistic and statistical approach which can enable the creation of a model to reveal the forthcoming of numerous learning techniques for the learners and to endow with the requisite learning methodology according to the learners quench and learning capability. We, in this paper have envisaged the Kolb Learning taxonomy for building the prediction model (LSM-Latent Learning Style Markov Model) using multi-stage markov assumption model. The LSM Multi-stage markov model puts forth numerous strategies of learning technique and its migration from one technique to the other during the advancement of the learning strategy. The evaluation of this model is analyzed with niche outcome and the manifestations are also analyzed with the requisite charts and plots. New learning methodologies are encapsulated taking into review various key facts and findings as the composites of cognitive, effective, and psychological stable metrics that the learners are capable of in the adaptive learning management system during the navigation process in their learning path in the corresponding mode. The progress of the methodology is made viable for the learners by providing the curriculum and its technique that fit the learning methodology. The challenging aspect of such adaptive methodology is the derivation of the capability of the learner's modeling technique. The learning methodology is identified with the help of cognitive traits of the learners. We develop a multi-stage learning module for formatting the dynamics of learning methodology based on the learner's activity log data analysis.