An agent-based e-learning assessing and instructing system

The research work on e-learning has become very important field in the education. Many demands for instructing strategies in the adaptive learning have turn out. Base on these instructing strategies, the learners could reduce their blindness in the learning process. This paper proposes a method to build a Bayesian networks model in order to assess the learner's knowledge level and instruct the learner. This e-learning assessing and instructing system is designed and implemented based on multi-agent systems (ELAIS). In this system, the knowledge cognitive level, the learning priorities and weakness of a learner could be analyzed and assessed through the tracking information. Then the corresponding instruction will give to the learner in order to improve the learner's learning efficiency. The parameters assessment is achieved using EM algorithm and the assessment results in this system reveal the pretty accuracy to the real testing situation.