Document Type : Original Research Paper

Authors

• H. Banadkouki
• K. Abbasi
• A. Rahati

Computer Science, Sistan and Baluchestan University, Iran

Abstract

: E-learning, by eliminating the limitation of space and time to attend in classes, has found a widespread use in communication between students and teachers. On the other hand, intelligence components, such as providing feedback and hint for students will increase the quality of education. But current methods for implementation of intelligent have high costs. This paper introduces a new method to provide intelligent e-learning at a low cost. Intelligence emergences in two components, including knowledge assessment and selection of appropriate hint during the problem solving. In this approach, a Bayesian network utilized to assess student knowledge and an Artificial Neural network utilized to select the appropriate hint. The structure of both networks is determined by training data. The proposed method is implemented and assessed in an e-learning system. The above 90 percent accuracy in both networks and low implementation cost are of the important advantages of the proposed method. The structure of the two networks which is based on training data makes it possible to use it in a variety of systems use e-learning systems with a diverse range of knowledge.

Keywords

• e-Learning
• Intelligent Learning
• Bayesian Networks
• Artificial neural network

20.1001.1.20080441.1394.9.2.2.7

Main Subjects

• Electronic learning- virtual