Document Type : Original Research Paper


Computer Science, Sistan and Baluchestan University, Iran


: 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.


Main Subjects

[1] Beatty, B. Ulasewicz, C. Online teaching and learning in transition: Faculty perspectives on moving from blackboard to the Moodle learning management system. TechTrends, 50(4). 2009. pp.36–45. [2] D'Mello, C. and Graessner, A. Dynamics of affective states during complex learning. Learning and Instruction, 22(2). 2012. pp.145–157. [3] Koedinger, K. and Aleven, V. Exploring the assistance dilemma in experiments with cognitive tutors. Educational Psychology Review, 19. 2007. pp.239–264. [4] Ford, L. A New Intelligent Tutoring System. British Journal of Educational Technology, 39(2). 2008. pp.311-318. [5] Banadkuki, H. Investigation of An Expert Model For Tutoring Heuristic Search Methods, M.Sc. Desert Of Computer Science, University of Sistan and Baluchestan, 2012. ]In Persian[ [6] Myung, I.J. Tutorial on maximum likelihood estimation. Journal of Mathematical Psychology, 47. 2009. pp.90–100. [7] Durkin, J. Expert Systems: Catalog of Applications. Intelligent Computer Systems. 2011. [8] Dymova, L., Sevastianov, P. and Kaczmarek, K. A stock trading expert system based on the rule-base evidential reasoning using Level 2 Quotes. Expert Systems with Applications, Volume 39, Issue 8. 2012. pp.7150-7157. [9] Vanlehn, K., Lynch, C., Schulze, K., Shapiro, J. A., Shelby, R. H., Taylor, L., Treacy, D. J., Weinstein, A., and Wintersgill, M. C. The Andes physics tutoring system: Five years of evaluations. Proceedings of the Artificial Intelligence in Education Conference. 2005. [10] Cruz-Ramireza, N., Acosta-Mesa, H.G., Carrillo-Calvet, H., Nava-FernJndez, A. and Barrientos-Martinez, R.E. Diagnosis of Breast Cancer Using BayesianNetworks: Acase Study .ELSEVIER. 2007. [11] Estevam R., Hruschka, Jr and Ebecken, N.F. Towards Efficient Variables Ordering for Bayesian Networks Classifier. ELSEVIER. 2007. [12] Munetomo, M., Nurao, N. and Akama, K. Introducing Assignment Functions to Bayesian Optimization Algorithms. ELSEVIER. 2012. [13] de Rigo, D., Castelletti, A., Rizzoli, A.E., Soncini-Sessa, R. and Weber, E. A selective improvement technique for fastening Neuro-Dynamic Programming in Water Resources Network Management. Proceedings of the 16th IFAC World Congress - IFAC-PapersOnLine. 16th IFAC World Congress. 2008. [14] Arroyo, I., Woolf, B. Inferring learning and attitudes from a Bayesian network of log file data. In Proceedings AIED 05, 12th international conference on Artificial intelligence in education. 2005. [15] Wu, J., Chen, E. A Novel Nonparametric Regression Ensemble for Rainfall Forecasting Using Particle Swarm Optimization Technique Coupled with Artificial Neural Network. 6th International Symposium on Neural Network. Springer. 2009.