Comparison of rough-set and statistical methods in inductive learning
International Journal of Man-Machine Studies
Communications of the ACM
Teaching CS1 on-line: the good, the bad, and the ugly
SIGCSE '99 The proceedings of the thirtieth SIGCSE technical symposium on Computer science education
Between Tanzania and Finland: learning Java over the Web
SIGCSE '99 The proceedings of the thirtieth SIGCSE technical symposium on Computer science education
Information Sciences: an International Journal
Induction By Attribute Elimination
IEEE Transactions on Knowledge and Data Engineering
Discovery of Rules about Compilations - A Rough Set Approach in Medical Knowledge Discovery
RSFDGrC '99 Proceedings of the 7th International Workshop on New Directions in Rough Sets, Data Mining, and Granular-Soft Computing
The Application of a Distance Learning Algorithm in Web-Based Course Delivery
RSCTC '00 Revised Papers from the Second International Conference on Rough Sets and Current Trends in Computing
Supporting E-Learning System with Modified Bayesian Rough Set Model
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Design E-learning Recommendation System Using PIRT and VPRS Model
WISM '09 Proceedings of the International Conference on Web Information Systems and Mining
Hi-index | 0.00 |
WebCT is a web-based instruction tool that enables instructors to create and customize their courses for distance post-secondary education. Students do assignments, quizzes, and a final examination on the World Wide Web (WWW). If a student fails the final examination, then the student needs to study the course material again. Questions that arise are "in what areas is the student weak" and "where should the student focus his/her efforts to obtain the necessary background for the next module/section." If the answers to these questions can be found automatically based on the performance of previous students, then students will be able to focus their study and the instructor will be able to reorganize the course material. In this paper, we discuss how to use Rough Sets and Rough Set based Inductive Learning to assist students and instructors with WebCT learning. The scores of quizzes are treated as conditional attributes and the final examination score as a decision attribute. Decision rules are obtained using Rough Set based Inductive Learning to give the reasons for student failure. For repeating students, these rules specify which sections need to be emphasized for the second round. For new students, these rules inform them about those sections requiring extra effort in order to pass the final examination. Hence, Rough Set Based WebCT Learning improves the state-of-the-art of Web learning by providing virtual student/teacher feedback and making the WebCT system much more powerful.