A Method for Predicting Understanding of Course Knowledge based on Junction Tree

DOI

10.2991/msetasse-15.2015.208How to use a DOI?

Keywords

course inference model; knowledge points; prior knowledge; junction tree

Abstract

For the same course, different application fields have different requirements for course content, and their course syllabuses cover knowledge points all. Select some knowledge points from course syllabus to create interrelationship among them based on knowledge structure, and generate conditional probability tables according to prior knowledge of course teaching experts so that the Bayesian network of course knowledge points can be created to show field knowledge coverage and knowledge inference among these nodes existing in the Bayesian network. In order to update nodes by message passing conveniently, a Bayesian network need to be transformed into a junction tree, which can be trained by historical course data recorded by course teachers, to improve accuracy of inference for subsequent knowledge learning effect based on learned knowledge points.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lijin Long
AU  - Huyi Liang
PY  - 2015/11
DA  - 2015/11
TI  - A Method for Predicting Understanding of Course Knowledge based on Junction Tree
BT  - Proceedings of the 2015 3rd International Conference on Management Science, Education Technology, Arts, Social Science and Economics
PB  - Atlantis Press
SP  - 961
EP  - 966
SN  - 2352-5398
UR  - https://doi.org/10.2991/msetasse-15.2015.208
DO  - 10.2991/msetasse-15.2015.208
ID  - Long2015/11
ER  -