Student classification in adaptive hypermedia learning system using neural network
Conventional hypermedia learning system can pose disorientation and lost in hyperspace problem that will cause learning objectives hard to achieve. Adaptive hypermedia learning system is the solution to overcome this problem by personalizing the learning module presented to the student based on the...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://repo.uum.edu.my/13888/1/KM159.pdf http://repo.uum.edu.my/13888/ http://www.kmice.cms.net.my |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Utara Malaysia |
| Language: | English |
| Summary: | Conventional hypermedia learning system can pose
disorientation and lost in hyperspace problem that will cause learning objectives hard to achieve. Adaptive hypermedia learning system is the solution to overcome this problem by personalizing the learning module presented to the student based on the student knowledge acquisition.This research aims to use neural network to classify the student whether he is advanced, intermediate and beginner student.The classification process is
important in adaptive hypermedia learning system in order to provide suitable learning module to each individual student by taking consideration of the studentsí knowledge level, his learning style and his performance as he learn through the system. Data about the student will be collected using implicit and explicit extraction technique.
Implicit extraction technique gathers and analyses the studentís behavior captured in the server log while they navigate through the system. Explicit extraction technique on the other hand collects studentís basic information from user registration data. Three classifiers were identified in
determining the studentís category.The first classifier determines the student initial status based on data collected from explicit data extraction technique.The second classifier identifies studentís status from implicit
data extraction technique by monitoring his behavior while using the system.The third classifier, meanwhile will be executed if the student has finished studying and finished
doing the exercises provided in the system. Further, the data collected using both techniques will be integrated to form a user profile that will be used for classification using simple back propagation neural network. |
|---|