Transcript Adaptive Web-Based Leveling Courses

Adaptive Web-Based Leveling
Courses
Shunichi Toida, Chris Wild, M. Zubair
Li Li, Chunxiang Xu
Computer Science Department
Old Dominion University
Outline
Motivation and background
Objectives
System Overview
functional requirements
implementation
Status
Course structure Jtree
Artificial intelligence in discrete math
Student/peer awareness
Future Work
Conclusions
Needs
Non-traditional Student
Second Career
Transfer
Second Major
Non-traditional Delivery
At Work/Home - Anywhere
Evenings?weekends – Anytime
Less expensive
Technology
Inexpensive/Ubiquitous Multi-media PCs
Improving Communications (internet)
Effective Utilization will require
Learning models
Methods of organization and delivery
Motivational mechanisms
Background
ODU CS Dept TechEd initiative
BS degree for AA graduates
Target non-traditional students
Web-centric delivery of course material
Background
ODU CS Dept TechEd initiative
BS degree for AA graduates
Target non-traditional students
Web-centric delivery of course material
Problem: Diverse backgrounds of entering
students
Background
ODU CS Dept TechEd initiative
BS degree for AA graduates
Target non-traditional students
Web-centric delivery of course material
Problem: Diverse backgrounds of entering
students
Solution: Leveling courses in discrete math
and programming
Objectives
To develop courses that are
adaptive
web based
leveling
supported by AI technologies
managed
System Overview
Use Case Summary
Adaptive Tutoring System
Create Course
Description
Regiser and Set
Profile
Create Course
Content
Browse
Course
Analyze and
Categorize Students
Work on Quizzes
and Tests
Instructor
Student
Update Students
Dynamic Profile
View Progress
Functional Requirements
Students
Navigate the course based on his profile and
progress
Get status on his/her progress and his relative
performance
Immediate feedback where possible
Instructor
Specify courses structure
Classify course contents
Monitor students performance
Trouble Alerts
Architectural Features
Course description including prerequisite structure (Oracle)
IEEE Learning Objects Metadata Standard
Student profile and progress (Oracle)
Browsing support for course structure
using applet
Content access based on student
progress
Student Interface
Navigation
Applet
Evaluation
Applet
Instructor Interface
View Progress
Applet
Course
Description
Applet
Analyze Profile
Applet
Student
Evaluate
Applet
First Tier
Web Browser
Internet
HTTP Server/
Request Handler
Instructor Servlet
Student Servlet
Course navigator
and Pre-requisite
Enforcer Module
Students
Registration
and Static Profile
Module
Course Description
Module
Content Creation
Module
Second
Tier
Students Progress
Module
Assignment, Quiz,
and Test Module
Analyze Students
Profile
Course Description and
Students Profile Interface
AI Interface
AI
System
Content
Repository
Evaluation
Module
Content Interface
Course
Description and
Students Profile
Third
Tier
Status
Query-based content selection
Student/Peer Awareness
Problem: motivating in a self-paced
course
Show progress relative to peers
Show current class averages in
assessment material
Artificial Intelligence in Discrete Math
Theorem prover and symbolic
computation are used for exercises on:
English to logic translation
Checking inferences
Checking induction proofs
Proving Equivalences of Natural
Language to Logic
Translate the following sentence into
predicate calculus using “likes(x,y)” predicate
“Nobody likes JOHN”
There are multiple correct answers
Proving Equivalences of Natural
Language to Logic
Translate the following sentence into
predicate calculus using “likes(x,y)”
predicate
“Nobody likes JOHN”
x(likes( x, JOHN ))
x(likes( x, JOHN ))
Handling Multiple Solutions
Restrict response to unique canonical
form
Compare student response to “all”
correct/obvious answers
Prove equivalence of student response
to any correct answer
Handling Multiple Solutions
Restrict response to unique canonical
form
Compare student response to “all”
correct/obvious answers
Prove equivalence of student response
to any correct answer
TPS: Theorem Proving System
Induction Proofs
Built on the MAPLE symbolic
computation system of MATLAB
Example
1+2+… + n = n(n+1)/2
Example of Jtree/and some content
On-going and Future Work
Continue development of course
materials (adaptability, exercises)
Integrate pieces
Define evaluation metrics (market,
effectiveness)
Run assessment
Conclusions
Need to serve non-traditional students
Need to adapt to diverse backgrounds
Need learning environment
architectures and technologies
Need effective learning strategies which
leverage the potential of web
connectivity
End of Presentation
Student Profile
<?xml version="1.0"?>
<!DOCTYPE STUDENT PROFILE "profile.dtd">
<course title="cs381 course" student=”John Smith”>
<block title="Propositional Logic" status="U">
<block title="Proposition" status="U">
<lesson title="What Is Proposition" href="course=cs381,block=cs381-1block1.2,lesson=cs381-lesson01">
</lesson> </block>
</block>
</course>
Course Navigation
Java applet navigation of high level
course structure
Access controlled by student profile
Course Development
XML Course Mark-up Language
Customized for course structure
e.g. course, block, lesson (marks)
Web-based Development Tools
Servlet (Tomcat)
Java Server Page (Tomcat)
Java
Content
Repository
Servlet
Information Flow
1. send a request to oracle in order to get the prerequisite
information of this lesson
2. get the prerequisite information from oracle
3. send a request to oracle in order to get the student
status information based on prerequisite.
4. get the student information and check the status
The student who satisfies the prerequisite.
5. send a request to oracle to get the real source
location.
6. get the location
7. display the content on the web
HTTP Server
with
TomCat Servlet
Engine
Request
Handler and
Pre-requisite
Enforcer
Oracle
Interface
Oracle
Server
Internet
The student who does not satisfy the prerequisite.
5. display the prerequisite that he does not satisfies and
tell him to study such content
Web Browser