adaptive e - learning website

Adaptive e-Learning Web Site

Created by:

Abhinav Singh10103500Faizan Akhtar 10103597Priyam Awasthy10103635

Submitted to:

Mr. Kishore KumarMs. Arti Jain

Supervisor:Ms. Mukta Goel

What is Artificial Intelligence??

It is the theory and development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.

Why Adaptive Learning ???

What is it that you expect from a system which offers you the opportunity to learn?

Course Material

MAY BE…But is that all? What is it you are actually looking for?

Something which can guide you along your whole path. Take decisions for you. A system which interacts with you.

BUT most importantly you are looking a system which can understand you, and will change for you.

And that’s why we need an Adaptive System. A Perfect System.

What is Fuzzy logic??

Fuzzy logic is an approach to computing based on "degrees of truth" rather than the usual "true or false" (1 or 0) Boolean logic on which the modern computer is based

Fuzzy logic includes 0 and 1 as extreme cases of truth (or "the state of matters" or "fact") but also includes the various states of truth in between so that, for example, the result of a comparison between two things could be not “cold" or "hot" but ".38 of hotness."

Currently all available teaching systems work on precise evaluation.

Computer can Evaluate and Manipulate Precise values while humans evolution is affected by uncertainty, vagueness & judgments.

Adaptive Learning Systems

Human thinking process Perfect+ = Online

Computer evaluation power Tutor

We propose web based tutoring model which is combination of

Intuitionistic fuzzy set theory + mamdani algorithm

Flow of Control1. IQ TEST

2. CALCULATION SCORE FUNCTION

3. MAMDANI CALCULATIONS

4. CATEGORIZATION OF USER

5. COURSE DISPLAY

6. TOPIC TEST

7. CALCULATION OF SCORE FUNCTION

8. MAMDANI ALGORITHM FOR NEW FUZZY VALUE

ALGORITHMS

Intuitionistic Fuzzy

X: set of questions.

Ta: degree of true.

Fa: degree of false.

Intuitionistic Fuzzy

S(a) : Score function

Ci: percentage of true.

Wi: percentage of false.

Ti: Ci/100

Fi: Wi/100

Intuitionistic Fuzzy

Intuitionistic Fuzzy Weighted Averaging (IFWA):

Every question has specific initial fuzzy value QF, true weight Tw, false weight & Fw.

Mamdani Model

Fuzzification of Inputs.

Rules Evaluation

Defuzzification

Mamdani Model

Fuzzification: Process of making Crisp value Fuzzy

Mamdani Model Rules Evaluation:

Mamdani Model

Defuzzification: Weightage Average Model

MAMDANI STEPSStep 1. Evaluate the antecedent for each ruleCalculate degree for each crisp input

Step 2. Obtain each rule's conclusion

OR = min(d1,d2) AND = max(d1,d2)

Step 3. Aggregate conclusions

In this step we combine the outputs obtained for each rule in step 2 (obtain conclusion) into a single fuzzy set, using a fuzzy aggregation operator.

Step 4. DefuzzificationCaculating centroid

Time and Score Functions

The Good, The Average, The Poor

QuestionData

Sample Questions and their Fuzzy Values

Our Grouping

0-.34 -> POOR

.35-.75 -> AVERAGE

.76-1 -> GOOD

Our Model D

ATA

BA

SE

User Level Analysis

User Progress Analysis

Theory Generation ‘n’ Presentation Curriculum Sequencing Adaptive Navigation Support Adaptive Presentation Problem Solving Support

Main System A.I.

Update D

atabase

FORUM

IQ TEST

Main Test

TEST

Theory

Practice

Report 

User

A look at The System

A look at The System

Test Report

A look at The System

A look at The System

ProgressReport

A look at The System

ProgressReport

FORUM

A look at The System

PracticeCompiler

A look at The System

THEORY DATA

A look at The System

A look at The System

THEORY DATA

A look at The System

THANK - YOU