adaptive e - learning website

34
Adaptive e-Learning Web Site Created by: Abhinav Singh 10103500 Faizan Akhtar 10103597 Priyam Awasthy Submitted to: Mr. Kishore Kumar Ms. Arti Jain Supervisor: Ms. Mukta Goel

Upload: faizanakhtar315

Post on 20-Dec-2014

73 views

Category:

Education


0 download

DESCRIPTION

The project is an Artificially Intelligent e-learning web site using Fuzzy Logic to teach students C. The system will be a website that will be exclusive for each student according to his/her intellect. The site will provide reserves of theory and quizzing material (in a way not present on www yet) based on fuzzy logic and AI. Hence our system will change its preferences as the intellect of the student grows. The student is provided with Initial Mental ability Test to get the initial level of understanding of the student which is further improvised using Intuitionistic fuzzy algorithm and Mamdani algorithm. The hence defuzzified value will show the range in which the student lies.

TRANSCRIPT

Page 1: 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

Page 2: Adaptive E - Learning Website

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.

Page 3: Adaptive E - Learning Website

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.

Page 4: Adaptive E - Learning Website

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."

Page 5: Adaptive E - Learning Website

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

Page 6: Adaptive E - Learning Website

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

Page 7: Adaptive E - Learning Website

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

Page 8: Adaptive E - Learning Website

ALGORITHMS

Page 9: Adaptive E - Learning Website

Intuitionistic Fuzzy

X: set of questions.

Ta: degree of true.

Fa: degree of false.

Page 10: Adaptive E - Learning Website

Intuitionistic Fuzzy

S(a) : Score function

Ci: percentage of true.

Wi: percentage of false.

Ti: Ci/100

Fi: Wi/100

Page 11: Adaptive E - Learning Website

Intuitionistic Fuzzy

Intuitionistic Fuzzy Weighted Averaging (IFWA):

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

Page 12: Adaptive E - Learning Website

Mamdani Model

Fuzzification of Inputs.

Rules Evaluation

Defuzzification

Page 13: Adaptive E - Learning Website

Mamdani Model

Fuzzification: Process of making Crisp value Fuzzy

Page 14: Adaptive E - Learning Website

Mamdani Model Rules Evaluation:

Page 15: Adaptive E - Learning Website

Mamdani Model

Defuzzification: Weightage Average Model

Page 16: Adaptive E - Learning Website

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

Page 17: Adaptive E - Learning Website

Time and Score Functions

Page 18: Adaptive E - Learning Website

The Good, The Average, The Poor

Page 19: Adaptive E - Learning Website
Page 20: Adaptive E - Learning Website
Page 21: Adaptive E - Learning Website

QuestionData

Sample Questions and their Fuzzy Values

Page 22: Adaptive E - Learning Website

Our Grouping

0-.34 -> POOR

.35-.75 -> AVERAGE

.76-1 -> GOOD

Page 23: Adaptive E - Learning Website

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

Page 24: Adaptive E - Learning Website

A look at The System

Page 25: Adaptive E - Learning Website

A look at The System

Page 26: Adaptive E - Learning Website

Test Report

A look at The System

Page 27: Adaptive E - Learning Website

A look at The System

ProgressReport

Page 28: Adaptive E - Learning Website

A look at The System

ProgressReport

Page 29: Adaptive E - Learning Website

FORUM

A look at The System

Page 30: Adaptive E - Learning Website

PracticeCompiler

A look at The System

Page 31: Adaptive E - Learning Website

THEORY DATA

A look at The System

Page 32: Adaptive E - Learning Website

A look at The System

THEORY DATA

Page 33: Adaptive E - Learning Website

A look at The System

Page 34: Adaptive E - Learning Website

THANK - YOU