Download as pdf or txt
Download as pdf or txt
You are on page 1of 9

RBR for Error-Tolerant Classification by Stochastic

Gradient Descent

A PROJECT REPORT

Submitted by

M.A.Ajith Sriram (910617205008)


S.Ananda Mayan(910617205009)
R.Kabilan (910617205024)
J.NandhaKumar(910617205036)

In partial fulfillment for the award of the


degreeOf
BACHELOR OF TECHNOLOGY
IN
INFORMATION TECHNOLOGY

K.L.N.COLLEGE OF ENGINEERING
POTTAPALYAM-630612

(An Autonomous Institution Affiliated to Anna University, Chennai)

MARCH 2021
ANNA UNIVERSITY: CHENNAI 600 025

BONAFIDE CERTIFICATE

Certified that this project report “RBR for Error-Tolerant Classificationby

Stochastic GradientDescent” is the bonafide work of “Mr. M.A.Ajith Sriram


(Reg.No:910617205008), Mr.S. Ananda Mayan (Reg.No: 910617205009) Mr.R.Kabilan
(Reg.No: 910617205024), Mr. J. Nandha Kumar (Reg.No: 910617205036)” who carried
out the project work under my supervision.

SIGNATURE SIGNATURE

Dr. R. ALAGESWARAN, M.E., Ph.D., Dr. J.S. KANCHANA, M.E.,Ph.D.,


HEAD OF THE DEPARTMENT ASSOCIATE PROFESSOR
SUPERVISOR

INFORMATION TECHNOLOGY INFORMATION TECHNOLOGY

K.L.N. COLLEGE OF ENGINEERING K.L.N. COLLEGE OF ENGINEERING

POTTAPALAYAM, POTTAPALAYAM,
SIVAGANGAI DISTRICT 630612 SIVAGANGAI DISTRICT 63061

Submitted for the Practical Examination held on ______________

Internal Examiner External Examiner


Acknowledgement

Any work would be unfulfilled without a word of thanks. We hereby take


pleasure in acknowledging the persons who guided me throughout our work.

First and foremost, thanks are to the omnipotent for providing us with his
abundant blessings all throughout. We all extend our heartfelt thanks to
Er.K.N.K.KARTHIK, B.E., President of our college and Dr.
A.V.RAMPRASAD, M.E., Ph.D., Principal for provisioning us with the all
required.

We esteem our self to articulate our sincere thanks to Dr.R.ALAGESWARAN,


M.E., Ph.D., Head of the Information Technology for leading us towards the
zenith of success.

We express our grateful thanks to our Project Guide .Dr.J.S.KANCHANA,


M.E.,Ph.D., and Project Coordinator Dr.J.S.KANCHANA, M.E., Ph.D for
their invaluable guidance and motivation. Their assistance and advices had been
very helpful throughout our project. I would like to thank all teaching and non-
teaching staffs of our department who have been the sources of encouragement
and ideas. I thank them for lending their support whenever needed.
ABSTRACT

Machine learning (ML) has been proven successful and helpful in


many areas of modern life, such a speech recognition, Medical
diagnosis and Business. An important task for machine learning is
classification. During classification, to provide the error tolerant,
Result based Re-computation (RBR) method is used. Stochastic
Gradient Descent (SGD)is widely used in Machine Learning (ML) to
perform classification. Stochastic gradient descent calculates the
derivative from each training data instance and update value. RBR is
based on the observation that the SGD result to detect the terms that
can modify the classification result and only these terms must be re-
computed. The proposed RBR reduces the re-computation needed to
protect an SGD against errors. The proposed RBR algorithm
outperforms in terms of Error Tolerance and low computational
demands when compared with other classification algorithms,.
TABLE OF CONTENTS

Chapter No Title Page No

ABSTRACT i

LIST OF SYMBOLS v

LIST OF FIGURES vi

1 INTRODUCTION 1

1.1 Introduction 2

1.2 Problem Statement 3

1.3 Project Objective 3

1.4 Scope of the Project 4

1.4.1 Existing System 4

1.4.2 Proposed System 4

1.5 Software Life Cycle Models 5

1.5.1 Types 6

1.5.2 Incremental Model 6

1.5.3 Reason for choosing the model 7

1.6 Project Plan 8

1.7 Summary 8

2 LITERATURE REVIEW 9

2.1 Introduction 10

2.2 Literature Review 10

2.3 Summary 12
3 SYSTEM ANALYSIS 13
3.1 Requirement Analysis 14
3.1.1 Functional Requirements 14
3.1.2 Non Functional Requirements 14
3.1.3 Hardware Requirements 15
3.1.4 Software Requirements 15
3.1.5 Module Specification 16
3.1.5.1 Data Extraction
3.1.5.2 SGD Classification
3.1.5.3 RBR Computing
3.1.5.4 Performance Comparision
4 SYSTEM DESIGN 19
4.1 Data Flow Diagram 20
5 IMPLEMENTATION 27
5.1 Software Implementation 28
6 TESTING 33

6.2 Software Testing 34

6.3 Basic Types of Testing 34

6.4 Testing Techniques 35

7 SCREENSHOTS 38

8 8 CONCLUSION 43

8.1 Conclusion 43

8.2 Future Enhancement 43

9 APPENDIX 45

10 REFERENCES 51
LIST OF FIGURES

FIGURE NO FIGURE NAME PAGE NO

SCHEMATIC ILLUSTRATION
1.5.2 6
OF INCREMENTAL MODEL

4.1 DATA – FLOW DIAGRAM 15

7.1 MODULES 30

7.2 DATA EXTRACTION 30

7.2.1 ATTRIBUTE DETAILS 31

7.3 SGD CLASSIFICATION 31

7.4 RBR (BEFORE COMPUTE) 32

7.4.1 RBR (AFTER COMPUTE) 32

7.5 PERFORMANCE ANALYSIS 33

7.5.1 ACCURACY COMPARISION 33


LIST OF SYMBOLS

S.NO SYMBOL NAME SYMBOLS

1 USE CASE

2 ACTOR

3 CONTROL FLOW

4 DECISION

5 START

6 STOP
1

You might also like