INTERNET DATA TRAFFIC ANALYSIS

USING TRAPGL-VQ ALGORITHM

A Project Report

Submitted by

PRIYA DHARSHINI.S (1301107)

SHAHANAS.S (1301124)
SOUNTHARYA.S (1301132)

in partial fulfillment for the award of the degree

of

BACHELOR OF ENGINEERING

in

COMPUTER SCIENCE AND ENGINEERING

SRI RAMAKRISHNA ENGINEERING COLLEGE

COIMBATORE - 641 022
APRIL-2017
 SRI RAMAKRISHNA ENGINEERING COLLEGE

BONAFIDE CERTIFICATE

Certified that this project report INTERNET DATA TRAFFIC ANALYSIS

USING TRAPGL-VQ ALGORITHM is the bonafide work of

PRIYA DHARSHINI.S (1301107)

SHAHANAS.A (1301124)
SOUNTHARYA.S (1301132)

who carried out the project work under my supervision.

SIGNATURE SIGNATURE

MR.S.HARIHARA GOPALAN DR.A.GRACE SELVARANI

SUPERVISOR HEAD OF THE DEPARTMENT

Assistant Professor Professor

Department of Computer Science Department of Computer Science
and Engineering and Engineering
Sri Ramakrishna Engineering College, Sri Ramakrishna Engineering College,
Coimbatore. Coimbatore.

Submitted for the University Project VIVA-VOCE held on ________________

INTERNAL EXAMINER EXTERNAL EXAMINER

i
 DECLARATION

We affirm that the project work titled INTERNET DATA TRAFFIC

ANALYSIS USING TRAPGL-VQ ALGORITHM being submitted in
partial fulfillment for the award of Bachelor of Engineering is the
original work carried out by us. It has not formed the part of any other
project work submitted for award of any degree or diploma, either in this
or any other University.

------------------------,------------------------,----------------------
(Signature of the Candidates)

PRIYA DHARSHINI.S (1301107)

SHAHANAS.A (1301124)
SOUNTHARYA.S (1301132)

I certify that the declaration made above by the candidate is true.

--------------------------
------
(Signature of the Guide)
Mr.S.Harihara Gopalan,
Assistant Professor,
Department of CSE
ii
 ACKNOWLEDGEMENT
We would like to express our sense of profound gratitude to
Sri.R.Vijayakumhar, Managing Trustee, Sri.D.Lakshmi Narayanasamy Joint
Managing Trustee, SNR sons Charitable Trust, Coimbatore for providing excellent
facilities to carry out our project.
We thank Dr.A.Ebenezer Jeyakumar, Director (Academic), Sri
Ramakrishna Engineering College, Coimbatore for his great inspiration and
blessings.
We express our deepest gratitude to our Principal Dr.N.R.Alamelu, for her
valuable guidance and blessings.
We are deeply indebted to our Head of the Department, Dr.A.Grace
Selvarani, Professor, Department of Computer Science and Engineering who
modeled us both technically and morally for achieving great success in life.
We express our sincere thanks to our Project Coordinator,
Dr.B.Mathivanan, Associate Professor, Department of Computer Science and
Engineering for his great inspiration.
Words are inadequate to offer thanks to our respected guide. We wish to
express our sincere thanks to Mr.S.Harihara Gopalan, Assistant Professor,
Department of Computer Science and Engineering, who gives his constant
encouragement and support throughout this project work and who makes this
project a successful one.
We also thank all the staff members of our Department and technicians for
their help in making this project successful one.

iii
 ABSTRACT

Network grows in terms of speed and size. The number of internet users
is also increasing. It is necessary to analyze, measure, and classify the internet
traffic and describes the methods of classifying traffic by observing features.
Accurate network traffic classification is elementary to quite a few internet
activities, from security monitoring and from quality of service. Yet
classification schemes are extremely difficult to operate accurately due to the
shortage of available knowledge to the network. Traffic classification is a major
component of automated intrusion detection systems. The extracted features are
used as an input to the machine learning algorithm for traffic classification.
Until now, many methods have been proposed, but studies
show that machine learning based algorithms have a best
performance in comparison to other methods. TRee Adaptive Parallel
Generalized Learning Vector Quantiser (TRAP GL-VQ) algorithm is a
machine learning algorithm which has number of advantages
over the other machine learning algorithms. The result shows
the improvement in efficiency, performance, accuracy, high
computational speed and reduces the processing time. TRee
Adaptive Parallel Vector Quantiser (TRAP-VQ) algorithm provides 70-80%
accuracy and it is slightly slower to execute in the testing phase due to a larger
tree structure, also has higher
computational Complexity. To overcome these drawbacks a new efficient
algorithm called TRee Adaptive Parallel Generalized Learning Vector Quantiser
(TRAPGL-VQ) is proposed. TRee Adaptive Parallel Generalized Learning
Vector Quantiser (TRAP GL-VQ) algorithm are able to achieve about 80-90%
accuracy in classification.
iv
 TABLE OF CONTENTS

CHAPTER NO. TITLE PAGE NO.

ABSTARCT iv
LIST OF FIGURES viii
LIST OF ABBREVIATION ix
1. INTRODUCTION
1.1 Virtual Reality 1
1.2 Android 3
1.3 Applications 6
1.3.1 Application Framework 6
1.3.2 Libraries 7
1.4 Android Runtime 8
1.5 Application Operating System 8
1.6 Android Workflow 9
1.7 Linux Kernel 10
2. LITERATURE REVIEW
2.1 Technologies Integration of 11
Immersive Virtual Reality on
SmartphoneswithReal-Time
Motion Capture
2.2 Low-cost virtual reality environment 11
for engineering and construction
2.3 3D modelling based on virtual reality 13
2.4 Enhanced user immersive experience 13
with a virtual reality based FPS game
interface
2.5 Virtual and Augmented Reality 14
Applications in Manufacturing

v
2.6 Using virtual reality and 3D 14
 industrial numerical models for
immersive interactive checklists
2.7 Development and evaluation of a 15
trauma decision-making simulator in
oculus virtual reality
3. SYSTEM ANALYSIS
3.1 Existing System 16
3.2 Proposed System 16
4. SYSTEM SPECIFICATION
4.1 Hardware requirements 17
4.2 Software requirements 17
5. SOFTWARE DESCRIPTION
5.1 Android Studio 18
5.2 Java Development Kit(JDK) 19
5.3 SQLite DB 20
6. PROJECT DESCRIPTION
6.1 Problem Statement 23
6.2 Introduction to Proposed System 23
6.3 Module Description 24
6.3.1 Layout Module 24
6.3.2 Operation Module 25
6.3.3 Database Module 25
7. TESTING
7.1 Unit test 27
7.2 Integration test 28
7.3 Acceptance test 28
7.4 Alpha test 29

vi
7.5 Beta test 29
 7.6 System test 30
8. CONCLUSION
8.1 Conclusion 31
8.2 Future Enhancements 31
9. APPENDIX
Appendix 1: Screenshots 32
Appendix 2: Coding 42
Appendix 3: Journal Certificate 94
Appendix 4: Reprint Paper 95
10. REFERENCES 100

vii
 LIST OF FIGURES

SNO. TITLE PAGE NO.

1. Virtual Reality 1
2. View of Virtual Reality 2
3. Android version and name 4
4. Android Architecture 5
5. Android App Workflow 9
6. Architecture diagram 23
viii
LIST OF ABBREVIATIONS

LABC Location Based Access Control

SDK Software Development Kit
SRS Software requirements specification
GPL General Public License
ADT Android Development Tool
HMD Head Mounted Display
VA Virtual Artifact
VR Virtual Reality

ix