ANNA UNIVERSITY: CHENNAI 600 025

BONAFIDE CERTIFICATE

Certified that this Project report titled “IMPLEMENTATION OF SMART GATE USING
AUTOMATIC NUMBER PLATE RECOGNITION” is the bonafide work of
M.NANDHINI (811715104058), L.SHAMEERABANU (811715104086), V.SOWMIYA
(811715104094), S.SUBATHRA (811715104099) who carried out the work under my
supervision. Certified further that to the best of our knowledge the work reported here in does
not form part of any other thesis or dissertation on the basis of which a degree or award was
conferred on an earlier occasion on this or any other candidate.

HEAD OF THE DEPARTMENT PROJECT SUPERVISOR

Mr.M.SIVAKUMAR M.E.,(Ph.D) Dr.T.AVUDAIAPPAN M.E.,Ph.D

Assistant Professor, Assistant Professor,
Department of Computer Department of Computer Science
Science and Engineering, and Engineering,
K. Ramakrishnan College of K. Ramakrishnan College of
Technology, Samayapuram, Technology, Samayapuram,
Trichy – 621 112. Trichy – 621 112.

Submitted for the Project Viva-Voce held at K. Ramakrishnan College of Technology on

_________________

INTERNAL EXAMINER EXTERNAL EXAMINER

ii
 ACKNOWLEDGEMENT

First, we like to express our sincere thanks to the God Almighty for giving
us talents and opportunity to complete our project and to our family for their
unwavering support.

At this moment of accomplishment, first of all we pay homage to our

college Chairman, Dr. K. Ramakrishnan B.E., for providing large facilities in the
institution for the completion of the project work.

It’s time to express our wholehearted thanks to our dynamic Director

Dr. S. Kuppusamy MBA., Ph.D., for providing the entire required infrastructure
and facilities in making this project a grand success.

With immense pleasure, we take this opportunity to express our sincere

gratitude to our Principal Dr. S. Muruganandam M.E., Ph.D., for encouraging us
to do innovative project.

A heartfelt thanks and sincere gratitude to our Head of the Department,

Mr. M. Sivakumar M.E., (Ph.D.,) for his valuable advice to complete this work
successfully and also for his enthusiastic encouragement to make our effort
worthwhile and fruitful.

A sincere thanks to Dr. T. Avudaiappan M.E., Ph.D., Co-ordinator for

forwarding us to do our project and offering adequate duration in completing our
project.

Our extreme indebted and appreciable gratitude to our project supervisor,

Dr. T. Avudaiappan M.E., Ph.D., who extended his full co-operation, advice and
valuable guidance which helped us to take further steps into the depth of our
project.

We also thank all other Faculty members and supporting staff of

department of Computer Science and Engineering for their support and
encouragement.
M. Janani
S. Josephine Divya
P. Karthika
iii
 ABSTRACT

Sentimental Analysis is the process of determining the opinion of the writer

based on their messages on various social networking sites. Twitter is one of the

famous social networking sites where user can read and post messages about a

person, an event, a product and the current happenings all over the world. These

are normally 140-280 characters in length. In this system, the tweets are used as

the raw data. The tweets are collected through Twitter API using the secret

tokens. Then they are preprocessed using text mining package to reduce the

noise in words. The score is computed for each pre-processed tweet using

Dictionary-Based Approach. For positive tweet the score is 1, for negative tweet

the score is -1 and 0 for neutral tweet. The pre-processed tweets along with the

scores are stored in CSV format for further process. The train data and test data

is provided in the ratio 60:40 to construct the classification model. After

classification, Convolutional Neural Network is implemented to compute the

probability of the tweets. The system uses K-fold cross validation method to

improve over the holdout method. Finally, as the result the opinion of the

sentiment related to the given tweets is predicted using probability of the

positive tweets by hybrid approach. This system produces a better performance

measure when compared to other method.

iv
 TABLE OF CONTENTS

CHAPTER NO TITLE PAGE NO

ABSTRACT iv
LIST OF FIGURES viii
LIST OF ABBREVIATIONS ix
LIST OF TABLES x

1 INTRODUCTION 1
1.1 Sentimental Analysis 1
1.1.1 Dictionary-Based Approach 2
1.1.2 Deep Learning 2
2 LITERATURE SURVEY 4
2.1 Sentiment Analysis on 4
Social Media
2.2 Comparative Analysis of 5
Twitter Data Using
Supervised Classifiers
2.3 Sentiment Analysis Based 6
on Dictionary Approach
2.4 Using Machine Learning 7
Techniques for Sentiment
Analysis
2.5 Twitter Sentiment Analysis 8
Using Deep Learning
Methods

v
CHAPTER NO TITLE PAGE NO
3 SYSTEM ANALYSIS 9
3.1 Existing System 9
3.1.1 Dictionary-Based Approach 9
3.1.2 CNN 10
3.2 Proposed System 11
4 SYSTEM SPECIFICATION 12
4.1 Hardware Requirements 12
4.2 Software Requirements 12
5 SOFTWARE ENVIRONMENT 13
5.1 R Language 13
5.2 R Studio 13
5.3 Features 14
6 SYSTEM DESIGN 15
6.1 Architecture Diagram 15
6.2 Use Case Diagram 16
6.3 Class Diagram 17
6.4 Sequence Diagram 18
6.5 Activity Diagram 19
7 IMPLEMENTATION 20
7.1 Module Description 20
7.1.1 Data Collection 20
7.1.2 Tweet Pre-processing 20
7.1.3 Polarity Mining using 21
Dictionary-Based Approach
7.1.4 Sentiment Analysis using 22

vi
 Hybrid Approach

CHAPTER NO TITLE PAGE NO

7.1.5 Performance Evaluation 24
7.1.5.1 Precision 24
7.1.5.2 Recall 24
7.1.5.3 Accuracy 24
8 EXPERIMENTAL RESULT 25
9 SYSTEM TESTING AND 28
MAINTENANCE
9.1 Test Case Scenarios 28

9.2 System Testing 28

9.3 Types of Testing 29

9.3.1 Unit Testing 29
9.3.2 Functional Testing 29
9.3.3 Integration Testing 29
9.3.4 White box Testing 29
10 CONCLUSION AND FUTURE 30
ENHANCEMENT
10.1 Conclusion 30
10.2 Future Enhancements 30
APPENDIX 1(SAMPLE CODING) 31
APPENDIX 2(SCREEN SHOTS) 43

REFERENCES 51

vii
 LIST OF FIGURES

FIGURE NO FIGURE NAME PAGE NO

6.1 Architecture Diagram 15
6.2 Use Case Diagram 16
6.3 Class Diagram 17
6.4 Sequence Diagram 18
6.5 Activity Diagram 19
7.1.4 CNN Construction 23
8.1 Comparison between Dictionary-Based 26
Approach, CNN and Hybrid Approach

viii
 LIST OF ABBREVIATIONS

S.NO. ACRONYM EXPANSION

1 AD Absolute Discounting
2 API Application Programming Interface
3 AI Artificial Intelligence
4 CNN Convolutional Neural Network
5 CSV Comma Separated Value
6 Dir Dirichlet
7 FN False Negative
8 FNN Feedforward Neural Network
9 FP False Positive
10 GNU GNU’s Not Unix
11 KDT Knowledge Discovery in Texts
12 Max Ent Maximum Entropy
13 NB Naïve Bayes
14 NLP Natural Language Processing
15 SCL Structural Correspondence Learning
16 SFA Special Feature Alignment
17 SNS Social Network Service
18 SVM Support Vector Machine
19 TC Text Classification
20 TN True Negative
21 TP True Positive

ix
 LIST OF TABLES

TABLE NO. TABLE NAME PAGE NO

8.1 Detail of Dataset 25
8.2 Train data for Dictionary-Based Approach 25
8.3 Detail of Train and Test dataset 25
8.4 Confusion Matrix for Dictionary-Based 26
Approach + CNN
8.5 Comparison of accuracy 26

x
xi