NOR FAZWANI BINTI DAGANGgreenskill.net/suhailan/fyp/report/038350.pdf · 1.8 Report Organizing 6...
Transcript of NOR FAZWANI BINTI DAGANGgreenskill.net/suhailan/fyp/report/038350.pdf · 1.8 Report Organizing 6...
BREAST CANCER PREDICTION SYSTEM
NOR FAZWANI BINTI DAGANG
BACHELOR OF COMPUTER SCIENCE
(SOFTWARE DEVELOPMENT)
UNIVERSITI SULTAN ZAINAL ABIDIN
2017
BREAST CANCER PREDICTION SYSTEM
NOR FAZWANI BINTI DAGANG
Bachelor of Computer Science (Software Development)
Faculty of Informatics and Computing
Universiti Sultan Zainal Abidin, Terengganu, Malaysia
MAY2017
i
DECLARATION
I hereby declare that this report is based on my original work except for quotations
and citations, which have been duly acknowledged. I also declare that it has not been
previously or concurrently submitted for any other degree at Universiti Sultan Zainal
Abidin or other institutions.
________________________________
Name : Nor Fazwani binti Dagang
Date : ..................................................
ii
CONFIRMATION
This is to confirm that:
The research conducted and the writing of this report was under my supervison.
________________________________
Name : PM Dr Fatma Susilawati binti Mohamad
Date : ..................................................
iii
DEDICATION
First of all thank you to ALLAH S.W.T for His mercy and guidance in giving
me the strength to complete this “Breast Cancer Prediction System” report on time.
Even facing with lots of difficulties in completing the task, I still manage to complete
it.
I would like to express my deepest sense of gratitude to my supervisor PM Dr
Fatma Susilawati Mohamad, who offered her continuous advice, idea, and
encouragement. Thank you for her effort and guidance in helping throughout this
semester.
Then I am thankful to my beloved parents for their love and continuous
support through thick and thin during my whole studies. Last but not least, I would
like to thank you to my classmates and friends who never give up on giving their
support and help in completing this task.
Thank you.
iv
ABSTRACT
Breast Cancer Prediction System is a web based system that has been prepared to be
use for user and it is an online prediction system. The problem that occurs is user or
patient is always having difficulties when they go to hospital to make a check up, but
the doctors were not available on that time. The purpose of this system is to allow user
to check whether they have breast cancer or not. User need to enter the details or
answer the questions that have been given and the cancer disease associated will
appear with those details. This system will give the prediction about breast cancer and
after that it will give the best advice and suggestion to the user. This system also
allows user to share their health related issues for breast cancer. It then processes user
specific details to check for various symptoms that could be associated with it. User
and admin also can create, update, delete and retrieve their profile. The added value of
this system is rule-based algorithm. Rule-based algorithm can be used for powering
prediction the disease.
v
ABSTRAK
Breast Cancer Prediction System adalah sistem berasaskan web yang disediakan
kepada pengguna dan ia adalah sistem ramalan atas talian. Masalah yang dihadapi
oleh pengguna atau pesakit ialah mereka selalu mengalami kesukaran apabila mereka
ke hospital untuk melakukan pemeriksaan, tetapi doktor tiada pada masa itu. Tujuan
sistem ini adalah untuk membenarkan pengguna untuk memeriksa sama ada mereka
mereka menghidap kanser payudara atau tidak. Pengguna perlu memasukkan
maklumat mereka atau menjawab soalan yang telah diberi dan maklumat yang
berkaitan dengan penyakit kanser akan muncul. Sistem ini akan memberi ramalan
tentang kanser payudara dan akan memberi nasihat dan cadangan yang terbaik
kepada pengguna. Sistem ini juga membenarkan pengguna berkongsi masalah
berkaitan kesihatan tentang kanser payudara. Ia akan memproses dan mengenalpasti
symptom yang berkaitan dengan masalah itu. Pengguna dan admin boleh create,
update, delete dan retrieve profil mereka. Nilai tambahan untuk sistem ini adalah
rule-based algoritma. Rule-based algoritma boleh digunakan untuk menjanakan
ramalan penyakit ini.
vi
CONTENTS
PAGE
DECLARATION i
CONFIRMATION ii
DEDICATION iii
ABSTRACT iv
ABSTRAK v
CONTENTS vi
LIST OF TABLES vii
LIST OF FIGURES xvi
LIST OF ABBREVIATIONS xv
CHAPTER I INTRODUCTION
1.1 Project Background 1
1.2 Problem statement 4
1.3 Objectives 4
1.4 Scopes 4
1.5 Expected Outcome 5
1.6 Limitation of Work 6
1.7 Project Planning 6
1.8 Report Organizing 6
1.9 Chapter Summary 7
CHAPTER II LITERATURE REVIEW
2.1 Introduction 8
2.2 Research Towards Existing System 9
2.3 Research Related with Others Method 10
2.4 Research on Related Techniques, Tools, and
Technologies
11
2.5 Rule-Based Concept Theory 12
2.6 Chapter Summary 14
vii
CHAPTER III
METHODOLOGY
3.1 Introduction 15
3.2 Justification Selection 15
3.3 Methodology Phases 17
3.3.1 Planning Phase 17
3.3.2 Risk Analysis Phase 17
3.3.3 Engineering Phase 17
3.3.4 Evaluation Phase 18
3.4 System Requirement 19
3.4.1 Hardware Requirement 19
3.4.2 Software Requirement 20
3.5 Framework 21
3.6 Context Diagram 23
3.7 Data Flow Diagram 25
3.7.1 DFD Level 1 Manage User Profile 27
3.7.2 DFD Level 1 Manage Questionnaire 28
3.7.3 DFD Level 1 Manage Result 29
3.7.4 DFD Level 1 Manage Admin profile 30
3.7.5 DFD Level 1 Manage Information 31
3.7.6 DFD Level 2 Manage User Profile 32
3.8 Entity Relationship Diagram (ERD) 33
3.9 Algorithms 34
3.10 Database Modelling 35
3.11 Chapter Summary 38
REFERENCES 39
viii
LIST OFTABLES
TABLE TITLE PAGE
3.1 List of Hardware 19
3.2 List of Software 20
ix
LIST OF FIGURES
FIGURE TITLE PAGE
3.1 Spiral Model 16
3.2 Framework 21
3.3 Context Diagram 23
3.4 Data Flow Diagram Level 0 25
3.5 DFD Level 1 for Manage User Profile 27
3.6 DFD Level 1 for Manage Questionnaire 28
3.7 DFD Level 1 for Manage Result 29
3.8 DFD Level 1 for Manage Admin Profile 30
3.9 DFD Level 1 for Manage Information 31
3.10 DFD Level 2 for Manage User Profile 32
3.11 Entity Relationship Diagram 33
3.12 Tables in Database for Breast Cancer System 35
3.13 Table Admin in Database 35
3.14 Table Information in Database 36
3.15 Table Questionnaire in Database 36
3.16 Table Result in Database 36
3.17 Table User in Database 37
x
LIST OF ABBREVIATIONS / TERMS / SYMBOLS
CD Context Diagram
DFD Data Flow Diagram
ERD Entity Relationship Diagram
FYP Final year project
xi
LIST OF APPENDICES
APPENDIX TITLE PAGE
A Gantt Chart FYP 1 41
1
CHAPTER I
INTRODUCTION
1.1 Project Background
Cancer or tumor is a group of disease that involve abnormal cell growth with
the potential to spread to other parts of the body but not all tumors are cancerous.
There are 100 types of cancer, including breast cancer, skin cancer, lung cancer,
colon cancer and lymphoma. Breast cancer is the one of the popular and second
leading cause of cancer death in women. The chance that a woman will die from
breast cancer is about 1 in 37 which is 2.7%.
Mostly the patient did not notice that they have breast cancer in the early stage
because breast cancer starts when cells in the breast begin to grow out of control.
This cell that from tumor usually can be seen on an x-ray or felt as a lump. Breast
cancer occurs almost in women, but men also can get breast cancer.
Each year, an estimated 1.6 milion new cases are diagnosed worlwide and in
2015, 560 thousand women die because of breast cancer (World Health
Organisation and National Cancer Registry of Malaysia 2005-2007). However,
death rates from breath cancer was dropped from 1989 to 2007. Since 2007, breast
cancer death rates have been steady in women younger than 50, but have
2
continued to decreased in older women (American Cancer Society’s Cancer
Statistic Centre,2016). The decreases of the death rates in older women is believed
that they noticed and get result of finding breast cancer earlier through screening
and increased awareness which is get the treatment as soon as possible.
Breast cancer is hard to diagnose but when finding the breast cancer as early as
possible, it will gives a better chance of successful treatment. To found out the
breast cancer, it need to do the screening test. Screening test can help find breast
cancer in its early stages, even before any symptoms appear. There are some
common symptom of breast cancer. The most common symptom is a new lump or
mass. A painless, hard mass that has irregular edges is more likely to be cancer,
but breast cancers can be tender, soft, or rounded. So that, if there have any new
breast mass or lump or breast change, it is important to checked by a health care
provider experienced in diagnosing breast disease.
So that, it is important to all people especially women to be aware of changes
in the breasts and to know the signs and symptoms of breast cancer. In this project,
we propose a rule-based algorithm that functions as a reliable decision support
system for breast cancer prediction.
3
Next, this project will arranged as starting by Chapter 1 that describes on the
introduction of the project, followed by Chapter 2 that explained on the literature
review that related to the previous research. After that, Chapter 3, the project
methodology, Chapter 4 deals with project design and modelling and lastly
Chapter 5 that concludes and identify the results of the project. The main goal of
this research is to develop a system that can be used by a person for predict
whether the person have breast cancer or not based on the symptoms details and
suggest to the patients what they need to do after that.
4
1.2 Problem Statement
The problem for this project is cancer are difficult to diagnose at early stages until
it comes to stage III and IV. Some people have difficulties to go to hospital to
make check up regularly because they lack of times or doctors did not free on that
time. Some people maybe have different symptoms and it will not be easily to
assume whether they have breast cancer or not. The possible symptoms of breast
cancer are swelling of all or part of a breast, skin irritation or dimpling, breast or
nipple pain, nipple retraction, redness, scaliness or thickening of nipple or breast
skin and nipple discharge that other than breast milk.
1.3 Objectives
i. To design and develop Breast Cancer Prediction system which can
help user to predict early sign of breast cancer.
ii. To apply Rule-Based algorithm for detecting symptoms of breast
cancer.
iii. To test and evaluate the proposed systems with the real cases.
1.4 Scope
This system will focus on Registered User, Admin and System Scope.
i. Registered User
The user that want to check or predict the health status on breast cancer
based on the symptoms that they have.
The user need to register/sign up to be a member and then login to
access the system.
Do prediction of breast cancer using the system.
ii. Admin
5
The person who will coordinate this system and update the system
based on situation.
iii. System
Login Module
- There is a registration and login access for user and admin to access
this system.
Evaluation Module
- Registered User will answer and evaluate the questionaires based
on what this system provide to find out the result.
Advice and Suggestion Module
- The system will give advices and suggestions to the user after they
predict the cancer and the result is positive.
Domain System (cancer)
- The result will generate based on the answer from Registered User
and analyze it with Rule-Based algorithm.
1.5 Expected Outcome
This system is expected to give an accurate prediction about the breast cancer
based on the symptoms that user have enter the details or answered the questions
that have be given. This system also expected to give advices and suggestions to
user after they predict the cancer and allow the user to share their health related
issues for breast cancer.
6
1.6 Limitation of Work
This system will focuses on prediction of breast cancer based on the details
that have be given. This system does not give the decision on what the stages of
cancer ( I,II,III or IV), it just only to predict whether the person have breast cancer
or not. The result may not be 100% accurate but the result from this system will
help the user to quickly take action and alert for the breast cancer by seek
consultant from doctor or diagnose the breast cancer using screening test.
1.7 Project Planning
Detailed project planning that has been implemented to facilitate system
development can referred to Appendix A.
1.8 Report Organizing
The reports organizing each chapter that have on the reort it arrange will refer
to the specific format and it easy for readers to understand the whole of the report.
The report is started with chapter 1 that explains about introduction, problem
statement, objective, scope, limitation of work, expected outcome and project
planning. The next chapter 2 explains about the literature review related paper
research for the system development. Then, chapter 3 discussed about project
methodology and requirement of software and hardware that guide the system
development. Chapter 4 deals with project design and modelling are the core part
in the development process. Lastly, chapter 4 conclude on the project
development.
7
1.9 Chapter Summary
In this chapter it will deliver about the early stages about this project
development. It explains more about initially project development process.
8
CHAPTER 2
LITERATURE REVIEW
2.1 Introduction
Basically, in this chapter, the study of previous research is done. The related
journal and articles was analyzed to find out what are the weakness of the previous
research that we can overcome. Research paper related to rule-based has proved to be
a powerful tool for decision making system, such as expert systems and pattern
classification systems. Rule-based has already been used in some medical expert
systems. The related system of cancer prediction is also been reviewed to help in
understanding and gain knowledge about how to implement the system in the real
applications. Here, some of the previous paper that has some weakness that can be
solved through this project.
9
2.2 Research towards Existing System
Breast cancer is one of cancer killer in the world and can also kill men as well,
not only women. Early detection of cancer is essential for a fast response and better
chances of cure. But it is difficult to detect when it is in beginning because some of
the symptoms of the disease are absent at the beginning. Machine learning methods
and clinical factors was use to develop tools of cancer management. Rule based is one
of the machine learning methods. It has proved to be a powerful tool of decision
making systems. Rule based set theory has already been used in some medical expert
system.
In traditional rule-based approach, knowledge is encoded in the form of
antecedent consequent structure. When new data is encountered, it is matched to the
antecedents clauses of each rule, and those rules where antecedent match a data
exactly are fired, establishing the consequent clauses. This process continues until
desire conclusion is reached. In the past decade, fuzzy logic has proved to be
wonderful tool for intelligent systems in medicine. Some examples of using fuzzy
logic to develop fuzzy intelligence systems are fuzzy systems in their micro
processors, fuzzy cameras and camcorders that map image data to lens settings, and
fuzzy voice commands “up”, “land”, “hover” to control unmanned helicopters. (Bart
Kosko, Fuzzy Engineering, Prentice Hakk, 1997).
10
2.3 Research Related with Others Method
Breast Cancer Diagnosis by using k-Nearest Neigbor with Different Distance
and Classification Rules by Seyyid Ahmad Medjahed, Tamazouzt Ait Saadi,
Abdelkader Benyettou, 2013. This paper is to analyze the distance by using different
values of the parameters “k” and by using several rules of classificarion and to
evaluate the performance that can be used in the K-NN algorithms. In this paper, they
study and analyze several distance and different values of the nearest neighbors
parameter k, by using different classification rules in the k-nearest neighbor algorithm.
K-nearest neigbors algorithms is one of the most used algorithms in machine learning
and its a learning method based on instances that does required a learning phase.
Before classifiying anew element, they compare it to other elements using a similarity
measures. Its k-nearest neigbors are then considered, the class that appears most
among the neighbors is assigned to the element to be classified. The neighbors are
weighted by the distance that separate it to the new elements to classify.
Next, Tumor-Infiltrating CD8+ Lymphocytes Predict Clinical Outcome in
Breast Cancer by Sahar M.Amahmoud, Emma Claire Paish, Desmond G. Powe, 2011
has applied CD8+ T-Cell Quantification Method in this paper. Based on this paper, the
number of CD8+ Tlymphocytes was counted in each tumor core by using Nikon
Eclipse 80i micrscope and an eyepiece graticule by an investigator who had no
previous kniwledge of the patients clinical background. CD8+ T-Cellwere counted in
three locations in each tumor. The total number of CD8+ T-Cell was determinrd by
combining the counts for the three compartments and the scores were randomly re-
examined by the same investigator after a period of time to ensure reproducibility.
11
2.4 Research on Related Techniques, Tools, and Technologies
Several techniques had been defined by experts such as CD8+ Tlymphocytes
Cell Quantification, k-Nearest Neigbor and some machine learning applications.
Machine learning relates the problem of learning from data samples to the general
concept of inference. Based on the paper by Konstantina Kourou, Themis P.Exarchos,
Konstantinos P. Exarchos, Michalis V. Karamouzis, Dimitrios I. Fotiadis in Machine
Learning applications in cancer prognosis and prediction, 2014, they present a review
of recent Machine Learning approaches employed in the modelling of cancer
progression. The predictive models discussed are based on various supervised
Machine Learning technique as well as on different input features and data samples.
Then, they present the most recent publications that employ these techniques.
Another paper that using Data Mining Techniques is Diagnosis of Lung
Cancer Prediction System Using Data Mining Classification Techniques by V.
Krishnaiah, Dr. G. Narsimha, Dr. N. Subhash Chandra, 2013. This paper is to examine
the potential use of classification based data mining techniques, propose a model for
early detection and correct diagnosis of the disease and to summarize various review
and technical articles on diagnosis of lung cancer. In this study, they briefly examine
the potential use of classification based data mining techniques such as Naive Bayes,
Rule-Based, Decision Tree and Neural Network to massive volume of healthcare data.
They list the various analysis tasks that can be goals of discovery process and lists
methods and research areas and then compare the result.
12
2.5 Rule-Based Concept and Theory
A rule-based system is a set of “if-then” statements that uses a set of
assertions, to which rules on how to act upon those assertions are created. In software
development, rule-based systems can be used to create software that will provide an
answer to a problem in place of a human expert. This type of system may also be
called an expert system. Rule-based systems are also used in AI (Artificial
Intelligence) programming and systems.
Example of Rule-Based Concept:
IF (fever (high)) THEN Malaria
IF (Coldness) THEN Malaria
IF (Throb) THEN Malaria
IF (Sweat) THEN Malaria
IF (Sometimes colour of urine is black water fever) THEN Malaria
IF (Headache) THEN Malaria
IF (Vomiting) THEN Malaria
IF (Muscle pain) THEN Malaria
IF (High temperature) THEN Malaria
IF (Diarrhoea) THEN Malaria
IF (Coma (Seizure)) THEN Tuberculosis
IF ( Stiff Neck) THEN Tuberculosis
IF (Headache) THEN Tuberculosis
IF (AbdoIfminal Pain) THEN Tuberculosis
IF ( Weight Pain) THEN Tuberculosis
IF ( Fever) THEN Tuberculosis
13
IF (Masses along the neck) THEN Tuberculosis
IF (Draining Sinus) THEN Tuberculosis
IF (Small Reddish brown lesions ( face, eyelid, nose, cheek and ear)) THEN
Tuberculosis
IF (Reddish brown wart-like growth on the body) THEN Tuberculosis
IF (Skin lesions on hand, feet, elbow and knees) THEN tuberculosis.
IF ( Ulcer or abscesses on the Skin) THEN Tuberculosis
IF ( Necrosis of infected Skin) THEN Tuberculosis
IF (Stiffness of affected area) THEN Tuberculosis
IF (Blood present in Urine) THEN Tuberculosis
IF (Painful or uncomfortable Urination) THEN Tuberculosis
IF ( Hemopysis (coughing up blood)) THEN Tuberculosis
14
2.6 Chapter Summary
This chapter discussed about the collection of literature review that had been
reviewed during the feasibility studies. The literature review helps developer to
discover the problem of previous research or systems which needs to be overcome in
this system development. Besides that, it also can gain understanding about the system
that undergo the development process.
15
CHAPTER 3
RESEARCH METHODOLOGY
3.1 Introduction
This chapter explains details of methodology being used in software
development. The project methodology is important in every project because it helps
to organize investigation in a scientific ways to overcome problems, hunting for facts
or truth about the subject in order to achieve the objectives of project. In order to have
a good project, it should begin with a good understanding on user’s needs.
3.2 Justification Selection
The methodology for the system development that had been used extensively
is Spiral Model. Based on the Spiral Development Model that developed by Barry
Boehm (Boehm, 1998) had a profound impact on life cycle modelling and process
architecture. It means that the Spiral Model is the most appropriate used for
development of some system.
The Spiral Model which clearly divides the phases into four which are
Planning, Risk Analysis, Engineering and Evaluation. For every phase, some activity
has been allocated. The figure below describes briefly what activities involve for each
of the phases. Thus, developer will have clear understanding about what to do for
every phases. The allocation of activities for each phase consequence in the cost and
resource estimation thus to help in reducing risk during development.
16
Figure 3.1 Spiral Model
17
3.3 Methodology Phases
3.3.1 Planning Phase
In this phase, planning phase discussed a reason for selected goals include the
detail overview of the goals. In this phase, first objective of the project are describe to
identify a risk for fit people who can possibly get cancer and to make early detection.
The title of this project has selected, Breast Cancer Prediction System. The abstract
was done with all information gathered. Then, the entire requirement that involved in
the system will be identified.
3.3.2 Risk Analysis Phase
In risk analysis phase, the requirements are studied and brain storming sessions
were done to identify the potential risks. The risk that may exist is when it is difficult
to differentiate the symptoms or it may be risk when the information of the symptoms
is false. Once the risk was identified, risk mitigation strategy is planned and finalized.
3.3.3 Engineering Phase
This phase involve the actual development and testing. Breast Cancer
Prediction System will be developed and will be tested. It will combine all the
modules to become a complete system and will do integrating testing to make sure this
system will function nicely. The development involves code, test cases, results, test
summary, and report.
18
3.3.4 Evaluation Phase
In evaluation phase, admin will use and evaluate of the system. Then, user will
provide their feedback and approval for the system. The features implemented
document will be an output from this phase.
19
3.4 System Requirement
System requirement is the pre-requisites for a system to be run on a device.
System requirement are often used as opposed to an absolute rule. There are two
requirements that need to be considered in the development process, software and
hardware requirement.
3.4.1 Hardware Requirement
The list of software that used to develop this system is shown in table below:
Table 3.1 List of Hardware
HARDWARE DESCRIPTION
Laptop HP
Processor: AMD A8-6410 APU with AMD Radeon R5 Graphic 2.00
GHz
RAM: 4.00 GB
OS: Windows 8.1
Printer HP Deskjet 3630 series
20
3.4.2 Software Requirement
The list of software that used to develop this system is shown in table below:
Table 3.2 List of Software
SOFTWARE DESCRIPTION
Microsoft Office Word 2007 As platform for documentation and presentation
Edraw Max Tool to draw diagrams (CD, DFD, framework and interfaces)
Mozilla Firefox, Google
Chrome
Browser for running a system and find research and information
about the system.
XAMPP version 3.2.2 Act as a local server to run and test the system.
MySQL Database
Open source relational database management system that uses
structured Query Language and store the data of the system.
Dropbox Application for backup the system and data.
21
3.5 System Framework
Figure 3.2 shows the framework for Breast Cancer Prediction System.
Figure 3.2 Framework
22
Description of framework:
Based on the figure 3.2, it shows the framework on how the system running.
Firstly, user need to register and then login to access the Breast Cancer Prediction
System. All the data of user that had been register will save into database. Then, user
needs to answer the questionnaires given to diagnose the cancer and then system will
generate the results. After that, system will give suggestions and preventions for the
disease after user get their result. The suggestions and preventions are based on the
result of diagnose the user based on the result answers of questionnaires given. Lastly,
user can see results and recommendation given by the system. All of the steps are
saving into the database. Next, admin can login into Breast Cancer Prediction System.
Admin can look up the results of the user and admin also can update the
questionnaires.
23
3.6 Context Diagram
Context diagram explains the flow of the system based on the entities
and main process that involve in the system functional. It just describes the
main function of the system.
Figure 3.3 Context Diagram
24
Description:
The context diagram for Breast Cancer Prediction System is shown in the
figure above. THE BREAST CANCER PREDICTION process is at the centre of the
diagram. There are two entities in this system which is USER and ADMIN. The
entities are placed around the central process. Ten data flows are involved in the
interaction between the central process and the entities. The USER entity has three
incoming data flows which are Cancer Evaluation, Breast Cancer Information and
Prediction Result. USER also has three outgoing data flows, Register/Login, Personal
Details and Answer Questionnaires. The ADMIN entity has only one incoming data
flow which is User Details and has three outgoing data flows. There are Update
Information, Login and Update Questionnaires.
25
3.7 Data Flow Diagram Level 0
Data flow diagram shows the flow of the data that through in this system. That
shows the data will save in the database with specific table that have been created in the
database.
Figure 3.4 Data Flow Diagram Level 0
26
Description of DFD Level 0:
The DFD has two entities which are User and Admin. Manage User Profile,
Manage Questionnaire, Manage Result, Manage Suggestion, Manage Admin Profile,
Manage Information and Report are the seven process involve in the system. There are
four data stores created in the system which are User, Questionnaire, Admin and
Information.
1. User enter the details which are email, username, password, first name,
last name, gender,status and state to register and log in process that is
user profile process which outputs the details into user data store.
2. A user inputs the answer details of the questionnaire into questionnare
process which output answer details into questionnaire data store.
3. The output from the questionnaire data store which is result details will
input to the result process and output to the user.
4. The output of the questionnaire data store which is suggestion details
will input to the suggestion process and send to user.
5. Admin input the update questionnaire into questionnaire process and
output to questionnaire data store.
6. Admin input the admin details into admin profile process to admin data
store.
7. Admin input the information details about breast cancer into
information process which output information details to information
data store.
8. All the entities will input the report to report process and all the data
store will input the report to report data store.
27
3.7.1 Data Flow Diagram Level 1
Manage User Profile
Figure 3.5 Data Flow Diagram Level 1 for Manage User
Description:
1. User input user details to Register process and output user details to User
data store.
2. The user details from User data store are input to Update Details process
and User input user details to Update Details process and output Updated
User Details to User data store.
28
3.7.2 Data Flow Diagram Level 1
Manage Questionnaire
Figure 3.6 Data Flow Diagram Level 1 for Manage Questionnaire
Description:
1. Admin input Questionnaire Details to Add Questionnaire process and output
Questionnaire Details to Questionnaire data store.
2. The questionnaire details from Questionnaire data store are input to Update
Questionnaire process and admin input questionnaire details to Update
Questionnaire process and output Updated Questionnaire Details to
Questionnaire data store.
3. Admin input Questionnaire Details to Delete Questionnaire process and output
questionnaire details to Questionnaire data store.
29
3.7.3 Data Flow Diagram Level 1
Manage Result
Figure 3.7 Data Flow Diagram Level 1 for Manage Result
Description:
1. User input answer details to Answer Questionnaire process and output answer
detail Questionnaire data store.
2. Questionnaire answer from Questionnaire data store input to Result process
and output Result of Prediction to User.
30
3.7.4 Data Flow Diagram Level 1
Manage Admin Profile
Figure 3.8 Data Flow Diagram Level 1 for Manage Admin Profile
Description:
1. Admin input admin details to Add Admin process and output admin details to
Admin data store.
2. The admin details from Admin data store are input to Update Admin process
and Admin input admin details to Update Admin process and output Updated
Admin Details to Admin data store.
3. Admin input Admin Details to Delete Admin process and output admin details
to Admin data store.
31
3.7.5 Data Flow Diagram Level 1
Manage Information
Figure 3.9 Data Flow Diagram Level 1 for Manage Information
Description:
1. Admin input information details to Add Information process and output
information details to Information data store.
2. The information details from Information data store are input to Update
Information process and Admin input information details to Update
Information process and output Updated Information Details to
Information data store.
3. Admin input Information details to Delete Information and output the information
details to Information data store.
32
3.7.6 Data Flow Diagram Level 2
Manage User Profile
Figure 3.10 Data Flow Diagram Level 2 for Manage User Profile
Description:
1. A User Update Password in the Update Password process by sending New
Password at User data store.
2. A User send new data to Update Email at Update Email process by sending
New Email to User data store.
33
3.8 Entity Relationship Diagram (ERD)
Entity Relationship Diagram (ERD) is a data model which is tools used in
analysis to describe the data requirement and assumptions in the system from top-down
perspectives. The ERD shows it using derived table. Derived are used for make a
relationship between two or more main tables, it will have only record of foreign key
from the main table.
Figure 3.11 Entity Relationship Diagram (ERD)
34
3.9 Algorithms
1. Start
2. Answer twenty questions about self information and the risk of breast cancer
3. Tick the answers
4. Each answer have its value which are 0 for no and 1 for yes
5. Select value1 and value2 from radio button
6. Value = value1 + value2
7. If ($Value ≤ 8) {
8. Display message "You are at LOWER risk of Breast Cancer !";
9. }
10. else if (9 ≤ $Value ≤18){
11. Display message "You are at INTERMEDIATE risk of Breast
Cancer!”;
12. }
13. else
14. Display message "You are at HIGH risk of Breast Cancer !”;
15. }
16. End
35
3.10 Database Modelling
There are five tables available in the database which is Admin, Information,
Questionnaire, Result, and User. Each table have their attributes in the column.
Figure 3.12 Tables in Database for Breast Cancer System
3.10.1 Table Admin
Figure 3.13 Table Admin in Database
Table Admin contain adminID, adminName, adminPass, adminEmail, and phone. In
this table, adminID is the Primary Key.
36
3.10.2 Table Information
Figure 3.14 Table Information in Database
In this table, it contains infoID, infoDetail and date. The infoID is the Primary Key.
3.10.3 Table Questionnaire
Figure 3.15 Table Questionnaire in Database
Table questionnaire contains questionID and question and the Primary Key is
questionID.
3.10.4 Table Result
Figure 3.16 Table Result in Database
This table contains resultID, suggestion and user_score which is resulted is the
Primary Key.
37
3.10.5 Table User
Figure 3.17 Table User in Database
Table user contains username, password, email, name, gender and status and the
Primary Key is username.
38
3.11 Chapter Summary
This chapter discusses methodology for the system development, hardware and
software required in order to develop the system thus make them able to run on
specific platform. Every phase in development follows the project methodology that
mention in this chapter. System requirement which is hardware and software required
for developing system is briefly explained. Throughout this chapter also focussed
about data modelling which are context diagram, data flow diagram and entity
relationship diagram. In data modelling, the discussion is more about the structure of
the data represent in the database. Diagrams were constructed in order to give more
understanding of the system.
39
REFERENCES
1. World Health Organisation and National Cancer Registry of Malaysia 2005-
2007.
2. American Cancer Society’s Cancer Statistic Centre, 2016.
3. Bart Kosko, Fuzzy Engineering, Prentice Hakk, 1997.
4. V. Krishnaiah, Dr. G. Narsimha, Dr. N. Subhash Chandra, 2013. Diagnosis of
Lung Cancer Prediction System Using Data Mining Classification Techniques.
5. Konstantina Kourou, Themis P.Exarchos, Konstantinos P. Exarchos, Michalis
V. Karamouzis, Dimitrios I. Fotiadis, 2014. Machine Learning Applications in
Cancer Prognosis and Prediction.
6. Sahar M.Amahmoud, Emma Claire Paish, Desmond G. Powe, 2011. Tumor-
Infiltrating CD8+ Lymphocytes Predict Clinical Outcome in Breast Cancer.
7. Seyyid Ahmad Medjahed, Tamazouzt Ait Saadi, Abdelkader Benyettou, 2013.
Breast Cancer Diagnosis by using k-Nearest Neigbor with Different Distance
and Classification Rules.
8. A. Priyanga, S. Prakasam, 2013. Effectiveness of Data Mining-based Cancer
Prediction System (DMBCPS).
9. Kyu-Won Jung, Sohee Park, Young-Joo Won, Hyun-Joo Kong, Joo Young
Lee, Hong Gwan Seo, Jin-Soo Lee, 2012. Prediction of Cancer Incidence and
Mortality in Korea.
10. Adewole K. S., Hambali M. A., Jimoh M. K., 2015. Rule-Based Expert
System for Disease Diagnosis.
40
11. Data Mining - Rule Based Classification. 2017.
https://www.tutorialspoint.com/data_mining/dm_rbc.htm. Accessed on 12
February 2017.
12. Jermal A,Murray T,Samuels A,Ghafoor A,Ward E,Thun MJ,2003. Cancer
Journal for Clinician.
41
APPENDIX A: GANTT CHART FYP1