A PRELIMENERY REPORT ON

WILD FIRE DETECTION USING IMAGE PROCESSING

SUBMITTED TO THE SAVITRIBAI PHULE PUNE UNIVERSITY, PUNE

IN THE PARTIAL FULFILLMENT OF THE REQUIREMENTS
FOR THE AWARD OF THE DEGREE

OF

BACHELOR OF ENGINEERING (COMPUTER ENGINEERING)

SUBMITTED BY

ADITI PHADKE BEA 64

RAJNI NARWADE BEC 15
MAYUR SAMRIT BEC
SAPTARSHI LANJEWAR BEC 21

DEPARTMENT OF COMPUTER ENGINEERING

STES’S SINHGAD INSTITUTE OF TECHNOLOGY

KUSGAON (BK), LONAVALA, PUNE- 410401

SAVITRIBAI PHULE PUNE UNIVERSITY

2021 -2022

SIT, Department of Computer Engineering 2021-2022 1

 CERTIFICATE

This is to certify that the project report entitles

“WILD FIRE DETECTION USING IMAGE PROCESSING”

Submitted by

ADITI PHADKE BEA 64

RAJANI NARWADE BEC 15
MAYUR SAMRIT BEC
SAPTARSHI LANJEWAR BEC 21

is a bonafide student of this institute and the work has been carried out by him/her under the
supervision of Prof. S. R. Patil and it is approved for the partial fulfillment of the
requirement of Savitribai Phule Pune University, for the award of the degree of Bachelor of
Engineering (Computer Engineering).

(Prof. S. R. Patil) (Prof. S. D. Babar)

Guide Head,
Department of Computer Engineering Department of Computer Engineering

(Dr. M.S. Gaikwad)

Principal,
Sinhgad Institute of Technology, Lonavala, Pune – 410401

Place: Lonavala
Date:
SIT, Department of Computer Engineering 2021-2022 2
 ACKNOWLEDGEMENT

It gives us great pleasure in presenting the preliminary project report on

‘WILD FIRE DETECTION USING IMAGE PROCESSING’.

Behind any major work undertaken by a team there lies the contribution of the people who
helped us to cross all the hurdles to achieve our goal. It gives us the immense pleasure to
express our sense of sincere gratitude towards our respected guide Prof. S. R. PATIL, for her
persistent, outstanding, invaluable co- operation and guidance. It is our achievement to be
guided under her. She is a constant source of encouragement and momentum that any
intricacy becomes simple. We gained a lot of invaluable guidance and prompt suggestions
from her during entire project work. We will be indebted of her forever and we take pride to
work under her.

We also express our deep sense of regards and thank Dr. S.D. Babar, Head of Computer
Engineering Department, Sinhgad Institute of Technology, Lonavala. We feel very privileged
to have had their precious advices, guidance and leadership.

Thanking you,

Group Members
Aditi Phadke (B150424351)
Rajani Narwade (B150424327)
Mayur Samrit (B150424373)
Saptarshi Lanjewar (B150424376)

SIT, Department of Computer Engineering 2021-2022 3

 ABSTRACT

Wildfires are a type of calamity that is difficult to predict and causes enormous damage to
human life, ecological systems, and infrastructure. There have been various attempts to use
convolutional neural networks (CNNs) to identify wildfires. However, because most of these
systems simply detect flames, they are insufficient to prevent death and mitigate economic
and material damage. We describe a deep learning-based method for detecting wildfires at an
early stage by identifying flames to address this issue.

A vast dataset on wildfire is obtained from the web in order to fulfil the proposed idea. To
balance efficiency and accuracy, a light-weight yet powerful design is used. Wildfires are a
danger to both the environment and human health, particularly in the age of global warming.
Because wildfires can be difficult to control once they reach a certain size, early detection is
critical to effective fighting. As a result, rangers have created automated wildfire detection
systems to assist them in their efforts to prevent wildfires.

The German aerospace facility DLR (Deutsches Zentrum für Luftund Raumfahrt) produced
one of the most successful systems, which relies on advanced hand-crafted characteristics.
The fshell algorithm is the brains behind this system. Convolutional neural networks (CNNs)
are specialized artificial neural networks that are the current state-of-the-art in image
recognition. As a result, it's being looked into whether these trainable models may be used to
improve wildfire detection.

SIT, Department of Computer Engineering 2021-2022 4

 TABLE OF CONTENTS
LIST OF ABBREVATIONS i.
LIST OF FIGURES ii.
LIST OF TABLES iii.

Page
Sr.No Title of Chapter No.
01 INTRODUCTION 11
1.1 Overview 13
1.2 Motivation 13
1.3 Problem Definition and Objectives 13
1.4 Project Scope & Limitations
1.5 Methodologies of Problem solving
02 LITERATURE SURVEY 16
03 SOFTWARE REQUIREMENTS SPECIFICATION
3.1 Assumptions and Dependencies
3.2 Functional Requirements
3.2.1 System Feature 1(Functional Requirement)
3.2.2 System Feature2 (Functional Requirement)
……
……
3.3 External Interface Requirements (If Any)
3.3.1 User Interfaces
3.3.2 Hardware Interfaces
3.3.3 Software Interfaces
3.3.4 Communication Interfaces
3.4 Nonfunctional Requirements
3.4.1 Performance Requirements
3.4.2 Safety Requirements
3.4.3 Security Requirements
3.4.4 Software Quality Attributes
3.5 System Requirements
3.5.1 Database Requirements
3.5.2 Software Requirements (Platform Choice)
3.5.3 Hardware Requirements
3.6 Analysis Models: SDLC Model to be applied
04 SYSTEM DESIGN
4.1 System Architecture
4.2 Mathematical Model
4.3 Data Flow Diagrams
4.4 Entity Relationship Diagrams
4.5 UML Diagrams
SIT, Department of Computer Engineering 2021-2022 5
05 PROJECT PLAN
5.1 Project Estimate
5.1.1 Reconciled Estimates
5.1.2 Project Resources
5.2 Risk Management
5.2.1 Risk Identification
5.2.2 Risk Analysis
5.2.3 Overview of Risk Mitigation, Monitoring, Management
5.3 Project Schedule
5.3.1 Project Task Set
5.3.2 Task Network
5.3.3 Timeline Chart
5.4 Team Organization
5.4.1 Team structure
5.4.2 Management reporting and communication
06 PROJECT IMPLEMENTATION
6.1 Overview of Project Modules
6.2 Tools and Technologies Used
6.3 Algorithm Details
6.3.1 Algorithm 1
6.3.2 Algorithm 2
6.3.3 …
07 SOFTWARE TESTING
7.1 Type of Testing
7.2 Test cases & Test Results
08 RESULTS
8.1 Outcomes
8.2 Screen Shots
09 OTHER SPECIFICATIONS
9.1 Advantages
9.2 Limitations
9.3 Applications
10 CONCLUSIONS
10.1 Conclusions
10.2 Future Work
Appendix A: Problem statement feasibility assessment using, satisfiability
analysis and NP Hard, NP-Complete or P type using modern algebra and
relevant mathematical models.
References
Integrated Forest Monitoring System for Early Fire Detection and Assessment
by George Georgiades, Xanthi S. Papageorgiou, Low-Cost System for Early
Detection and Deployment of Countermeasures Against Wild Fires by Low-
Cost System for Early Detection and Deployment of Countermeasures Against
Wild Fires, Firebird – Small Satellites For Wild Fire Assessment by Winfried
Halle1, Sarah Asam2, Erik Borg2, etc

SIT, Department of Computer Engineering 2021-2022 6

SIT, Department of Computer Engineering 2021-2022 7
LIST OF ABBREVATIONS
ABBREVIATION ILLUSTRATION

VPN Virtual Private Network

IP Internet Protocol
IDS Intrusion Detection System
TCP Transmission Control Protocol

SIT, Department of Computer Engineering 2021-2022 8

 LIST OF FIGURES

FIGURE ILLUSTRATION PAGE NO.

1.1 System Overview 3

1.2 System Behavior 5
2.1 TCP Header 11
4.1 Waterfall Model 27
4.2 Timeline Chart 30
4.3 DFD Level – 0 31
4.4 DFD Level – 1 32
4.5 DFD Level – 2 33
4.6 Use case Diagram 34
4.7 Sequence Diagram 35
4.8 ER Diagram 36
4.9 Class Diagram 37
4.10 Component Diagram 38
4.11 Deployment Diagram 39
4.12 State Machine Diagram 40

SIT, Department of Computer Engineering 2021-2022 9

 LIST OF TABLES

TABLE ILLUSTRATION PAGE NO.

4.1 Project Plan 29

3.1 Packet Information 47
3.2 Network Error 48
3.3 IP Configuration 48

SIT, Department of Computer Engineering 2021-2022 10

 CHAPTER 1

INTRODUCTION

SIT, Department of Computer Engineering 2021-2022 11

INTRODUCTION

Wildfires are a major contributor to climate change. Fires that are out of reach and serious in
nature can threaten natural structures, people, and land. In today's environment, the ability to
predict wildfires early in more severe climatic circumstances, reduce their impact on strategic
assets, and maximize the time available to warn firefighting authorities and the general public
of impending fire activity is vital. Forest fires, sometimes known as wildfires, are
uncontrolled fires that burn uncontrollably in remote locations, wreaking havoc on natural
and human resources. Large, repeated fires, paired with poor post-fire management practices,
have disastrous implications for the natural environment as well as human populations. Early
detection of wildfires aids in forest conservation and reduces the amount of burned
vegetation.

SIT, Department of Computer Engineering 2021-2022 12

1.1. OVERVIEW

One of the most difficult aspects of successful handling and control of. The emergency
reaction to wildfires is a quick response. teams. The difference between success and failure
can be determined by the quickness with which you respond a fire that has gotten out of hand
or has been put out quickly. Recognizing the need in a fire-prone area of Central America at
Western Arkansas University, a multidisciplinary group of students Faculty and students
collaborated on a project to design and develop a system for detecting wildfires with remote
capabilities data transmission and monitoring Aside from the sensing.

1.2. MOTIVATION

One area of computer vision is image recognition. It is the task of identifying one or more
items in a photograph. Image classification, object identification, and image segmentation are
the most common sub-categories of this topic. Image classification is the process of assigning
one of a set of predetermined class labels to an entire image. This assumes that each image
provided contains only one dominant object. Object detection is a type of picture
categorization that has been generalized. An arbitrary number of objects must be identified in
the shown photos. This also entails locating each object in the image.

1.3 PROBLEM DEFINITION AND OBJECTIVE:

The primary aim of this work was to establish a way to secure small areas of interest
proactively: isolated households, small villages, campsites, music festivals, etc. The
suggested solution was tested by experiments with real fire.
 The project's goal is to use an algorithm that can help predict forest fires in their early stages.
 Using simple and inexpensive system create a forest fire detection system.
 To decrease the likelihood of false detection
 To create a system that is both energy and performance efficient in a distributed context.

SIT, Department of Computer Engineering 2021-2022 13

1.4 PROJECT SCOPE AND LIMITATIONS:

This project has a bright future ahead of it. Furthermore, significant research in this sector is
required in the next years. Our project can be expanded in the future to include discovering an
efficient method of determining the fire's location, gravity, spread direction, burned area, and
other factors. The procedure of simulating a forest fire in our experiment was accomplished
by burning the dry leaves directly. We might be able to come up with techniques to make this
simulation more realistic. Furthermore, in order to generate a model for prediction, we might
integrate region-specific meteorological data in the dataset. The nodes can be upgraded by
making them more efficient so that they have a longer sensing range and are more robust to
the harsh environment.

1.5 METHODOLOGY:

The proposed methodology is divided into steps in this paper. A. Dataset acquisition, B. Data
preprocessing, C. Feature extraction, D. Model construction, and E. Validation and testing are
the steps.

A. Dataset Acquisition

Data is in the form of video frames gathered from CCTV footage, although custom-made
films will be used for training and testing for simplicity of use. Collecting such recordings
with fire is a time-consuming operation. After that, the frames with and without fire are kept
separately. The dataset is then split into two parts: a training set and a test set. This should be
done with caution since if the data provided to the neural network is incorrect, the results will
be skewed and the system will fail to produce reliable findings.

B. Preprocessing of data

The next step in creating a good machine learning model is data preprocessing. The data is
cleaned and processed here, or simply made fit for usage. Noise and other undesired elements

SIT, Department of Computer Engineering 2021-2022 14

 are removed from the frame during data preprocessing. If the algorithm does not require
relevant data, it may produce unfavorable results.

C. Extraction of Characteristics

To effectively identify fire, the neural network must first learn the characteristics of fire
and how it appears in a computer's vision. The human eye can easily recognize the feature of
fire. Fire emits a reddish color and takes on varied shapes and motions depending on the fuel
it consumes. The shape, color, and mobility of fire and smoke are employed to detect them in
this study. The features are extracted from various frames in the training set. The feature
extraction network in the CNN, which is powered by a bespoke algorithm, extracts these
features for the neural network. These video frames are sorted into fire and non-fire
conditions after the features are extracted.

D. Model construction

After that, the retrieved characteristics are sent into the network, which creates a model.
This model is a set of thresholds that helps the network detect fire accurately. The model
learns from the extracted features and establishes a baseline for interpreting incoming input
data.

E. Validation and testing are the last two steps in the validation process.

Validation of the machine learning model is critical since it is critical to obtain accuracy
and determine whether the system is operational. The validation phase is carried out with a
different set of video frames that are completely different from the dataset used to create the
model. The system obtained roughly 98 percent accuracy with the validation set, according to
the test findings.

SIT, Department of Computer Engineering 2021-2022 15

 CHAPTER 2

LITERATURE REVIEW
SR.NO TITTLE AUTHOR DESCRIPTION
1 Integrated Forest George Georgiades, The presence of ferror
Monitoring System for Xanthi S. contributes to a rise in the
Early Fire Detection and Papageorgiou number of false positives (false
Assessment alarms). The proposed system
solves these issues by
combining complementary
thermal and optical cameras
located at a panoramic static
ground position with similar
cameras installed onboard a (or
possibly more) UAS..
2 Low-Cost System for Miguel Antunes, Lu´ıs Fire detection is based on
Early Detection and Miguel Ferreira, human observation, fixed
Deployment of Carlos Viegas optical cameras and aerial
Countermeasures Against surveys. Fire detection is almost
Wild Fires always based on the spectral
anomalies produced by the fires
that are detectable in several
parts of the electromagnetic
SIT, Department of Computer Engineering 2021-2022 16
 spectrum. It is also indicated
that although fires can be
detected using microwave
wavelengths these sensors are
almost never used because of
their high cost and low spati.

SIT, Department of Computer Engineering 2021-2022 17

3 Firebird – Small Satellites Winfried Halle1, Furthermore, the satellites'
for Wild Fire Assessment Sarah Asam2, Erik high agility allows for image
Borg2 acquisition over many days,
which is useful for
monitoring the progress of
active fires. To increase the
reliability of the results
obtained so far, ongoing
changes concentrate on a
more precise assessment of
the background temperatures
next to observed fires.
4 Next Generation Fire Simon Jones ab, Pixels from the non-flaming
Detection from Bryan Hallyab, Karin region in the immediate
Geostationary Satellites Reinke vicinity This method of
determining background
temperature relies on
accurate separation of cloud
and smoke-affected pixels
from true occlusion-free
pixels, as well as the
removal of adjacent fire-
affected pixels and any
necessary adjustments due to
effects like sensor point
spread factor..

SIT, Department of Computer Engineering 2021-2022 18

 CHAPTER 3
SOFTWARE REQUIREMENTS SPECIFICATION

SIT, Department of Computer Engineering 2021-2022 19

3.1INTRODUCTION

3.1.1 PROJECT SCOPE

 plant disease detection strategy would likewise elevate Indian Farmers to do smart
cultivating which sets aside opportunity to time choices which additionally spare time and
lessen loss of leaf because of diseases. This research can be extended to increase the accuracy
using soft computing technique and validate with a greater number of samples.
 The proposed method focuses on deep learning to further improve upon the image classify
using CNN algorithm. Experiments are conducted on the plant leaf dataset. This research can
be extended to increase the accuracy using soft computing technique and validate with more
number of sample.

3.1.2 USE CLASSES AND CHARACTERISTICS

Our system is divided into two class/modules:
1) user
2) system

3.1.3 ASSUMPTIONS AND DEPENDENCIES

1. User must have the knowledge of web-based application.
2. User must have the knowledge of English.
3. User must have all required software to run the application.

SIT, Department of Computer Engineering 2021-2022 20

 3.2MATHEMATICAL MODELING

Fig. 1 mathematical modeling

Where,
Q = User entered input
CB = preprocess
C= feature selection
PR= Preprocess request evaluation
UB = predict outcome
Set Theory:
1) Let S be as system which input image
S = {In, P, Op,Φ }
2) Identify Input In as
In = {Q}
Where,
Q = User entered input image(dataset)
Identify Process P as
P = {CB, C, PR}
Where,
CB = System check entered list is for fire detection
C = Fire prediction
PR = Preprocess request

SIT, Department of Computer Engineering 2021-2022 21

 4) Identify Output Op as
Op = {UB}
Where,
UB = Update Result
Φ =Failures and Success conditions.

Failures:
1. Huge database can lead to more time consumption to get the information.
2. Hardware failure.
3. Software failure.

Success:
1. Search the required information from available in Datasets.
2. User gets result very fast according to their needs.

Space Complexity:
The space complexity depends on Presentation and visualization of discovered patterns. More
the storage of data more is the space complexity.

Time Complexity:
Check No. of patterns available in the datasets= n
If (n>1) then retrieving of information can be time consuming. So the time complexity of this
algorithm is O( n n ).

SIT, Department of Computer Engineering 2021-2022 22

 3.3FUNCTIONAL REQUIRMENTS

 It should be able to detect leaf.

 It should be able to detect presence of intruder.
 Performance of the functions and every module must be well. The overall performance of
the software will enable the users to work efficiently.
 The application is designed in modules where errors can be detected and fixed easily. This
makes it easier to install and update new functionality if required.
 User information can only view by user himself/herself.

3.4EXTERNAL INTERFACE REQUIREMENTS

3.4.1 USER INTERFACES

The requirements section of hardware includes minimum of 180 GB hard disk and 4 GB
RAM with 2 GHz or higher speed. The primary requirements include a memory of 4GB for
the Android Application development and MySQL

3.4.2 HARDWARE INTERFACES

As this is an online application for product management we are not enabling or installing any
hardware components for user interface. It’s not an embedded system.
 Processor - Pentium IV 2.4 GHZ
 Speed - 1.5 Ghz and Above
 RAM - 4 GB (min)
 Hard Disk - 220 GB
 Key Board - Standard Windows Keyboard
 Mouse - Two or Three Button Mouse

SIT, Department of Computer Engineering 2021-2022 23

 3.4.3 SOFTWARE INTERFACES

This is the software configuration in which the project was shaped. The programming
language used, tools used, etc are described here.

 Operating System : Windows

 Front End : html,css,boostrap,javascript
 Tool : Sublimetext3,pycharm
 Database : MySQL

3.4.4 COMMUNICATION INTERFACES

 User can access the web application from remote location.

 Standard internet connection is required.
 TCP/UDP connection will be required.

3.5NON-FUNCTIONAL REQUIREMENTS

3.5.1 PERFORMANCE REQUIREMENTS

 High Speed:

System should process requested task in parallel for various action to give quick response.
Then system must wait for process completion.

 Accuracy:

System should correctly execute process, display the result accurately. System output should
SIT, Department of Computer Engineering 2021-2022 24
 be in user required format.

1. SAFETY REQUIREMENTS

The data safety must be ensured by arranging for a secure and reliable transmission media.
The source and destination information must be entered correctly to avoid any misuse or
malfunctioning. Password generated by user is consisting of characters, special character &
number so that password is difficult to hack. So, that user account is safe.

2. SECURITY REQUIREMENTS
Secure access of confidential data (user’s details).
 Information security means protecting information and information systems from
unauthorized access, use, disclosure, disruption, modification or destruction.
 The terms information security, computer security and information assurance are frequently
incorrectly used interchangeably. These fields are interrelated often and share the common
goals of protecting the confidentiality, integrity and availability of information; however,
there are some subtle differences between them.
 User password must be stored in encrypted form for the security reason
 All the user details shall be accessible to only high authority persons.
 Access will be controlled with usernames and passwords.

3.5.2 SOFTWARE QUALITY ASSURANCE

 Availability [related to Reliability]
 Modifiability [includes portability, reusability, scalability]
 Performance
 Security

SIT, Department of Computer Engineering 2021-2022 25

 Testability
 Usability [includes self-adaptability and user adaptability]

3.6SYSTEM REQUIREMENTS

3.6.1 DATABASE REQUIREMENTS

MySQL : MySQL is an open-source relational database management system (RDBMS). Its

name is a combination of "My", the name of co-founder Michael Widenius's daughter, and
"SQL", the abbreviation for Structured Query Language.
MySQL is free and open-source software under the terms of the GNU General Public

License and is also available under a variety of proprietary licenses. MySQL was owned and
sponsored by the Swedish company MySQL AB, which was bought by Sun Microsystems
(now Oracle Corporation). In 2010, when Oracle acquired Sun, Widenius forked the open-
source MySQL project to create MariaDB.
MySQL is a component of the LAMP web application software stack (and others), which is
an acronym for Linux, Apache, MySQL, Perl/PHP/Python. MySQL is used by many
database-driven web applications, including Drupal, Joomla, phpBB, and WordPress. MySQL
is also used by many popular websites, including Facebook, Flickr, MediaWiki, Twitter, and
YouTube.

3.6.2 SOFTWARE REQUIREMENTS

Operating system : Windows 7 and above.

Coding Language : Python,
IDE : Sublimetext3 Pycharm

SIT, Department of Computer Engineering 2021-2022 26

3.6.3 HARDWARE REQUIREMENTS

System :         Intel I3 Processor and above.

Hard Disk           : 200 GB.
Monitor : 15 VGA Color.
Ram : 4 GB.
Mobile : ANDROID

3.7ANALYSIS MODELS : SDLC MODEL TO BE APPLIED

SIT, Department of Computer Engineering 2021-2022 27

3.8 SYSTEM IMPLEMENTION PLAN

3.8.1 Requirement gathering and analysis:

In this step of water-fall we identify what are various requirements are need for our project
such are software and hardware required, database, and interfaces.

3.8.2 System Design:

In this system design phase we design the system which is easily understood for end user i.e.
user friendly. We design some UML diagrams and data flow diagram to understand the
system flow and system module and sequence of execution.

3.8.3 Implementation:
In implementation phase of our project we have implemented various module required of
successfully getting expected outcome at the different module levels.
With inputs from system design, the system is first developed in small programs called units,
which are integrated in the next phase. Each unit is developed and tested for its functionality
which is referred to as Unit Testing.

3.8.4 Testing:
The different test cases are performed to test whether the project module are giving expected
outcome in assumed time.All the units developed in the implementation phase are integrated
into a system after testing of each unit. Post integration the entire system is tested for any
faults and failures.

3.8.5 Deployment of System:

Once the functional and nonfunctional testing is done, the product is deployed in the customer
environment or released into the market.

SIT, Department of Computer Engineering 2021-2022 28

3.8.6 Maintenance:
There are some issues which come up in the client environment. To fix those issues patches
are released. Also to enhance the product some better versions are released. Maintenance is
done to deliver these changes in the customer environment.All these phases are cascaded to
each other in which progress is seen as flowing steadily downwards like a waterfall through
the phases. The next phase is started only after the defined set of goals are achieved for
previous phase and it is signed off, so the name "Waterfall Model". In this model phases do
not overlap.

SIT, Department of Computer Engineering 2021-2022 29

 CHAPTER 4

SYSTEM DESIGN

SIT, Department of Computer Engineering 2021-2022 30

4.1SYSTEM ARCHITECTURE

SIT, Department of Computer Engineering 2021-2022 31

4.2DATA FLOW DIAGRAMS

DFD level 0

SIT, Department of Computer Engineering 2021-2022 32

DFD level 1

SIT, Department of Computer Engineering 2021-2022 33

SIT, Department of Computer Engineering 2021-2022 34
DFD level 2

SIT, Department of Computer Engineering 2021-2022 35

4.3ENTITY RELATIONSHIP DIAGRAMS

SIT, Department of Computer Engineering 2021-2022 36

4.4UML DIAGRAM

USECASE DIAGRAM

SIT, Department of Computer Engineering 2021-2022 37

SEQUENCE DIAGRAM

SIT, Department of Computer Engineering 2021-2022 38

COLLABORATIVE DIAGRAM

SIT, Department of Computer Engineering 2021-2022 39

DEPLOYMENT DIAGRAM

SIT, Department of Computer Engineering 2021-2022 40

COMPONENT DIAGRAM

SIT, Department of Computer Engineering 2021-2022 41

CLASS DIAGRAM

SIT, Department of Computer Engineering 2021-2022 42

STATE CHART DIAGRAM

SIT, Department of Computer Engineering 2021-2022 43

ACTIVITY DIAGRAM

SIT, Department of Computer Engineering 2021-2022 44

 CHAPTER 5

PROJECT PLAN

SIT, Department of Computer Engineering 2021-2022 45

5.1 PROJECT ESTIMATES

Analysis Models: SDLC Model to be applied

 Requirement gathering and analysis:

In this step of water-fall we identify what are various requirements are need for our project
such are software and hardware required, database, and interfaces, first of all collect on line
all paper and analysis the all paper

 System Design:

In this system design phase we design the system which is easily understood for end user. i.e.
user friendly. We design some UML diagrams and data flow diagram to understand the
system flow and system module and sequence of execution. System design in which that
design the all web pages for example that login, registration, forget-password, contact, etc.

SIT, Department of Computer Engineering 2021-2022 46

 Implementation:

In implementation phase of our project we have implemented various module required of

successfully getting expected outcome at the different module levels. With inputs from
system design, the system is first developed in small programs called units, which are
integrated in the next phase. Each unit is developed and tested for its functionality which is
referred to as Unit Testing.

 Testing

The different test cases are performed to test whether the project modules are giving expected
outcome in assumed time. All the units developed in the implementation phase are integrated
into a system after testing of each unit. Post integration the entire system is tested for any
faults and failures.

 Deployment of System

Once the functional and non-functional testing is done, the product is deployed in the
customer environment or released into the market.

 Maintenance

There are some issues which come up in the client environment. To fix those issues patches
are released. Also, to enhance the product some better versions are released. Maintenance is
done to deliver these changes in the customer environment.
All these phases are cascaded to each other in which progress is seen as flowing steadily
downwards like a waterfall through the phases. The next phase is started only after the
defined set of goals are achieved for previous phase and it is signed off, so the name
“Waterfall Model”. In this model phases do not overlap.

SIT, Department of Computer Engineering 2021-2022 47

5.1.1 Reconciled Estimates

The project cost can be found using any one of the models. COCOMO-1Model
COCOMO-2Model

Cost Estimate

1. Model 1: The basic COCOMO model computes software development efforts as a function of
program sized expressed in estimated lines of code.
2. Model-2: The intermediate COCOMO model computes software development ef-forts as a
function of program size and a set of cost drivers that include subjective assessment of the
product, hardware, personnel, project attributes.
3. Model-3: The advanced COCOMO model incorporates all characteristics of the
intermediate version with an assessment of the cost drivers impact one each step of the
software engineering process. Following is the basic COCOMO-2 model.

The basic COCOMO-2 model equations take form: E=A(b)KLOCB(b) D=C(b)ED(b)

Where E is the effort applied in person months. Di development time in chrono-logical
month. KLOC is estimated number of delivered lines of code for the project. This project
can be classified as Semidetached software project. The rough estimate of number of
lines of this project is 9.072k. Applying the above formula E=3.0*(9.072)1.22 = 44.20
person- months
D=2.5*44.35 =9.40months
Hence according COCOMO-2 model the time required for completion of the project is
9(9.40) months.
Cost of Project: Equation for calculation of cost of project using COCOMO - 2 model is:
C=D*Cp
Where, C=Cost of project
D=Duration in month
Cp=Cost incurred per person-month,

SIT, Department of Computer Engineering 2021-2022 48

 Cp=Rs.5000/- (per person-month) (approx.)
C=9*5000=45000/-
Hence, according COCOMO-2 model the cost of project is 45000/-(approx.)

Time Estimates

The time estimate of this project is approximate 11 months.

5.1 Project Resources

Well configured Laptop, sublimetext3,2GHZCPUspeed,2GBRAM, Internet connection.

5.2 RISK MANAGEMENT W.R.T. NP HARD ANALYSIS

1. Inappropriate dataset- To overcome this risk we are trying to use well organized and complete
dataset.
2. Security-
Toovercomeandimprovingsecurityweusemultilevelsecuritylikeaccesspermissionsofuser

5.2.1 Risk Identification

For risks identification, review of scope document, requirements specifications and

schedule is done. Answers to questionnaire revealed some risks. Each risk is categorized as
per the categories mentioned in [?]. Please refer table 1 for all the risks. You can referred
following risk identification questionnaire

SIT, Department of Computer Engineering 2021-2022 49

1. Have top software and customer managers formally committed to support the project?
Ans: Not applicable.

2. Are end users enthusiastically committed to the project and the system/product to be
built?
Ans-Not known at this time.

3. Are requirements fully understood by the software engineering team and its customers?
Ans-Yes

4. Have customers been involved fully in the definition of requirements?

Ans- Not applicable

5. Do end-users have realistic expectations?

Ans- Not applicable

6. Does the software engineering team have the right mix of skills?
Ans- Not applicable

7. Are project requirements stable?

Ans- Not applicable

8. Is the number of people on the project team adequate to do the job?

Ans- Not applicable
SIT, Department of Computer Engineering 2021-2022 50
 9 . Do all customer/user constituencies agree on the importance of the project and on the
requirements for the system/product to be built?
Ans- Not applicable

5.2.2 Risk Analysis

The risks for the Project can be analyzed within the constraints of time and quality

ID Risk Description Probability Impact

Schedule Quality Overall

1 Description1 Low Low High High

2 Description2 Low Low High High

Table1: Risk Table

Probability Value Description

High Probability of occurrence is >75%

Medium Probability of occurrence is 26−75%

Low Probability of occurrence is <25%

Table2: Risk Probability definitions[?]

SIT, Department of Computer Engineering 2021-2022 51

5.2.3. Overview of Risk Mitigation, Monitoring, Management

Following are the details for each risk

Risk ID 1

Risk Description Description1

Category Development Environment.

Source Software requirement Specification document.

Probability Low

Impact High

Response Mitigate

Strategy Strategy

Risk Status Occurred

Risk ID 2

Risk Description Description2

Category Requirements

Source Software Design Specification documentation review.

Probability Low

Impact High
SIT, Department of Computer Engineering 2021-2022 52
Response Mitigate

Strategy Better testing will resolve this issue.

Risk Status Identified

Risk ID 3

Risk Description3
Description

Category Technology

Source This was identified during early development and testing.

Probability Low

Impact Very High

Response Accept

Strategy Example Running Service Registry behind proxy

balancer

Risk Status Identified

SIT, Department of Computer Engineering 2021-2022 53

5.3 PROJECT SCHEDULE

5.3.1Projecttaskset

Major Tasks in the Project stages are:

5.3.1 Task1: Correctness

5.3.2 Task2: Availability

5.3.3 Task3: Integrity

5.3.2. Task network

Project tasks and the ir dependencies are noted in this diagrammatic form.

Figure11 : A Task Networks

SIT, Department of Computer Engineering 2021-2022 54

 5.3.3. Timeline Chart

5.4.TeamOrganization
 T:1Searchingforprojecttopic.

 T:2Submittingsynopsison3topicsforproject.

 T:3Enquiringaboutdifferentaspectsfortopicselection.

 T:4Literaturesurvey:Papersurvey.

 T:5Literaturesurvey.

 T:6Studyofsystemarchitecture.

 T:7 Study of UML-Use case diagram.

 T:8 Study of UML-Activity Diagram

 9T:9 Study of UML-Class diagram.

 T:10 Study of Data Flow Diagram.

 T:11 Studying for creating a first module.

 T:12 Creating a first module with testcases.

 T:13 Finalizing a first module with testcases.

 T:14 Recovering error of database.

 T:15 Presentation on phase I of project.

 T:16 Studying for creating a second module.

 T:17 Finalizing a second module with testcases.

 T:18 Studying and preparing a GUI for second module.

 T:19 Checking a solution for data duplication problem.

SIT, Department of Computer Engineering 2021-2022 55

  T:20 Removing of data duplication problem

 T:21 Implement update option.

 .T:22 Adding already registered link to patient register.

 T:23 Demonstration of one attribute per columns lining module.

5.4. MANAGEMENT REPORTING AND

COMMUNICATION
Well planning mechanisms are used for progress reporting and inter/intra team
communication are identified as per requirements of the project.

SIT, Department of Computer Engineering 2021-2022 56

 CHAPTER 6

PROJECT IMPLEMENTATION

SIT, Department of Computer Engineering 2021-2022 57

6.1. OVERVIEW OF PROJECT MODULES
This system, while fully functioning, .News outlets are used to gather real-time
information, which is then fed into the system. To interpret the news and move it on
for further analysis, the Python News Analyzer Package is used. Stemming is the
next step, in which the terms are reduced to the ir source, known as lemma. The aim
of this step is to obtain the key words that the Keyword Extractor will extract.

6.2. TOOLS AND TECHNOLOGIES USED

1. Technology: python.
2. Front End Design: HTML5, CSS3, Bootstrap, JavaScript.
3. Database: MySql

6.3. ALGORITHM
CNN

Despite the fact that there have been numerous papers on wildfire smoke detection algorithms, there
have been no attempts to apply deep learning approaches to the topic. CNNs are a specialized kind of
artificial neural networks built exclusively for vision tasks, based on biological inspiration. Artificial
neural networks (ANNs) are a type of mathematical model that can be developed to represent virtually
any mathematical function. [63] CNNs, as offspring of artificial neural networks, are deep learning
algorithms that can learn complex representations from enormous amounts of visual data in the same
way. The term "deep" refers to the models' hierarchical architecture, in which less complex features are
extracted at stages closer to the input and then combined to generate increasingly sophisticated
representations.

SIT, Department of Computer Engineering 2021-2022 58

 CHAPTER 7

SOFTWARE TESTING

SIT, Department of Computer Engineering 2021-2022 59

7.1 TYPE OF TESTING USED

1. Unit Testing Unit testing concentrates verification on the smallest element of the
program – the module. Using the detailed design description important control paths
are tested to establish errors within the bounds of the module. In this system each
submodule is tested individually as per the unit testing such as campaign, lead,
contacted care tested individually. The ir input field validations are tested.
2. Integration testing Once all the individual units have been tested there is a need to
test how they were put together to ensure no data is lost across interface, one module
does not have an adverse impact on another and a function is not executed correctly.
3. Functional Testing Functional testing is the testing to ensure that the specified
functionality required in the system requirements works. It falls under the class of
black box testing.
4. System Testing System testing is the testing to ensure that by putting the software in
different environments (e.g., Operating Systems) it still works. System testing is
done with full system implementation and environment. It falls under the class of
black box testing.
5. Stress Testing Stress testing is the testing to evaluate how system behaves under
unfavorable conditions. Testing is conducted at beyond limits of the specifications. It
falls under the class of black box testing.
6. Performance Testing Performance testing is the testing to assess the speed and
effectiveness of the system and to make sure it is generating results within a
specified time as in performance requirements. It falls under the class of black box
testing.
7. Usability Testing Usability testing is performed to the perspective of the client, to
evaluate how the GUI is user friendly? How easily can the client learn? After
learning how to use, how proficiently can the client perform? How pleasing is it
to use its design? This falls under the class of black box testing.

SIT, Department of Computer Engineering 2021-2022 60

 8. Acceptance Testing Acceptance testing is often done by the customer to ensure
that the delivered product meets the requirements and works as the customer
expected.It falls under the class of black box testing. After unit testing each
and every submodule is tested with integrating each other.

System testing for the current system: In this level of testing we are testing the sys-tem as
a whole after integrating all the main modules of the project. We are testing whether
system is giving correct output or not. All the modules were integrated and the flow of
information among different modules was checked. It was also checked that whether the
flow of data is as per the requirements or not. It was also checked that whether any
particular module is non-functioning or not i.e. once the integration is over each and
every module is functioning in its entirely or not.
In this level of testing we tested the following:-
1. Whether all the forms are properly working or not.
2. Whether all the forms are properly linked or not.
3. Whether all the images are properly displayed or not.
4. Whether data retrieval is proper or not.

7.2 TEST CASES AND TEST RESULTS

Specific knowledge of the application’s code/internal structure and programming

knowledge in general is not required .The tester is aware of what the software is
supposed to do but is not aware of how it does it. For instance, the tester is aware
that a particular input returns a certain, invariable output but is not aware of how the
software produces the output in the first place .Test Cases.
Test cases are built around specification sand requirements ,i.e. what the application is
supposed to do .Test cases are generally derived from external descriptions of the
software, including specifications, requirements and design parameters .Although the
tests used are primarily functional in nature, non-functional tests may also be used. The
test designer selects both valid and invalid inputs and determines the correct output
without any knowledge of the test object’s internal structure.
Test Design Techniques

SIT, Department of Computer Engineering 2021-2022 61

 Typical black-box test design techniques include:

 Decision table testing

 All-pairs testing

 State transition Analysis

 Equivalence partitioning

 Boundary value analysis

 Cause–effect graph

 Error guessing

Advantages

 Efficient when use don large systems.

 Since the tester and developer are independent of each other, testing is balanced
and un prejudiced.
 Tester can be non-technical.
 There is no need for the tester to have detailed functional knowledge of system.
 Tests will be done from an end user’s point of view, because the end user
should accept the system. (This testing technique is sometimes

 Also called Acceptance testing.)

 Testing helps to identify vagueness and contradictions in functional specifications

 Test cases can be designed as soon as the functional specifications are complete.

Disadvantages

 Testcasesarechallengingtodesignwithouthavingclearfunctionalspecifications.

 It is difficult to identify tricky inputs if the test cases are not developed based on
specifications.
 It is difficult to identify all possible inputs in limited testing time. As a result,
writing test cares maybe slow and difficult.
 There are chances of having unidentified paths during the testing process.
 There is a high probability of repeating tests already performed by the programmer
SIT, Department of Computer Engineering 2021-2022 62
 CHAPTER 8

RESULTS

SIT, Department of Computer Engineering 2021-2022 63

8.1 Screenshot:

Result:login

SIT, Department of Computer Engineering 2021-2022 64

SIT, Department of Computer Engineering 2021-2022 65
SIT, Department of Computer Engineering 2021-2022 66
SIT, Department of Computer Engineering 2021-2022 67
SIT, Department of Computer Engineering 2021-2022 68
 CHAPTER 9

OTHER SPECIFICATION

SIT, Department of Computer Engineering 2021-2022 69

ADVANTAGES:
Monitoring possible danger areas and early detection of fire can dramatically minimise
reaction times, as well as the potential for damage and firefighting costs.

LIMITATIONS :

When the pixel values in the fire  images are very near to those in the backdrop, the proposed
approach may make mistakes early on. This is a difficulty that our method has primarily when
the weather is cloudy. We are currently testing with datasets containing images which consist
of RGB images from more complex land coverings, in order to overcome this difficulty. In
our research, dataset photographs play an important role in detecting fire scenes.

APPLICATIONS :

Early identification of fires can save countless lives while also protecting properties from
irreversible infrastructure damage and financial losses. In congested metropolitan settings,
detection by local monitoring is both required and effective for achieving high accuracy and
robustness. Traditional opto-electronic fire detection systems have a number of drawbacks,
including the need for many, frequently redundant systems, faulty hardware, frequent
maintenance, false alarms, and so on. It is also impossible to use sensors in hot, dusty
industrial environments. As a result, detecting fires via surveillance video stream is one of the
most feasible and cost-effective solutions for replacing old systems without requiring massive
infrastructure installations or investments.

SIT, Department of Computer Engineering 2021-2022 70

9.2.CONCLUSION AND FUTURE WORK

CONCLUSION:

In this research, we suggest using CNNs based on deep learning to detect wildfires using
camera photos. Wildfires are a tremendous problem, and early detection and response are
critical to preserving human and natural resource health and safety. This research improves on
a previously proposed wildfire detection system and aims to find a CNN framework that
provides the maximum wildfire detection accuracy while minimising computing cost.
Because the tested algorithm will be implemented on a prototype wildfire detection system,
this part of the project is critical. The researchers discovered a wildfire image collection on
kaggle that saved them a lot of time that would have otherwise been spent collecting and
manually annotating the images.

FUTURE WORK:

The use of video frames for fire detection using machine learning is both difficult and unique.
Surveillance systems can be used to avoid damage and loss from random fire incidents
provided they have a low error rate and can be used on a large scale, such as in significant
industries, households, and forests. The proposed system can be upgraded to a more advanced
system by combining wireless sensors with CCTV for increased security and precision. In
terms of adapting to varied surroundings, the algorithm has a lot of potential.

SIT, Department of Computer Engineering 2021-2022 71

 Appendix A:

Risk Management w.r.t. NP Hard analysis

Risk is inevitable in a business organization when undertaking projects. However, the project
manager needs to ensure that risks are kept to a minimal. Risks can be mainly divided
between two types, negative impact risk and positive impact risk. Not all the time would
project managers be facing negative impact risks as there are positive impact risks too. Once
the risk has been identified, project managers need to come up with a mitigation plan or any
other solution to counter attack the risk.

What is P?

P is set of all decision problems which can be solved in polynomial time by a deterministic.
Since it can be solved in polynomial time, it can be verified in polynomial time.
Therefore P is a subset of NP.

P:
Handling of large data and deploying data on cloud by VMs.

SIT, Department of Computer Engineering 2021-2022 72

What is NP?

"NP" means "we can solve it in polynomial time if we can break the normal rules of step-by-
step computing".

What is NP Hard?

A problem is NP-hard if an algorithm for solving it can be translated into one for solving any
NP-problem (nondeterministic polynomial time) problem. NP-hard therefore means "at least
as hard as any NP-problem," although it might, in fact, be harder.

Risk Identification

Any unauthorized user should be prevented from accessing the system. Password
authentication can be introduced. To ensure the safety of the system, perform regular
monitoring of the system so as to trace the proper working of the system. An internal staff has
to be trained to ensure the safety of the system. He has to be trained to handle extreme error
cases.

Risk Analysis

Risks can be evaluated based on quantity. Project managers need to analyze the likely
chances of a risk occurring with the help of a matrix.

SIT, Department of Computer Engineering 2021-2022 73

 Using the matrix, the project manager can categorize the risk into four categories as Low,
Medium, High and Critical. The probability of occurrence and the impact on the project are
the two parameters used for placing the risk in the matrix categories. As an example, if a risk
occurrence is low (probability = 2) and it has the highest impact (impact = 4), the risk can be
categorized as 'High'.

Overview of Risk Mitigation, Monitoring, Management

Risk Response
When it comes to risk management, it depends on the project manager to choose strategies
that will reduce the risk to minimal. Project managers can choose between the four risk
response strategies, which are outlined below.
 Risks can be avoided
 Pass on the risk
 Take corrective measures to reduce the impact of risks
 Acknowledge the risk
Risk Monitoring and Control
Risks can be monitored on a continuous basis to check if any change is made. New risks can
be identified through the constant monitoring and assessing mechanisms.
Risk Management Process
Following are the considerations when it comes to risk management process:
 Each person involved in the process of planning needs to identify and understand the risks
pertaining to the project.
SIT, Department of Computer Engineering 2021-2022 74
 Once the team members have given their list of risks, the risks should be consolidated to a
single list in order to remove the duplications.

 Assessing the probability and impact of the risks involved with the help of a matrix.
 Split the team into subgroups where each group will identify the triggers that lead to project
risks.
 The teams need to come up with a contingency plan whereby to strategically eliminate the
risks involved or identified.
 Plan the risk management process. Each person involved in the project is assigned a risk in
which he/she looks out for any triggers and then finds a suitable solution for it.
Risk Register
Often project managers will compile a document, which outlines the risks involved and the
strategies in place. This document is vital as it provides a huge deal of information.
Risk register will often consists of diagrams to aid the reader as to the types of risks that are
dealt by the organization and the course of action taken. The risk register should be freely
accessible for all the members of the project team.
Project Risk; an Opportunity or a Threat?
As mentioned above, risks contain two sides. It can be either viewed as a negative element or
a positive element. Negative risks can be detrimental factors that can haphazard situations for
a project.
Therefore, these should be curbed once identified. On the other hand, positive risks can bring
about acknowledgements from both the customer and the management. All the risks need to
be addressed by the project manager.

SIT, Department of Computer Engineering 2021-2022 75

 REFERENCES

[1] Departamento de Gesta˜o de A´ reas Pu´blicas e de Protec¸a˜o Florestal, “10.º Relat´orio

Provis´orio de Incˆendios Florestais - 2017,” Instituto da Conservac¸ ˜ao da Natureza e
Florestas, Tech. Rep., 2017, In Portuguese. [Online]. Available:
http://www2:icnf:pt/portal/florestas/dfci/Resource/ doc/rel/2017/10-rel-prov-1jan-31out-
2017:pdf
[2] State of California. Incident Information - Numbers of Fires and Acres. Accessed: 2018-
12-14. [Online]. Available: http://cdfdata:fire:ca:gov/ incidents/incidents stats
[3] B. Leblon, J. San-Miguel-Ayanz, L. Bourgeau-Chavez, and M. Kong, “3 - Remote
Sensing of
Wildfires,” in Land Surface Remote Sensing, N. Baghdadi and M. Zribi, Eds. Elsevier, 2016,
pp. 55 – 95.
[4] A. A. A. Alkhatib, “A Review on Forest Fire Detection Techniques,” International Journal
of Distributed Sensor Networks, vol. 10, no. 3, 2014.
[5] D. M. Doolin and N. Sitar, “Wireless sensors for wildfire monitoring,” vol. 5765, 2005,
pp. 477–484.
[6] IQ FireWatch. Why IQ FireWatch. Accessed: 2018-12-10. [Online]. Available:
https://www:iq-firewatch:com
[7] K. Bouabdellah, H. Noureddine, and S. Larbi, “Using Wireless Sensor Networks for
Reliable Forest Fires Detection,” Procedia Computer Science, vol. 19, pp. 794 – 801, 2013.
2019 IEEE 5th World Forum on Internet of Things (WF-IoT) 422
[8] C. L. Beyler, “A design method for flaming fire detection,” Fire Technology, vol. 20, no.
4, pp. 5–16, Nov 1984.
[9] C. E. Van Wagner, Development and Structure of the Canadian Forest Fire Weather Index
System. Canadian Forestry Service, 1987.
[10] STMicroelectronics, “STM32L432KB STM32L432KC - Ultra-lowpower Arm®
Cortex®-M4 32-bit MCU+FPU, 100DMIPS, up to 256KB Flash, 64KB SRAM, USB FS,
analog, audio,” 2018.

SIT, Department of Computer Engineering 2021-2022 76