Republic of the Philippines

BOHOL ISLAND STATE UNIVERSITY

Calape Campus
San Isidro, Calape, Bohol

FIRE ALARM SYSTEM USING FOREST

FIRE DETECTION ALGORITHM

FRANCIS CABOVERDE
MARY GRACE P. CUSI
SARAH MAE E. PADABOC
ELMIRA HOPE S. RECITAS
BSCS – 3A
 Table of Contents

Page

TITLE PAGE …………………………………………………………… i

TABLE OF CONTENTS …………………………………………………………… ii

LIST OF TABLES …………………………………………………………… iii

Chapter 4 2

Chapter 2 12

2.0 Objectives of the Study

Chapter 3 13

3.0 Methodology

3.1 Design 13

1.0 Introduction ………………………………………………………… 1

1.1 Background of the study ……………………………………………………… 1
1.2 Literature Review ………………………………………………………… 2 Review
of Related Literature ………………………………………………… 2

Review of Related Study ………………………………………………… 4

Legal Basis ………………………………………………… 7
1.3 Significance of the Study ………………………………………………… 9

3.2 Instrument ………………………………………………… 12

Chapter 4

4.0 Results and Discussion ………………………………………………… 13

 4.1 Requirements ………………………………………………… 13
4.2 System Design ………………………………………………… 15
4.3 Algorithm …………………………………………………15
Bibliography ………………………………………………… 17 Chapter
I

1.0 Introduction
1.1 Background of the study
A fire alarm is a unit made of several devices, which uses visual and audio
signalization to warn people about a possible fire smoke, or carbon monoxide
occurrence in the area of coverage. Fire alarms are usually set in fire alarm
systems to provide zonal coverage for residences and commercial buildings. The
warning signal is either a loud siren/bell or a flashing light, or it can include both. A
fire alarm system warns people when smoke, fire, carbon monoxide or other
firerelated emergencies are detected. These alarms may be activated
automatically from smoke detectors and heat detectors or may also be activated
via manual fire alarm activation devices such as manual call points or pull
stations. Alarms can be either motorized bells or wall mountable sounders or
horns. They can also be speaker strobes which sound an alarm, followed by a
voice evacuation message which warns people inside the building not to use the
elevators.

Fire alarm systems are obtainable on company or government buildings,

public and private properties. However, despite of being prepared in having
emergency signals installed, most fire incidences occur when a certain building is
left unattended. Also, when it comes to a simple or average family-owned
household, there is this situation that is repeating and that is the late emergency
response. And for those household which lacking in budget just to have alarms
will have worse outcomes that it could lose lives aside from assets. With that,
occupants which do not have alarm systems cannot be early informed if there
would be fire occurrences within or outside the household especially if the
household owner is not at home. Late emergency alert is one of the common
factors why most fire cases are more than destructive that could lose lives. Some
fire alarm systems use additional warnings, such as sending voice messages or
making a phone call to the management. Inopportunely these warnings are not
yet made known in local residents’ mobile devices but if introduced, it can be
helpful in minimizing late fire alert responses and assist

1
residents to act and call authorized personnel immediately when fire occurs.
Solving this kind of problem will be helpful especially the society so that late
responses during emergencies can be solved quickly.

1.2 Literature Review

Review of Related Literature

According to Western States Fire Protection Co., fire alarm and detection
systems are an essential part of the life safety system for any building. Whether
you have a commercial, residential or industrial facility, it is important that all of
the components of your fire alarm and detection system can work together to
protect the lives of people within the facility. The basic fire alarm system
components are: fire alarm initiating devices, fire notification devices, fire alarm
control panel, primary power supply and backup power supply.

https://www.wsfp.com/blog/what-are-the-basic-components-of-fire-alarmhttps://
www.wsfp.com/blog/what-are-the-basic-components-of-fire-alarm-detection-systems/
detection-systems/

R. Craig Schroll (2007) concluded that fire detection systems are designed to
discover fires early in their development when time will still be available for the
safe evacuation of occupants. Early detection also plays a significant role in
protecting the safety of emergency response personnel. Property loss can be
reduced and downtime for the operation minimized through early detection
because control efforts are started while the fire is still small. Most alarm systems
provide information to emergency responders on the location of the fire, speeding
the process of fire control.
 The most basic alarm system does not include detection. It has manual pull
stations and sounds only a local alarm. This level of system is not what is typically
used; it relies on an occupant to discover the fire, which can cause a significant
delay. The more quickly you want to be notified of the fire, the more costly the
system you must install. Speed of detection is expensive. The slowest system to
detect a fire is a heat detector, which is also the least expensive. An air-aspirating

2
smoke detection system provides the most rapid indication of fire, but these systems are
five to 10 times as expensive.

Smoke detectors are available in a variety of types. Photoelectric smoke

detectors operate based upon light scattering within the detection chamber of the
detector. Light is projected through the chamber and will be scattered if it strikes
smoke. This light, reflected off the smoke in the chamber, is detected by a
photocell.

Ionization smoke detectors (the most common used at home) detect the
particles in smoke. As smoke passes through the chamber, the particles are
ionized. These particles may then be detected by charged plates in the detector.
Smoke detectors are also available in combination with a heat detector. The
beam type detector operates when the beam is interrupted by obscuring smoke
between the laser emitter and receiver. These detectors are most often used in
areas of large open spaces. https://ohsonline.com/Articles/2007/12/Fire-
Detection-and-Alarm-Systems-A-

Brief-Guide.aspx
Mahgoub, Asma, et al. (2019) also concluded that fire alarm systems are
essential in alerting people before fire engulfs their homes. However, fire alarm
systems, today, require a lot of wiring and labor to be installed. This discourages
users from installing them in their homes. Therefore, IoT (internet of things) based
wireless fire alarm system are proposed that is easy to install. The proposed
system is an ad-hoc network that consists of several nodes distributed over the
house. Each of these nodes consists of a microcontroller (ESP8266 node MCU)
connected to smoke, temperature, humidity, flame, Methane and Carbon
Monoxide (CO) sensors that continuously sense the surrounding environment to
detect the presence of fire. The nodes create their own Wi-Fi network. These
nodes communicate with a centralized node implemented with a Raspberry Pi
microcontroller integrated with a 4G module. Once fire is detected by a node, it
sends a signal to a centralized node that is triggered to send an SMS to the fire
department and the user, call the user and alert the house by producing a local
alarm. The user can also get information about the status of his home via sending

3
an SMS to the system. The sensing nodes create a mesh network and they are
linked to the central node via a bridge node. Communication between the bridge
node and the sensing node is through Message Queuing Telemetry Transport
(MQTT) protocol. A prototype was developed for the proposed system and it
carried out the desired functionalities successfully with an average delay of less
than 30 seconds.

https://ieeexplore.ieee.org/abstract/document/8904001
When it comes to cooking, lots of false fire alarms have been experienced,
especially in apartments and in household kitchens. The cooking habits of these
occupants lead to generation of smoke during cooking, and the kitchen fan in the
apartment is not strong enough to take away all the smoke. According to Chen,
Yanghou (2011), The following suggestions are made to this issue.

1. Make sure the kitchen fan is turned on during cooking. Even though the
capacity of the fan is not enough in some cases. Using kitchen still reduce the
false demands significantly.

2. Make sure the bedroom doors are closed. A major false alarm will only be
trigger when at least 2 or more than 2 detectors detect false demand. Closure of
bedroom will reduce the major false alarm to a large extent.
3. Replace the smoke-based fire detector in the kitchen with other types of
detectors. Most experienced false alarm is caused by smoke generated during, if
the detector is not based on smoke, this kind of spurious will be omitted.

https://reader.elsevier.com/reader/sd/pii/S1877705811055792?token=4BCD62B3
8B5106A103C25355290DA588F0FC840529BB946988DC04BE8F501D5860D4
0D22AD95DF90B48EAEA4D3F675CB&originRegion=us -east-
1&originCreation=20220406073930

Review of Related Study

Several fire detection algorithms have been proposed by various researchers. In
the study conducted by Thou-Ho et al. (2004) entitled Forest Fire Detection Using a
Rule-Based Image Processing Algorithm and Temporal

Variation, they presented fire detection algorithm, which combines the saturation

4
channel of the HSV color and the RGB color. This algorithm employs three rules
(R≥G>B), (R≥RT), and (S≥ ((255-R) ST/RT). Determination of the two thresholds
RT and ST is required. The certain values range is from 115 to 135 for RT and
from 55 to 65 for ST based on many investigational results done by the authors.
This method is computationally simple compared to the other algorithms;
however, it suffers from false-positive alarms in case of moving fire-like objects.

Dios et al.’s (2008) study presented an optical model used to detect forest
fires and measure the properties of the fire such as flame height, fire front, fire
base width, and flame inclination angle. This system is very good; nevertheless, it
is very expensive because it consists of infrared cameras and other technologies
such as GPS and telemetry sensors.

In the study conducted by Yinglian et al. (2018) proposed forest fire

disaster prevention algorithm based on image processing. This algorithm depends
on fire and smoke color properties to identify fire. Yinglian’s algorithm is good, but
the smoke spreads quickly and it has many different colors which depend on the
burning material; thus, the false alarm rate rises.
https://www.hindawi.com/journals/mpe/2018/7612487/
To reduce false alarm rates, there are some modern fire alarm systems that are
designed to handle such cases just like Den Breejen et al.’s (1998) research
which states that the autonomous forest fire detection system is capable of
detecting quickly (high temporal resolution) a relatively small smoke plume (high
spatial resolution) with a low false alarm rate. The said system is using the forest
fire detection algorithm. These characteristics meet a demand from the fire
community, and needs to be finalized and tested during operational conditions to
obtain a commercial and operational product. Such systems provide fire
managers with an all-year detection system with fixed cost. Patrolling and
manned watch towers have additional variable cost during to the period these
detection methods are used.

https://www.researchgate.net/profile/KlamerSchutte/publication/2478027_Autono
mous_Forest_Fire_Detection/links/0912f514831a07aee6000000/Autonomous -

Forest-Fire-Detection.pdf
De Zhang et al.’s (2016) research proposed a new way to recognize the
fire using single camera. Flames are processed by using 2 features, one is by
using pixel color detection and other one is by using shape identification with
respect to time. After this it uses the hidden markov model to differentiate flame
flicker from the objects which have same color as the flame. This method uses 6
videos and gives total 97% correct result for fire detection.

Enis Cetin et al.’s (2013) study supported De Zhang et al.’s research

which provides video handling systems for identification and investigation of
uncontrolled fire. We know that human can detect fire easily even from long
distance but machine cannot understand it. Traditional point sensors have
transport delay whereas VFD reduces the recognition time in both inside and
outside on the grounds because cameras can screen "volumes". It is feasible to
cover a zone of 100 km2 with the help of a single tilt-zoom camera set on top of a
peak for wildfire detection. A further advantage of the VFD association is; it
provides significant information about the size and direction of smoke circulation.
This system is used in high-risk areas and in risky buildings. Despite not being
fully automated systems, they are precious utensils for security point of view. The
operator can check whether it is an actual fire or just a fire like image (false alarm)
whenever the VFD system produces an alarm.

According to T Wirayuda et al., (2013) their study focused on detecting fire

based on the intensity of fire after getting image data through video handling
systems by Enis Cetin et al.’s (2013) and De Zhang et al.’s (2016) study. For this,
chromatic rule and color look up tables are used with histogram analysis i.e.,
value of pixel distribution. Histogram reduces the number of false fires which is
used as input intemporal phase. First use color detection method then create Blob
and after this apply histogram analysis using some rules. If fire is detected then
apply temporal analysis.

P.Patel et al., (2012) proposed an approach which combine color, motion,

and area for detecting fire. Firstly, it determines the fire on the bases of color, then
finds whether the pixels are movable or not. If pixels are changing then find the
area of pixels in a frame. This method converts the RGB to YCbCr so that it can

56
recognize luminance and chrominance information separately and then apply

some set of rules. After this motion can be detected by using frame differencing
approach and remove noise with the help of Gaussian filter. At last, find fire pixel

region. https://www.researchgate.net/profile/Parul-Saxena

7/publication/358582321_An_Effective_Approach_For_Forest_Fire_Detection_In
Surveillance_Video_Using_Rule-
Based_And_Temporal_Variations/links/620a3acd87866404a16947bd/An -
Effective-Approach-For-Forest-Fire-Detection-In-Surveillance-Video-Using-Rulehttps://
www.researchgate.net/profile/Parul-Saxena
7/publication/358582321_An_Effective_Approach_For_Forest_Fire_Detection_InSurveilla
nce_Video_Using_Rule-Based_And_Temporal_Variations/links/
620a3acd87866404a16947bd/An-Effective-Approach-For-Forest-Fire-Detection-In-
Surveillance-Video-Using-Rule-Based-And-Temporal-Variations.pdf Based-And-Temporal-
Variations.pdf
 Legal Basis
This study is anchored to Republic Act (RA) No. 9514, otherwise known as
the "Fire Code of the Philippines of 2008,". The researchers created this study as
a result of the importance of implementing of fire alarm systems in the family
household. To develop the study’s security and credibility, the "Fire Code of the
Philippines of 2008," will serve as the basis of this study. The principal law
governing the prevention and suppression of all destructive fires and the
professionalization of the fire service is legalized as a profession.

In Republic Act. 9514 Section 2 which is the Declaration of Policies, it is stated

that:

(a) The government, with the cooperation of the private sector, shall develop
and promulgate sets of standards and regulations taking into consideration the
latest development in fire technology suitable to Philippine conditions;

(b) Fire prevention and fire safety shall be given equal, if not greater emphasis
as the suppression or extinguishment of fires. Fire prevention education shall be
undertaken continuously involving all sectors of the community;

(c) The Fire Service of the Integrated National Police shall endeavor to
respond to all fires before they reach critical and conflagration stages. Towards
this end, the organization, administration and operation of the Fire Service shall
be

7
improved and developed, its personnel and equipment augmented and effective fire
alarm systems set up; and

(d) The Fire Service shall be professionalized. For this purpose, educational
institutions shall endeavor to include in their curricula, courses on fire technology
and fire protection engineering.
 In Republic Act. 9514 Section 4 which is Applicability of the Code, it is
declared that the provisions of the Fire Code shall apply to all persons and all
private and public buildings, facilities or structures erected or constructed before
and after its effectivity.

In Republic Act. 9514 Section 8 which is Inspections, Safety Measures,

Fire Safety, Constructions, and Protective and/or Warning Systems, it is declared
that as may be defined and provided in the Rules and Regulations, owners,
administrators or occupants of buildings, structures and their premises or facilities
and other responsible persons shall be required to comply with the following, as
may be appropriate:

d. Provision on Fire Safety Construction, Protective and Warning System Owners,

occupants or administrator or buildings, structures and their premises or facilities,
except such other buildings or structures as may be exempted in the rules and
regulations to be promulgated under Section 6 hereof, shall incorporate and
provide therein fire safety construction, protective and warning system, and shall
develop and implement fire safety programs, to wit:

(1) Fire protection features such as sprinkler systems, hose boxes, hose reels or
standpipe systems and other firefighting equipment;

(2) Fire Alarm systems;

(3) Fire walls to separate adjoining buildings, or warehouses and storage areas from
other occupancies in the same building;

(4) Provisions for confining the fire at its source such as fire resistive floors and walls
extending up to the next floor slab or roof, curtain boards and other fire containing
or stopping components
To sum up everything that has been stated, the researchers believe that the
Republic Act No. 9514 also known as the "Fire Code of the Philippines of 2008,"
is the most appropriate for the study since it stated the legalized implementation
about fire technology and concerns fire safety of owners or occupants of a
building.

https://www.lawphil.net/statutes/presdecs/pd1977/pd_1185_1977.html
1.3 Significance of the Study
Fire alarm is essential for early detection in every household. Fire can cause
deaths from toxic gases, thick smokes and running out of oxygen. It can happen
anytime in any room of a particular household. No matter where or how, having a
fire alarm is the opening move toward family safety. Researchers knew that
smoke and gases are more fatal than heat that most victims die through
suffocation and not from being burned. Most of the time this incident happens
when a family is at home, sleeping and unaware until there is no time to escape
and to go near safe. Having fire alarm installed at home is considered one of the
best and valuable of having early warning of deadly fire and it could reduce
almost the risk of dying in fire at home.

This study needs an attention in order to change, resolve and improve every
family and household’s safety and also in order for the proposed system to be
known by the public. The researchers will conduct this study in order to be able to
contribute ideas that will benefit the community.

8
 Chapter 2

2.0 Objectives of the Study

The fire alarm system is designed to give an early warning when there is
smoke or fire condition in a building. Researchers want to design a fire alarm
system that all family members can use in single-home residences. It must be
able to detect fires at all locations, residents must be able to activate it from
convenient locations themselves, and it must alert residents in all portions of the
house.

This study is guided by the following objectives:

1. What is the design of the fire alarm system in terms of?

a. Materials
b. Mechanism
c. Procedure
2. What is the mechanism of the proposed system from developer to the end-users?

3. What is the performance of the components used in the proposed system?

a. Smoke sensor MQ2

b. Flame Sensor Features LM393 comparator chip
c. Flame Sensor Features LM393 comparator chip
d. Temperature and Humidity Sensor (DHT22) Sensor Module AM2302
4. What is the program flow design of the proposed fire alarm system?
5. How are the problems and the processes be dealt in implementing fire alarm
system?
 9

Chapter 3

3.0 Methodology

3.1 Design

Developmental research has been defined as the systematic study of

designing, developing, and evaluating instructional programs, processes, and
products that must meet criteria of internal consistency and effectiveness.

According to Klaassen, Kees & Kortland, Koos. (2015). Developmental

research is a particular way of addressing the basic questions of why and how to
teach what to whom. It involves a cyclical process of small-scale in-depth
development and evaluation, at a content-specific level, of exemplary
teachinglearning sequences. It aims to produce an empirically supported
justification of the inner workings of such a sequence, which is claimed to be an
important contribution to the expertise of teachers, curriculum developers, and
educational researchers.

This study will use developmental research design since researchers will
develop fire alarm system that tends to lessen late emergency response cases.
By using developmental design, it supports the entire research gathering
systematically and researchers can come up with ideas for developing and
redesigning the application.
 10

3.2 Instrument

In order to gather data, this study is using guided questions which respondents
will use the application developed by the researchers and assess the application
by answering the questionnaire on system usability and web usability which is the
instrument or research tool for checking the application’s usability and
effectiveness.

The system usability questionnaire is a conduct kind of review adopted from

Lewis, J.R in 1995 consists of 19 questions with a scale from 1-7 interpreted as:
7- The respondent strongly believed in the usability of the system,6- The
respondent believed in the usability of the system,5- The respondent tends to
believe in the usability of the system, 4- The respondent is neutral in trusting that
the system is usable, 3- The respondent tends not to trust that the system is
usable, 2- The respondent believes that the system is not usable, 1- The
respondent strongly believed that the system is not usable.

Whereas, web usability questionnaire is developed by Massachusetts

Institute of Technology consists of 8 parts namely: I. Navigation with 5 questions,
II. Functionality with 3 questions, III. User Control with 5 questions, IV. Language
and Content with 7 questions, V. Online Help and User Guides with 6 questions,
VI. Consistency with 3 questions, VII. Error Prevention and Correction with 7
questions and VIII. Architectural and Visual Clarity with 7 questions with a scale
from 1-5 interpreted as: 5- The respondents strongly believe and confident that
the website is excellent in all aspects in design, development and implementation,
4- The respondents believe and are confident that the system is very usable. They
are also confident that if ever the website may have minor inconsistencies and
aesthetic issues, these are manageable and will not affect the performance of the
proposed system,3- The respondents believe and are confident that the system is
usable. They are also confident that if ever the website may have problems, these
 1112
are non-critical and will not cause major confusion or irritation, 2- The respondents
are neutral in trusting that the website is usable. They also believe that a serious
problem occurring in the website that needs high priority to fix can cause a user to
make a significant error and 1- The respondents believe that the website is not
usable. They also believe that the website has a severe problem.

Chapter 4

4.0 Results and Discussion

4.1 Requirements

An operating system is a software program required to manage and operate a

computing device like smartphones, tablets, computers, supercomputers, web
servers, cars, network towers, smartwatches, etc. It is the operating system that
eliminates the need-to-know coding language to interact with computing devices.
The communication between a user and a system takes place with the help of an
operating systems. Windows, Linux, and Android are examples of operating
systems that enable the user to use programs like MS Office, Notepad, and
games on the computer or mobile phone.

In the purposed solution different sensors that are used include smoke sensor
along with temperature and humidity sensor. The flame sensor is used for
detecting flame. In order to power these sensors and perform operation the
Arduino UNO microcontroller is used. The details and specification for the
mentioned sensors are discussed below:

HARDWARE REQUIREMENTS

▪ Intel Core i3-7020U Processor, 2.3 GHz

▪ 1 TB Hard Drive RAM 4 GB
▪ 1366 × 768-pixel HD Resolution Monitor Screen Keyboard and Mouse
▪ Flame Sensor Features LM393 comparator chip
▪ Program for the Micro Sensors in Arduino IDE
▪ Flame Sensor Features LM393 comparator chip
▪ Arduino UNO Microcontroller based processing circuits
▪ Temperature and Humidity Sensor (DHT22) Sensor Module AM2302
▪ Smoke Sensor MQ2
▪ Lcd display
▪ Power supply

SOFTWARE REQUIREMENTS

▪ Operating System: Windows 10 Operating System

▪ 18-inch desktop
▪ System unit intel core i3 or more ▪ LTE internet connection 65mpbs or above ▪
Platform: Arduino IDE 1.8.19.

▪ Language Used: C language

The software for the system design to be built is a context diagram (a description
of the system designed), called DFD (Data Flow Diagram). The context diagram is
a general explanation of the entities involved. The entities in this system are the
admin, community, and firefighters. The admin will input the data required to
design this system and receive the information contained in the system. The
citizens will receive notifications of fire and smoke leaks. Notification of house
fires will be sent by text message and alarm if there is a fire. The fire team will
receive information on the occurrence of fires and confirm fires in people’s
houses.

DFD (Data Flow Diagram) on the home fire detection system built. In this
perspective, there are three processes, 1.0—process, 2.0—tool checking, and 3.0
—confirmation. The admin aims to input the data needed for the system
configuration to be built and collected on the Arduino system. After the data is
stored on the Arduino system, people only need to check the tools installed at
their houses. The citizens will receive notification of smoke leaks and potential
fires that occur. The last process is when a house fire happens, the Arduino
system will send

114 3
information in the form of an SMS to the fire department, and then it will be confirmed that
the fire incident occurred.

4.2 System Design

4.3 Algorithm
This study is based on the forest fire detection algorithm which refers to a dynamic
multispectral thresholding contextual algorithm that uses the shortwave
"visible" channel (when available during the daytime), middle infrared (3.9 μm),
and longwave infrared (11.2 μm) infrared window bands to locate and
characterize hot spot pixels. The algorithm can be used in parallel with
conventional fire detection systems to reduce false alarms. There are four main
components in the

15
internet of things (IoT) system which the algorithm included and these are sensor
nodes, gateways, Internet servers and end users (for example, firefighters and the
public, etc.). A star network topology is adopted in the connection between the
sensor nodes and the gateways. The algorithm adopts the cluster topology and
hierarchical routing protocols. The nodes members transmit their data to the
cluster head, which will transmit to the base station. Many sensor nodes are
distributed evenly over the forest with distances of 1 kilometer and are connected
to gateways to transmit data to Internet servers. To cover the terrain, a long range
LoRa communication signal modulation is adopted for the sensor nodes. It offers
a wide range of flexibility for the distribution and deployment of sensor nodes.
After collecting the data, the gateways send the data via Internet. The data is then
stored on the Internet server, and is displayed in an online dashboard.

Each sensor node measures at a given frequency, the values of

temperature (T), relative humidity (RH), atmospheric pressure (P), the amount of
carbon monoxide (CO), the amount of carbon dioxide (CO2), the quantity of
Particulate Matter (PM), fine particles. The PM2.5 and PM10 fine particle
diameters are less than 2.5 and 10 μm, respectively. The procedure of the
proposed fire detection algorithm consists of three steps. The first step is to
determine the fire weather index (FWI) from weather data using the weather
station located in the forest. The second step is the most important step of the
study; it consists of the acquisition of data from each sensor node at a frequency
determined according to the danger potential, which is estimated by the
calculation of FWI. The objective of this step is to determine, using the algorithm
and following the metrics of all the sensor nodes at a given time, whether there is
a probability of existence of fires. If this last function recommends the existence of
fire, the algorithm will trigger the third step which consists in launching an
Unmanned Aerial Vehicle (UAV) or drone to measure the values of these sensors
in more detail in a mobile way. In addition, the UAV can embark on an infrared
camera to have a temperature map. All this information received will be sent to
the control tower to trigger all means of extinguishing the fire if necessary.

1166
 Bibliography

Klaassen, Kees & Kortland, Koos. (2015). Developmental Research.

10.1007/97894-007-2150-0_155.

Mahmoud, Mubarak AI, and Honge Ren. "Forest fire detection using a rule-based
image processing algorithm and temporal variation." Mathematical Problems in
Engineering 2018 (2018).

C. Thou-Ho, W. Ping-Hsueh, and C. Yung-Chuen, “An early fire-detection

method based on image processing,” in Proceedings of the 2004 International
Conference on Image Processing, ICIP '04, vol. 3, pp. 1707–1710, 2004.

J. R. Martinez-de Dios, B. C. Arrue, A. Ollero, L. Merino, and F. Gómez-

Rodríguez,
“Computer vision techniques for forest fire perception,” Image and Vision
Computing, vol. 26, no. 4, pp. 550–562, 2008.

Den Breejen, Eric, et al. Autonomous forest fire detection. Coimbra, Portugal:
ADAI-Associacao para o Desenvolvimento da Aerodinamica Industrial, 1998.

Mahgoub, Asma, et al. "IoT-based fire alarm system." 2019 Third World
Conference on Smart Trends in Systems Security and Sustainablity (WorldS4).
IEEE, 2019.

Muheden, Karwan, Ebubekir Erdem, and Sercan Vançin. "Design and

implementation of the mobile fire alarm system using wireless sensor networks."
2016 IEEE 17th International Symposium on Computational Intelligence and
Informatics (CINTI). IEEE, 2016.

Ahmad, Muhammad Baballe, et al. "The Various Types of sensors used in the
Security Alarm system." International Journal of New Computer Architectures
and their Applications (IJNCAA) 9.2 (2019).

17
Chen, Yanghou. "Reliability analysis of a fire alarm system." Procedia
Engineering 24 (2011): 731-736.

Kang, Bo-Seon, and Keun-Ho Lee. "Fire alarm solutions through the
convergence of image processing technology and M2M." Journal of the Korea
Convergence Society 7.1 (2016): 37-42.

Khanna, Vikshant, and Rupinder Kaur Cheema. "Fire detection mechanism using
fuzzy logic." International Journal of Computer Applications 65.12 (2013).

Sekizawa, Ai, and Masayuki Mizuno. "Analysis of response behavior of people in

fire incidents where residential fire alarms successfully worked." Fire and
Materials 41.5 (2017): 441-453.

Reisinger, Keith S. "Smoke detectors: reducing deaths and injuries due to fire."
Pediatrics 65.4 (1980): 718-724.

https://www.ifsta.org/sites/default/files/Chapter14_FICE8.pdf
https://www.wsfp.com/blog/what-are-the-basic-components-of-fire-alarmhttps://
www.wsfp.com/blog/what-are-the-basic-components-of-fire-alarm-detection-
systems/detection-systems/

https://library.ssec.wisc.edu/research_Resources/publications/pdfs/SSECPUBS/
SSEC_Publication_No_10_09_S4.pdf

https://www.researchgate.net/profile/Parul-Saxena-
7/publication/358582321_An_Effective_Approach_For_Forest_Fire_Detection_In
_Surveillance_Video_Using_Rule-
Based_And_Temporal_Variations/links/620a3acd87866404a16947bd/An -
Effective-Approach-For-Forest-Fire-Detection-In-Surveillance-Video-Using-
Rulehttps://www.researchgate.net/profile/Parul-Saxena-7/publication/
358582321_An_Effective_Approach_For_Forest_Fire_Detection_In_Surveillance
_Video_Using_Rule-Based_And_Temporal_Variations/links/
620a3acd87866404a16947bd/An-Effective-Approach-For-Forest-Fire-Detection-

18
In-Surveillance-Video-Using-Rule-Based-And-Temporal-Variations.pdf Based-
And-Temporal-Variations.pdf

https://create.arduino.cc/projecthub/ayanfeoluwaadekanye1/fire -and-
smokehttps://create.arduino.cc/projecthub/ayanfeoluwaadekanye1/fire-and-
smoke-alarm-8fe55b?ref=similar&ref_id=29956&offset=3 alarm-8fe55b?
ref=similar&ref_id=29956&offset=3
https://create.arduino.cc/projecthub/mrmodder/diy -arduino-fire-alarm-system-
athttps://create.arduino.cc/projecthub/mrmodder/diy-arduino-fire-alarm-system-at-
home-c70970home-c70970

https://ohsonline.com/Articles/2007/12/Fire-Detection-and-Alarm-Systems-
Ahttps://ohsonline.com/Articles/2007/12/Fire-Detection-and-Alarm-Systems-A-
Brief-Guide.aspxBrief-Guide.aspx

https://www.sciencedirect.com/topics/earth-and-planetary-sciences/forest-
firehttps://www.sciencedirect.com/topics/earth-and-planetary-sciences/forest-fire-
detectiondetection

19
20