Turkish Journal of Computer and Mathematics Education Vol.12 No.

9 (2021), 152-158
Research Article

Flood Detection and Avoidance System using IoT

Mallangi Surya Prakash Reddy a, N. S. Fizalb, A. Lokeshc, and K. Kishore Kumard

a,b, c
Student, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and
Technology. Avadi, Chennai-600062, Tamil Nadu, India,
dAsst. Professor, Department of Computer science & engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of

Science and Technology. Avadi, Chennai-600062, Tamil Nadu, India,

Article History: Received: 10 January 2021; Revised: 12 February 2021; Accepted: 27 March 2021; Published
online: 20 April 2021
Abstract: Flooding is one of the major disasters across major geographical locations in the world. Due to this disaster majority
of people had lost their livelihood. In recent times we can see the major natural disaster occurred in our country in those disasters
flooding in the major one, due to this natural calamity all over India majority of people have lost their survival and lost their
beloved one's heavy property damage has also occurred. To rectify this major problem, we have developed a solution with the
help of IoT and data sciences. This model is very much useful in monitoring the water level variations in various water resources
like rivers, dams, reservoirs. The sensor technology values are monitored and stored regularly in the cloud server which is
useful to visualize flood and with the help of IFTTT alerts to corresponding authorities like nearby police stations and NSS,
CRPF camp people to take proper action. With the help of data visualizations and the KNN algorithm, we will find the place
where we can place this device. These complete data are going to be updated to our web page we are developing for this project.
In addition to this model, we are again going to use sensors and automatically lift the dam gates. The model was designed and
developed to monitor and control the disaster in this Intelligent system that will control the overall water management.
Subsequently, the system will alert the authorities to reduce the impact that is going to happen when the flood is going to occur.

Keywords: Thingspeak cloud, IFTTT, Internet of things (IoT), KNN algorithm, Data visualization, Web development.
___________________________________________________________________________
1. Introduction
Disasters are the natural phenomenon that attracts major global interest. In those disasters, flooding is the
major one it results in tremendous environmental destruction and loss of livelihood and many other day-to-day
activities. Flooding is a result of substantial rainfalls, structural failures, and a large number of human factors.
Floods play on precipitation amounts and rates, topology, geology, land use, and antecedent moisture condition.
In 2020 during the time of pandemic we have seen major natural disasters in those disaster floods have played a
major role. This is due to the abnormal change in the climatic conditions all over the world mainly rains occurred
during the rainy seasons i.e. From September to December every year. Early rainfall is usually in June with full
commencement in September, and stops in November each year, with a few showers in December to herald the
dry season and the typical monsoon winds in sea bed zone areas.

Due to global warming and changes in the climatic condition's rains are not coming in the months where
rainfalls have to come. Due to this flooding has occurred in major rivers occupied areas and hilly regions like
Tamil Nadu, Kerala, Vishakhapatnam, Mumbai, Gujarat, and other regions of India. There are three major forms
of flooding regions in India they are: coastal, river, and urban flooding. Coastal flooding happens in a low-lying
belt and freshwater swamps along the coast. River flooding happens in the floodplains of bigger rivers. Flash
floods are also attributed to rivers in the inland areas where sudden heavy rainfall in a short period can turn into
destructive torrents. Also, urban flooding happens in towns, on flat or low-lying surfaces mostly where surface
drainage more or less does not exist, or where existing 1drainage has been blocked with waste. Dams are among
the most important human creations in the hydrological cycle built to impound water in reservoirs amid times of
high flow, with the goal that it can be utilized to meet human water prerequisites amid times that natural flows
are deficient in disasters.

In this proposed model with the help of an intelligent sensor system, we are going to keep a close watch over
various natural factors to predict a flood, so we can embrace ourselves for caution, and minimize the damage
caused by the flood. Natural disasters like a flood can be devastating leading to property damage and loss of lives.
To eliminate or lessen the impacts of the flood, the system uses various natural factors like temperature, humidity,
and water raise in level. After building up this smart object we are going to find out the place where we can fix
our smart object with the help of the KNN algorithm. Finally, these complete data will be going to be updated
and make available to all people in real-time with the help of our web page that we have created.

152
 Turkish Journal of Computer and Mathematics Education Vol.12 No.9 (2021), 152-158
Research Article

2. Methodologies
2.1 Physical Design: -
2.1.1 NODEMCU:NODEMCU is an open-source firmware and development kit that helps you to prototype
or build IoT products. It includes firmware that runs on the ESP8266 Wi-Fi modulations from ESP Systems and
hardware which is based on the ESP8266 module. This firmware was developed with the help of Lua and c
scripting language. It is based on the Elua project and built on the ESP modulations of Non-OS SDK files for
ESP8266[5][6]. MCU stands for Microcontroller Unit - which means it is a computer that processes the data on
a single chip. A microcontroller contains one or more CPU processors along with memory and programmable
input/output peripherals. They are used to automate automobile engine control, implantable medical devices,
remote controls, office machines, appliances, power tools, toys.
2.1.2 DHT11:DHT11 is a temperature and humidity sensor where the climatic conditions can be recognized
by this sensor. There are threepin configurations to the sensor where the VCCpin will get the power supply, OUT
pin will show the result i.e., climatic condition report, and GND pin will neutralize or grounds the unwanted
activities.
2.1.3 Ultrasonic Sensor:Ultrasonic sensor is used to find the depth and height of water. The basic principle of
ultrasonic sensor is related to that of laws of reflection i.e., the Tring pin will transmit the signal and those signals
will be reflected to echo pin after touching the upper surface of the water or any object that is stable this will help
us to find the distance or raise in water level. In the ultrasonic sensor, there are 4 pins where the two extreme pins
will be used for the transmission and receiver of depth and also the rise in the water level.
2.2 Logical Design:
2.2.1 Arduinocompiler:The Arduino IDE is a cross-platform application for Windows that is written in
functions from C and C++. It is used to integrate the sensors that can be programmed and operatable according
to the surrounding environmental condition with the help of Arduino compatible software. It is the place where
the main operations are going to be done i.e. Data uploading to the cloud and the message transmission to the
phone through IFTTT.
2.2.2 Thingspeak cloud:Thing speak is an IoT analytics platform service that allows you to aggregate,
visualize, and analyze live data streams in the cloud. You can send data to Thingspeak from your devices, create
instant visualizations of live data, and send alerts using web services like Twitter and Twilio. With Thing-speak,
you can write and execute Arduino code to perform pre-processing, visualizations, and analyses [9]. Thing-speak
enables engineers and scientists to prototype and builds IoT systems without setting up servers or developing web
software.
2.2.3 IFTTT:If This Then That is an IoT platform where certain actions are going to be triggered when the
action has occurred. This is predefined in the code and these all are going to be completely integrating with the
WIFI module that we are going to be used in the project development.
2.2.4 R Studios: This a data science platform tool that is used to visualize. R Studio is an integrated
development environment for R, a programming language for statistical computing and graphics. It is available
in two formats: R Studio Desktop is a regular desktop application while R Studio Server runs on a remote server
and allows accessing R Studio using a web browser.
2.2.5 XAMPP: XAMPP is a free and open-source cross-platform web server solution stack package developed
by Apache Friends, consisting mainly of the Apache 8HTTP Server, MariaDB database, and interpreters for
scripts written in the PHP and Perl programming languages. Since most actual web server deployments use the
same components as XAMPP, it makes transitioning from a local test server to a live server possible.
2.2.6 KNN:K-Nearest Neighbor (KNN) Algorithm for Machine Learning K-Nearest Neighbor is one of the
simplest Machine Learning algorithms based on the SupervisedLearning technique. K-NN algorithm assumes the
similarity between the new case/data and available cases and puts the new case into the category that is most
similar to the available categories.
3. Implementation
3.1 Basic Architecture: -

Fig 1 General architecture flow diagram of the model

153
 Turkish Journal of Computer and Mathematics Education Vol.12 No.9 (2021), 152-158
Research Article

Fig. 1 will focus on the complete structure of the proposed work; Hear We used three sensors with a controller
for analysis of the water-body status. Moreover, based on sensor threshold data we may trigger an automated
message passed to the user of the system.
3.2 System Setup
There are three different phases in the proposed model they are
Phase 1: Hardware and Cloud setup.
Phase 2: Place identification using KNN.
Phase 3: Placing all the data on a webpage.
3.2.1 Hardware and Cloud setup
In this model, the NODEMCU board is the place where all sensors are going to be integrated and the collected
sensors data is going to be sent to the cloud and IFTTT to android phones. Here the DHT11 sensor will calculate
the temperature and humidity for every 1 hour in a day and those data will be uploaded to the cloud with the help
of NODEMCU with integrating ESP8266 module. That data is also getting uploaded to the cloud and stored in
the form of graphs. In thing speak cloud the collected data is going to be stored in the form of graphs. The
ultrasonic sensor will help find the raise in the level of water. The basic working of ultrasonic sensor is similar to
that of reflection laws i.e. The Echo pin will send the signal to the water level depth or the surface of the water
and the Tring will receive the reflected signal and will calculate if there is any raise in the level of water. Finally,
the main function Water flows sensor where the water flow data is going to be stored and going to be represented
in the form of graphs in thing speak cloud represents in Fig.3. These all modules are going to be integrated into
NODEMCU in such a way that all the sensors will help in finding the flood occurrence Fig.2.

Fig.2 Physical Design of Flood Monitoring System

Fig.3 Thing Speak Cloud Configuration.

3.2.2 IFTTT
In Fig.4. We are going to find the area and the place where major floods have occurred from the past 50 years'
data. We have applied the KNN algorithm to find the most flood occurred area so that we can place the smart
object near to that place.

Fig.4 Decision tree

154
 Turkish Journal of Computer and Mathematics Education Vol.12 No.9 (2021), 152-158
Research Article

Fig.4.1 KNN algorithm output

Fig 4.1 Gives the output of the KNN algorithm output
d(x,y) = sqrt((y1-x1)^2-(y2-x2)^2)

Fig.4.2 Confusion matrix

In 4.2 We can see the output of the confusion matrix and also we can find the accuracy and error rate.
Accuracy = 0.9531
Error = 0.0469
3.2.3 Message Transmissions
Finally, after developing the smart object and finding out a place we are going to update those data on our
web page. So that every common people alert themselves and also alert others.
4. Results and Discussion

Fig. 5 Serial Monitor view in IDE

Fig. 5 will give you the idea of whether the sensors and WIFI are connected or not. It is available in the
Arduino compiler or namely known as the Arduino IDE.With the help of a serial monitor, we can also normally
view and check the connection to WIFI and speed in the flow and level of water.

155
 Turkish Journal of Computer and Mathematics Education Vol.12 No.9 (2021), 152-158
Research Article

Fig. 6. Thing Speak Cloud Data Visualization

Fig. 6. will indicate the data accumulation of sensor data which is located in water bodies. Hear data has been
visualized in Thinker Speak IoT Cloud and the same has visualized any remote location using Thinker View for
Android Application.

Fig.7 Confusion matrix

In Fig.7 The above confusion matrix will givethe output of the various performance metrics accuracy and
error rate.
Accuracy: 0.8934
Error: 0.1066

Fig.7.1 KNN algorithm

In Fig.7.1 We will find the KNN algorithm output that will give the idea of what is happening and what is not
going to happen.
d(x,y) = sqrt((y1-x1)^2-(y2-x2)^2)

Fig.7.2 Sanitation controls

156
 Turkish Journal of Computer and Mathematics Education Vol.12 No.9 (2021), 152-158
Research Article

From the above figures, we came to know that we are going to focus mainly on the low sanitation control
areas where major floods have occurred.

Fig.8. Alert Message in Mobile Phone

Fig 8.1 Web page

In Fig.8. Represents the alert message communicated to the authorities of the expert system. Moreover, it will
lead to taking immediate action to save guard the human life [7]. Also contains the information the people need
whether a flood is occurring or not. This confidential information can be accessed only by authorized persons. So
that it will provide in the security of the data.
5. Conclusion
At present India is facing a devastating flood in many parts of India, there arise a need for efficient flood
monitoring systems. Flood forecasting and the issuing of flood warnings are effective ways to reduce damage.
The proposed system will be efficient because it has better coordination of monitoring, communication, and
transmission technologies which are adaptable to background conditions. The proposed system also ensures
increased accessibility for the assessment of emergencies and enhances effectiveness and efficiency in responding
to a catastrophic situation. In summary, the proposed system would be beneficial for decision-making and
evacuation planning purposes.

References
1. R. Becker, “A future of more extreme floods, brought to you by climate change,” May 2017. [Online].
Available: https://www.theverge.com/2017/5/18/15658342/flooding-sealevel- rice-meltingice- climate-
change-extreme.
2. Z. M. Taib, N. S. Jaharuddin, and Z. D. Mansor, “A review of flood disaster and disaster management in
Malaysia,” International Journal of Accounting Business Management, vol. 4, no. 3, 2016.
3. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, and M. Ayyash, “Internet of things: A survey on
enabling technologies, protocols, and applications,” IEEE Communications Surveys Tutorials, vol. 17, no. 4,
pp. 2347–2376, Fourth quarter 2015.
4. S. J. Priya, S. Akshaya, E. Aruna, J. A. M. Julie, and V. Ranjani, “Flood monitoring and alerting system,”
International Journal of Computer Engineering Technology (IJCET), vol. 8, no. 2, p. 15, Mar 2017.

157
 Turkish Journal of Computer and Mathematics Education Vol.12 No.9 (2021), 152-158
Research Article

5. D. Satria, S. Yana, R. Munadi, and S. Syahreza, “Prototype of google maps-based flood monitoring system
using Arduino and gsm module,” International Research Journal of Engineering and Technology (IRJET),
vol. 4, no. 10, Oct 2017.
6. M. Madhumathi and R. Grace, “Flood alert management system using IoT and microcontroller,” International
Journal of Innovative Research in Computer and Communication Engineering, vol. 5, no. 4, April 2017.
7. K. Rose, S. Eldridge, and L. Chapin, “The Internet of Things: An Overview: Understanding the Issues and
Challenges of a More Connected World,” www.internetsociety.org, October 2015.
8. E.A. Basha, S. Ravela, and D. Rus, “Model-Based Monitoring for Early Warning Flood Detection,”
SenSys’08, November 5–7, 2008, Raleigh, North Carolina, USA.
9. J. Sunkpho and C. Ootamakorn, “Real-time flood monitoring and warning system,” Songklanakarin J. Sci.
Technol., vol. 33, no. 2, Mar-Apr. 2011, pp. 227-235.

158