ABSTRACT

Nowadays air pollution has turned out to be one of the significant issues because of increment in the
quantity of vehicles and during the time spent industrialization and urbanization. This expansion in the
level of contamination brings about destructive consequences for prosperity. This project explains the
depiction and execution of an Air Pollution detection system. The innovation grasped here, is a hands-on
execution of the idea of Internet of Things. This detailed work is an exploration of the possibilities of
consumption of this innovation, in this world, where natural well-being is turning into a genuine risk.
The work is actualized utilizing microcontroller board of Arduino. In this project I am going to make an
IoT based Air Pollution Detection Monitoring System in which I will monitor the Air Quality over a web
server using ESP8266 Wi-Fi device and will a trigger alarm when the air quality goes down a certain
level means when there is amount of harmful gases is present in the air like CO2. It will show the air
quality in PPM (Parts Per Million) as like “Fresh Air”, “Poor Air”, “Danger Air” on LCD and webpage
so that I can monitor it very easily.

As the world’s population is becoming increasingly urban, the cities are under pressure to remain
livable. In recent years, the air quality of the cities has become one of the major cause of concern
around the world. Thus, it is necessary to constantly monitor the air quality index of a city to make it
smart and livable. In this paper, we propose and develop an IoT based Air Quality Monitoring System
for Smart Cities. The real-time data of the air quality is accessed through the smart devices and
analyzed to measure the impact on city dwellers. The smart devices are capable of measuring the
Temperature, Humidity, Carbon Monoxide, LPG, Smoke and other hazardous particulate matters like
PM2.5 and PM10 levels in the atmosphere. The gathered data is accessible globally through an Android
Application.

i
 TABLE OF CONTENTS
Abstract I
Declaration II
Acknowledgement III
Table of Contents IV
CHAPTER NO. CHAPTER NAME PAGE NO.

Chapter 1 INTRODUCTION
1.1 Basic Topics of the project 1
1.2 Problem Definition 2
1.3 Scope of the Project 4
1.4 Motivation 5
1.5 Objective 6
1.6 Organization of the Report 6
Chapter 2 LITERATURE SURVEY

2.1 Introduction 7
2.2 Related Work 7
Chapter 3 SYSTEMREQUIREMENT SPECIFICATION

3.1 Introduction 13
3.2 Functional requirements 13
3.3 Non Functional requirements 14
3.4 Hardware requirements 15
3.5 Software requirements 15
3.6 Preliminary Investigation 16
3.7 System Environment 16
Chapter 4 SYSTEM ANALYSIS

4.1 Existing System 23

4.2 Proposed System 23
Chapter 5 BIBILOGRAPHY 21
APPENDIX A ACRONYMS 22

APPENDIX B REFERENCES 23

ii
CHAPTER 1

INTRODUCTION

1.1 INTODUCTION

Air Pollution occurs when harmful or excessive quantities of substances

including gases, particulates, and biological molecules are introduced into Earth's
atmosphere. It may cause diseases, allergies and even death to humans; it may also
cause harm to other living organisms such as animals and food crops and may
damage the natural or built environment. Both human activity and natural processes
can generate air pollution.
Indoor air pollution and poor urban indoor air quality are listed as two of the
world's worst toxic pollution problems in the 2008 Blacksmith Institute World's
Worst Polluted Places report. According to the 2014 World Health Organization
report, air pollution in 2012 caused the deaths of around 7 million people worldwide,
an estimate roughly echoed by one from the International Energy Agency.

Air Pollutants:

An air pollutant is a material in the air that can have adverse effects on humans
and the ecosystem. The substance can be solid particles, liquid droplets, or gases. A
pollutant can be of natural origin or man-made. Pollutants are classified as primary
or secondary.Primary pollutants are usually produced by processes such as ash from
a volcanic eruption.Other examples include carbon monoxide gas from motor vehicle
exhausts or Sulphur dioxide released from the factories. Secondary pollutants are not
emitted directly. Rather, they form in the air when primary pollutants react or interact.
Ground level ozone is a prominent example of secondary pollutants. Some pollutants
may be both primary and secondary: they are both emitted directly and formed from
other primary pollutants

1
Air Quality Monitoring and Prediction using Machine Learning Introduction

1.2 Major Air Pollutants:

 Carbon dioxide (CO2)

 Sulfur Oxides (Sox)

 Nitrogen Oxides (NOx)

 Carbon Monoxide (MOx)

 Volatile Organic Compounds (VOC)

 PM 2.5 & PM 10

Carbon dioxide (CO2) – Because of its role as a greenhouse gas it has been described as
"the leading pollutant" and "the worst climate pollution". Carbon dioxide is a natural
component of the atmosphere, essential for plant life and given off by the human respiratory
system. This question of terminology has practical effects, for example as determining
whether the U.S. Clean Air Act is deemed to regulate CO2 emissions. CO2 currently forms
about 410 parts per million (ppm) of earth's atmosphere, compared to about 280 ppm in pre-
industrial times, and billions of metric tons of CO2 are emitted annually by burning of fossil
fuels. CO2 increase in earth's atmosphere has been accelerating.

Sulfur oxides (SOx) – particularly Sulphur dioxide, a chemical compound with the formula
SO2. SO2 is produced by volcanoes and in various industrial processes. Coal and petroleum
often contain Sulphur compounds, and their combustion generates Sulphur dioxide. Further
oxidation of SO2, usually in the presence of a catalyst such as NO2, forms H2SO4, and thus
acid rain. This is one of the causes for concern over the environmental impact of the use of
these fuels as power sources.

Nitrogen oxides (NOx) – Nitrogen oxides, particularly nitrogen dioxide, are expelled from
high temperature combustion, and are also produced during thunderstorms by electric
Air Quality Monitoring and Prediction using Machine Learning Introduction
discharge. They can be seen as a brown haze dome above or a plume downwind of cities.
Nitrogen dioxide is a chemical compound with the formula NO2. It is one of several nitrogen
oxides. One of the most prominent air pollutants, this reddish-brown toxic gas has a
characteristic sharp, biting odor.

Carbon monoxide (CO) – CO is a colorless, odorless, toxic yet non-irritating gas. It is a

product of combustion of fuel such as natural gas, coal or wood. Vehicular exhaust
contributes to the majority of carbon monoxide let into our atmosphere. It creates a smog type
formation in the air that has been linked to many lung diseases and disruptions to the natural
environment and animals. In 2013, more than half of the carbon monoxide emitted into our
atmosphere was from vehicle traffic and burning one gallon of gas will often emit over 20
pounds of carbon monoxide into the air.

Volatile organic compounds (VOC) – VOCs are a well-known outdoor air pollutant. They
are categorized as either methane (CH4) or non-methane (NMVOCs). Methane is an
extremely efficient greenhouse gas which contributes to enhanced global warming. Other
hydrocarbon.
VOCs are also significant greenhouse gases because of their role in creating ozone and
prolonging the life of methane in the atmosphere. This effect varies depending on local air
quality. The aromatic NMVOCs benzene, toluene and xylene are suspected carcinogens and
may lead to leukemia with prolonged exposure. 1,3-butadiene is another dangerous
compound often associated with industrial use.

1.2 Problem Definition

There exist several challenges for urban air computing as the related data have some
special characteristics. First, since there are insufficient air-quality-monitor stations in a city
due to the high cost of building and maintaining such a station, it is expensive to obtain
labeled training samples when dealing with fine-gained air quality.
Air Quality Monitoring and Prediction using Machine Learning Introduction

1.3 Scope of the Project

 One major basic right is clean air that is integral to the concept of citizenship and it's
while not a doubt, the responsibility of every subject to try to do his/her half to stay
the air clean.
 Air quality prognostication has been looked into because the key answer of early
warning and management of pollution.
 During this project, we tend to propose an Associate in nursing air quality prediction
system supported by a machine learning framework.
 More severe impacts affect people building an early warning system, which provides
precise forecasts and also alerts health alarms to local inhabitants will provide
valuable information to protect humans from damage by air pollution best prediction
using several models and compares them to find the appropriate solutions.
 To develop robust application using Machine learning algorithms and different
techniques using large datasets and find out the optimum solution for Air Quality that
helps the human being and It is used to predict the future concentrations of air
pollutants in accordance with methodological variables.
 The major pollutants area unit oxide (NO), monoxide (CO), stuff (PM), SO2, etc.
monoxide is made thanks to the deficient Oxidization of propellant like rock oil, gas,
etc.
 Nitrogen Oxide is made thanks to the ignition of thermal fuel; Carbon monoxide
causes headaches, vomiting; aromatic hydrocarbon is made due to smoking, it causes
metabolic process problems; gas oxides cause vertigo, nausea; stuff with a diameter of
2.5 micrometers or but that affects additional to human health.
 Measures should be taken to reduce air pollution within the atmosphere. Air Quality
Index (AQI), is used to measure the standard of air. Earlier classical ways like
probability, statistics were accustomed predict the standard of air, but those ways area
units terribly complicated to predict the standard of air.
Air Quality Monitoring and Prediction using Machine Learning Introduction

 Due to the advancement of technology, currently, it's terribly straightforward to fetch

the data regarding the pollutants of air exploitation sensors. Assessment of data to
notice the pollutants wants vigorous analysis. Convolution Neural networks.

1.3 Motivation
Air pollution is one of the greatest threats we are facing today. It is rapidly increasing
due to various human activities, and the occurrence of particulates, chemicals, or biological
resources into the environment that cause unexpected, humans' death, or disease, damage
source of revenue, or spoil the natural environment. The direct impact of air pollution
problems on human health resulted in an increased public awareness of the air quality in
developing and developed countries. The commonly occurring pollutants include carbon
monoxide (CO2), Respirable Suspended Particulate Matter (RSPM), Sulphur dioxide (SO2),
Nitrogen dioxide (NO2), Ozone etc.

The increase in the concentration of pollutants in the air will be life-threatening and will
cause several diseases. So, it is necessary to monitor and forecast the criteria pollutants in the
air. The prediction of air pollutants can be made through models. In most of the air quality
predictions, Gaussian dispersion models are used. These dispersion models have some
physical basis. So, information about the source of pollutants and other parameters are not
known to us. Statistical models can be used to overcome these difficulties. They are capable
of forecasting the concentration of pollutants in air. The AQI is defined as an index or rating
scale for reporting the daily combined effect of ambient air pollutants recorded in the
monitoring sites.

1.4 OBJECTIVES
 The proposed system entitled "Air Quality Index Prediction and Classification" aimed
to predict AQI of future month-wise and classify them in different categories.
 To design a system which will help common people as well as those in the
meteorological department to detect and predict pollution levels .

 The proposed system entitled "Air Quality Index Prediction and Classification" aimed
to predict AQI of future month-wise and classify them in different categories.
 To design a system which will help common people as well as those in the
meteorological department to detect and predict pollution levels and take the
necessary action following that. Also, this will help the public set up a data source for
small localities which are usually left out in comparison to the large cities.
Air Quality Monitoring and Prediction using Machine Learning Introduction

1.5 Organization of the Report

Chapter 1: The chapter 1 describes, in brief, the idea of the project. It begins with the
explanation of the purpose of the project, the definitions of a few terms used in the document,
the problem definition, motivation and the scope of the project.
Chapter 2: This chapter describes the literature survey and the background preparation
done to understand more about this project.
Chapter 3: It describes the system requirements such as hardware and software
requirements functional and non-functional requirements, preliminary investigations, system
environment.
Chapter 4: This chapter describes the existing system and its limitations and how it tries to
improve the existing system. It explains the proposed system and its architecture.
Finally, this project explains the problem in hand for the system that is being designed
CHAPTER 2

LITERATURE SURVEY
By studying literature, it seems that several classification methods have been
developed for “AI Based image classification Techniques”. Literature survey is the most
important step in software development process. Before developing the tool it is necessary to
determine the time factor, economy and company strength. Once these things are satisfied,
then next step is to determine which operating system and language can be used for
developing the tool. Once the programmer start building the tool the programmers need lot
of external support. This support can be obtained from senior programmers, from book or
from websites.

2.1 RELATED WORK

[1] Air Pollution Prediction Using ML

AUTHORS: - Mushtak Sayyed, Adesh Salunkhe, Akshay Sarode and Swaraj Desai
Due to large scale industrialization and advances in technology there has been increased
pressure on mother nature. This includes air pollution that is somewhat like a bad omen for
humanity. There have been a lot of steps taken to reduce pollution but it has been of no avail.
To provide a solution to this ongoing crisis, there needs to be some kind of air pollution level
prediction technique that can be utilized.

[2] Air Quality Prediction of Data Log by Machine Learning

AUTHORS:- Venkat Rao Pasupuleti; Uhasri; Pavan Kalyan; Srikanth; Hari Kiran Reddy
The air quality monitoring system measures various air pollutants in various locations to
maintain good air quality. It is the burning issue in the present scenario. Air is contaminated
by the arrival of dangerous gases into the climate from the industries, vehicular emissions,
etc.. Nowadays, air pollution has reached critical levels and the air pollution level in many
major cities has crossed the air quality index value as set by the government. It has a major
impact on the health of the human. With the advancement in technology of machine
learning, it is now possible to predict the pollutants based on the past data.

7
 [3] PREDICTION OF AIR QUALITY INDEX BY
EXTERNAL LEARNING

AUTHORS: - Burhan BARAN

In this study, it is aimed to predict the Air Quality Index (AQI) by the Extreme Learning

Machines (ELM) algorithm. For this purpose, six parameters have been selected which can
affect the AQI. These are temperature, humidity, pressure, wind speed, PM10 and SO2
respectively. First of all, “Forecast Sheet” application that presented in the Excel environment
and the correlation analysis were used to determine the relationship status between these six
parameters and AQI.

[4]DETERMINATION OF AIR QUALITY MONITORING & PREDICTIONAUTHORS:-

Purvesh Patil, Parth Modi, Ninad Kamble

Air pollution and its prevention are constant scientific challenges during last decades. However,
they still remain huge global problems. Affecting human’s respiratory and cardiovascular system,
they are cause or increased mortality and increased risk for diseases for the population. Many
efforts from both local and state government are done in order to understand and predict air
quality index aiming improved public health.

[5]Air Pollution Prediction using Machine Learning

AUTHORS: - Shreyas Simu; Varsha Turkar; Rohit Martires; Vranda Asolkar; Swizel Monteiro
Industrial pollution is one of the most serious problems faced today. Long-term exposure to air
pollution causes severe health issues including respiratory and lung disorders. Presently laws
regarding industrial pollution monitoring and control are not stringent enough. The working
dataset includes parameters of air in terms of ambient air as well as of the stack emission. On
this data, various Machine Learning (ML) algorithms were applied for prediction of emission
rate, and comparative analysis is done.

Dept.of CSE,CBIT 8 2021-2022

 [6]Urban Air Quality Analysis and Prediction Using Machine
Learning AUTHORS:-K. Nandini;G.Fathima
Air pollution is one of the influential factors that can affect the quality of every living being
Prediction is done using Machine learning techniques.K Means algorithm is used for clustering
And different classifiers such as Multinominal Logistic Regression and Decision Tree
algorithms are used to analyze the results based on available data in the R programming
language.

[7] Air Quality Prediction and Monitoring using Machine Learning Algorithm
basedIoT sensor- A researcher's perspective

AUTHORS: - G. Kalaivani; P. Mayilvahanan

Air Pollution (AP) is one of the serious and major environmental problem worldwide.
Many researchers have drawn attention and have focused about these problems keeping in
mind human health. Air quality prediction information is one of the better ways through
which people can be informed to be more vigilant about serious health issues and protect
human health caused by air pollution. In many metropolitan cities air pollution is a major
challenging environmental issue. To analyze the present traffic condition of the city, local
authorities can be enabled by real time monitoring of pollution data which makes
appropriate decisions.

[8] Smart City Air Quality Prediction

MachineLearningAUTHORS: - Rishanti,

Murugan,

Naveen Palanichamy
Air pollution in smart cities in the world has been drastically increasing lately and the
increase inthe concentration of particulate matter (PM 2.5) in the air is a threat for
thecountry and citizens as it can out-turn unbearable consequences such as
cardiovasculardisease and worsen asthma. PM 2.5 is a deadly air pollutant that is a
mixture of solid and liquid coarse particles and has a diameter of 2.5 micrometres. In
Malaysia, traffic congestion has been the main contributor to developing air pollution in

Dept.of CSE,CBIT 9 2021-2022

 smart cities such as Kuala Lumpur and Johor Bahru.

Dept.of CSE,CBIT 10 2021-2022

[9]Machine Learning Techniques for Air Quality Forecasting and Study on Real-

TimeAirQuality Monitoring
AUTHORS: - Varsha Hable-Khandekar; Pravin Srinath
Air Pollution has become major, serious problem worldwide. Because of its close relation to
human health, it has gained a lot of attention of many researchers. People are becoming cautious
about better ways of monitoring air quality information and has become important toprotect human
health from serious health problems caused by air pollution. Many researchers areworking on real-
time air quality monitoring and forecasting for getting accurate results.

[10] INDIAN AIR QUALITY PREDICTION AND ANALYSIS

USINGMACHINELEARNING
AUTHORS:- Mrs. A. Gnana Soundari, Mrs. J. Gnana Jeslin, Akshaya A.C
We forecast the air quality of India by using machine learning to predict the air quality index of a
given area. Air quality index of India is a standard measure used to indicate the pollutant (so2, no2,
rspm, spm. etc.) levels over a period. We developed a model to predict the air quality index based
on historical data of previous years and predicting over a particular upcoming year as a Gradient
decent boosted multivariable regression problem.
CHAPTER 3
SYSTEM REQUIREMENTSPECIFICATIONS
3.1 INTRODUCTION
A Software Requirement Specification (SRS) is basically an organization's understanding
of a customer or potential client's system requirements and dependencies at a particular point
priorto any actual design or development work. The information gathered during the analysis is
translated into a document that defines a sets of requirements. It gives the brief description of
the services that the system should provide and also the constraints under which, the system
should operate. Generally, the SRS is a document that completely describes what the proposed
software should do without describing how the software will do it. It's a two-way insurance
policy that assures that both the client and the organization understand the other's requirements
from that perspective at a given point in time.
The SRS document itself states in precise and explicit language those functions and
capabilities a software system must provide, as well as states any required constraints by which
the system must abide. The SRS also functions as a blueprint for completing a project with as
little cost growth as possible. The SRS is often referred to as the "parent" document because all
subsequent project management documents, such as design specifications, statements of work,
software architecture specifications, testing and validation plans, and documentation plans, are
related to it. Requirement is a condition or capability to which the system must conform.
Requirement Management is a systematic approach towards eliciting, organizing and
documenting the requirements of the system clearly along with the applicable attributes. The
elusive difficulties of Requirements are not always obvious and can come from any number of
sources.

3.2 FUNCTIONALREQUIREMENTS
A function of software system is defined in functional requirement and the behavior of the
system is evaluated when presented with specific inputs or conditions which may include
calculations, data manipulation and processing and other specific functionality. The functional
requirements of the project are one of the most important aspects in terms of entire mechanism
of modules.

11
Air Quality Monitoring and Prediction using Machine Learning System Requirements

3.3 NON-FUNCTIONAL REQUIREMENTS

 Reliability

The structure must be reliable and strong in giving the functionalities. The
movements must be made unmistakable by the structure when a customer has revealed a
couple of enhancements. The progressions made by the Programmer must be Project
pioneer and in addition the Test designer.

 Maintainability

The system watching and upkeep should be fundamental and focus in its approach.
There should not be an excess of occupations running on diverse machines such that it
gets hard to screen whether the employments are running without lapses.

 Performance

The framework will be utilized by numerous representatives all the while. Since the
system will be encouraged on a single web server with a lone database server outside of
anyone's ability to see, execution transforms into a significant concern. The structure
should not capitulate when various customers would use everything the while. It should
allow brisk accessibility to each and every piece of its customers. For instance, if two
test specialists are all the while attempting to report the vicinity of a bug, then there
ought not to be any irregularity at the same time.
 Portability

The framework should to be effectively versatile to another framework. This is

obliged when the web server, which s facilitating the framework gets adhered because of
a few issues, which requires the framework to be taken to another framework.
 Scalability

The framework should be sufficiently adaptable to include new functionalities at a

later stage. There should be a run of the mill channel, which can oblige the new
functionalities.

Dept. of CSE, CBIT, 12 2021-2022

Kolar
Air Quality Monitoring and Prediction using Machine Learning System Requirements

 Flexibility

Flexibility is the capacity of a framework to adjust to changing situations and

circumstances, and to adapt to changes to business approaches and rules. An adaptable
framework is one that is anything but difficult to reconfigure or adjust because of
diverse client and framework prerequisites. The deliberate division of concerns between
the trough and motor parts helps adaptability as just a little bit of the framework is
influenced when strategies or principles change.

3.4 HARDWAREREQUIREMENTS

 Arduino uno

 Gas sensors

 Wifi module

 Power supply

 Lcd display

3.5 SOFTWARE REQUIREMENTS

 Operating System : Windows XP/10 or Linux

 Coding Language : Python, embedded c

 Tool : PyCharm community, arduino suite

Dept. of CSE, CBIT, 13 2021-2022

Kolar
 Air Quality Monitoring and Prediction using Machine Learning System Requirements

Modules
 Data cleaning / modeling

 Feature Selection and Extraction

 Model Training Phase

 Test and Analysis phase

Modules Description:

Data cleaning / modeling:

Machine learning needs two things to work, data (lots of it) and models. When acquiring
the data, be sure to have enough features (aspect of data that can help for a prediction, like the
surface of the house to predict its price) populated to train correctly your learning model. In
general, the more data you have the better so make to come with enough rows.
The primary data collected from the online sources remains in the raw form of statements,
digits and qualitative terms. The raw data contains error, omissions and inconsistencies. It
requires corrections after careful scrutinizing the completed questionnaires. The following steps
are involved in the processing of primary data. A huge volume of raw data collected through
field survey needs to be grouped for similar details of individual responses.
Data Preprocessing is a technique that is used to convert the raw data into a clean data set. In
other words, whenever the data is gathered from different sources it is collected in raw format
which is not feasible for the analysis.
Therefore, certain steps are executed to convert the data into a small clean data set. This
technique is performed before the execution of Iterative Analysis. The set of steps is known as
Data Preprocessing. It includes -
 Data Cleaning

 Data Integration

 Data Transformation

 Data Reduction
 Air Quality Monitoring and Prediction using Machine Learning System Requirements

Feature Selection and Extraction:

Starts from an initial set of measured data and builds derived values (features). In
machine learning feature extraction starts from an initial set of measured data and builds derived
values (features) intended to be informative and non-redundant, facilitating the subsequent
learning and generalization steps, and in some cases leading to better human ...intended to be
informative and non-redundant, facilitating the subsequent learning and generalization steps,
and in some cases leading to better human interpretations.
Feature extraction is related to dimensionality reduction. When the input data to an
algorithm is too large to be processed and it is suspected to be redundant (e.g. the same
measurement in both feet and meters, or the repetitiveness of images presented as pixels), then
it can be transformed into a reduced set of features (also named a feature vector).
Determining a subset of the initial features is called feature selection. The selected
features are expected to contain the relevant information from the input data, so that the desired
task can be performed by using this reduced representation instead of the complete initial data.

Model Training Phase:

The process of training an ML model involves providing an ML algorithm (that is, the
learning algorithm) with training data to learn from. The term ML model refers to the model
artifact that is created by the training process. The training data must contain the correct answer,
which is known as a target or target attribute. The learning algorithm finds patterns in the
training data that map the input data attributes to the target (the answer that you want to predict),
and it outputs an ML model that captures these patterns.

Test and Analysis phase:

In testing phase, the model is applied to new set of data. The training and test data are
two different datasets. The goal in building a machine learning model is to have the model
perform well. On the training set, as well as generalize well on new data in the test set. Once the
build model is tested then we will pass real time data for the prediction. Once prediction is done
then we will analyze the output to find out the crucial information.
"Performance Metrics for Predictive Modeling in classification problems, the primary
source of performance analysis is a coincidence matrix (classification matrix or a contingency
table)”. Above figure shows a coincidence matrix for a two-class classification problem. The
equations of the most commonly used metrics that can be calculated from the coincidence
matrix are:
 As being seen in above figure, the numbers along the diagonal from upper-left to lower-
right represent the correct decisions made, and the numbers outside this diagonal represent the
error "The true positive rate (also called hit rate or recall) of a classifier is estimated by dividing
the correctly classified positives (the true positive count) by the total positive count. The false
positive rate (also called a false alarm rate) of the classifier is estimated by dividing the
incorrectly classified negatives (the false negative count) by the total negatives. The overall
accuracy of a classifier is estimated by dividing the total correctly classified positives and
negatives by the total number of samples.
CHAPTER 4
SYSTEM ANALYSIS

4.1 EXISTING SYSTEM

The interpolation, prediction, and feature analysis of fine-gained air quality are three
important topics in the area of urban air computing. The solutions to these topics can provide
extremely useful information to support air pollution control, and consequently generate great
societal and technical impacts. Most of the existing work solves the three problems separately
by different models.

4.2 PROPOSED SYSTEM

This paper is motivated to address all these challenges by utilizing the information
contained in the unlabeled data and the spatio-temporal data, and performing feature selection
and association analysis for the urban air related data. Though labeled data are difficult or
expensive to obtain, large amounts of unlabeled examples can often be gathered cheaply. In
general, unlabeled data can help in providing information to better exploit the geometric
structure of the data. Moreover, most of the urban air related data contain both space and time
information.

APPLICATIONS
 It is used to measure of how air pollution affects one's health within a short time period
 Come to know about the pollution at hospitals and publics places to avoid the
breathability
 Air quality prediction is mainly used for asthma patients to be precautioned.
 AQI prediction will overcome by planting trees and controlling human if it is unhealthy
 Roadside pollution Monitoring.
 Industrial perimeter Monitoring.
 Site selection for reference monitoring stations.
 Indoor Air Quality Monitoring.
 To make this data available to the common man.

20
 CHAPTER 5
METHODOLOGY and IMPLEMENTATION
Block diagram

Internet of Things (IoT) mainly deals with connecting smart devices to internet by joining
the advantage of OSI layered Architecture. In the context of this work we propose a cluster
of Air Quality Monitoring Gas Sensor MQ135, MQ2, MQ4, MQ7 motes, which are used to
measure the concentration of Air pollutants in the air. The Gas Sensors MQ135 is interface
with a tiny entrenched platform equipped with other. We have mainly used the Arduino
UNO which is an open source development boards with ESP8266-12E chips. M MQ135,
MQ2, MQ4, MQ7 Q135 Gas Sensors is used to collect gas concentration measurements.
This sensor data would be captured and sent to the Arduino UNO for IoT (Internet of
Things) based data acquirement.

The sensor data will be updated to cloud using a iot module ESP8266. The cloud using in
our project is thingspeak, the thingspeak reads the data from the ESP8266 and visualize the
sensor data. The machine learning module gets the data from the thingspeak and analyize
the result using machine learning algorithms. Predict the air quality based on the obtained
result.
21
 Components description
Arduino Uno:

Arduino/GenuinoUno is a microcontroller board based on theATmega328P. It has 14 digital input/output

pins (of which 6 can be used as PWM outputs), 6 analog inputs, a 16 MHz quartz crystal, a USB
connection, a power jack, an ICSP header and a reset button. It contains everything needed to support
the microcontroller; simply connect it to a computer with a USB cable or power it with an AC-to-DC
adapter or battery to get started. You can tinker with your UNO without worrying too much about
doing something wrong, worst case scenario you can replace the chip for a few dollars and start over
again. "Uno" means one in Italian and was chosen to mark the release of Arduino Software (IDE) 1.0. The
Uno board and version 1.0 of Arduino Software (IDE) were the reference versions of Arduino , now
evolved to newer releases. The Uno board is the first in a series of USB Arduino boards, and the
reference model for the Arduino platform; for an extensive list of current, past or outdated boards see the
Arduino index of boards.

Arduino specification:
Microcontroller ATmega328P

22
 OperatingVoltage 5v
Input voltage 7-12v
Input voltage limit 6-20v
Digital I/O Pins 6
Analogue input Pins 6
DC current perI/O pins 20 mA
DC current for 3.3v Pin 50 mA
Flash Memory Of which o.5KB is used
SRAM 2 KB
EEPROM 1KB
Clock Speed 16MHz
Length 68.6mm
Width 53.4nm
Weight 25g

Gas sensor

Features

 Operating Voltage is +5V

 Can be used to Measure or detect LPG, Alcohol, Propane, Hydrogen, CO and even methane
 Analog output voltage: 0V to 5V
 Digital Output Voltage: 0V or 5V (TTL Logic)
 Preheat duration 20 seconds
 Can be used as a Digital or analog sensor
 The Sensitivity of Digital pin can be varied using the potentiometer

23
Type of gas sensor
MQ2- this sensor is used for gas leakage detection
MQ4- this sensor is used for metal oxide detection
MQ7- this sensor is used for CO gas detection
M135- this sensor is used for wide range of gasses. It is a air quality sensor

LCD DISPLAY

The specifications of LCD 16X2 are discussed below.

 The operating voltage of this display ranges from 4.7V to 5.3V

 The display bezel is 72 x 25mm
 The operating current is 1mA without a backlight
 PCB size of the module is 80L x 36W x 10H mm
 HD47780 controller
 LED color for backlight is green or blue
 Number of columns – 16
 Number of rows – 2
 Number of LCD pins – 16
 Characters – 32
 It works in 4-bit and 8-bit modes
 Pixel box of each character is 5×8 pixel
 Font size of character is 0.125Width x 0.200height

LCD 16X2 Pin Configuration

The pin configuration of LCD 16 X 2 is discussed below so that LCD 16×2 connection can be done easily
with external devices.

24
16X2 LCD Pin Diagram

 Pin1 (Ground): This pin connects the ground terminal.

 Pin2 (+5 Volt): This pin provides a +5V supply to the LCD
 Pin3 (VE): This pin selects the contrast of the LCD.
 Pin4 (Register Select): This pin is used to connect a data pin of an MCU & gets either 1 or 0. Here,
data mode = 0 and command mode =1.
 Pin5 (Read & Write): This pin is used to read/write data.
 Pin6 (Enable): This enables the pin must be high to perform the Read/Write procedure. This pin is
connected to the data pin of the microcontroller to be held high constantly.
 Pin7 (Data Pin): The data pins are from 0-7 which are connected through the microcontroller for
data transmission. The LCD module can also work on the 4-bit mode through working on pins 1, 2,
3 & other pins are free.
 Pin8 – Data Pin 1
 Pin9 – Data Pin 2
 Pin10 – Data Pin 3
 Pin11 – Data Pin 4
 Pin12 – Data Pin 5
 Pin13 – Data Pin 6
 Pin14 – Data Pin 7
 Pin15 (LED Positive): This is a +Ve terminal of the backlight LED of the display & it is connected
to +5V to activate the LED backlight.
 Pin16 (LED Negative): This is a -Ve terminal of a backlight LED of the display & it is connected to
the GND terminal to activate the LED backlight.

LCD 16X2 Commands

The LCD 16×2 commands are discussed below.

25
  HexCode 1: This command will remove data displaying on the screen of LCD.
 HexCode 2: It used to move return home.
 HexCode 4: It is used to modify a cursor location to the left side.
 HexCode 6: It is used to change the cursor location to the right side.
 HexCode 5: It is used to shift the display to right.
 HexCode 7: It used to shift the display to left.
 HexCode 8: It is used to turn off the display & the cursor will be turned off.
 HexCode 0A: It is used to turn ON the cursor &turn off the display
 HexCode 0C: It is used to turn OFF the cursor & turn oON the display
 HexCode 0E: It is used to turn ON the display & blink the cursor.
 HexCode 0F: It is used to turn ON display & blink the cursor
 HexCode 10: It changes the cursor location to left.
 HexCode 14: It changes the cursor location to right.
 HexCode 18: It changes the display location to the left side.
 HexCode 1C: It changes the display location to the right side.
 HexCode 80: It is used to shift the cursor to the primary line.
 HexCode C0: It moves the cursor to the beginning of the next line
 HexCode 38: 2- lines & 5×7 matrix

Working Principle

The basic working principle of LCD is passing the light from layer to layer through modules. These
modules will vibrate & line up their position on 90 o that permits the polarized sheet to allow the light to
pass through it.

NodeMCU

26
The NodeMCU (Node MicroController Unit) is an open-source software and hardware development
environment built around an inexpensive System-on-a-Chip (SoC) called the ESP8266. The ESP8266,
designed and manufactured by Espressif Systems, contains the crucial elements of a computer: CPU, RAM,
networking (WiFi), and even a modern operating system and SDK. That makes it an excellent choice for
Internet of Things (IoT) projects of all kinds.

However, as a chip, the ESP8266 is also hard to access and use. You must solder wires, with the
appropriate analog voltage, to its pins for the simplest tasks such as powering it on or sending a keystroke
to the “computer” on the chip. You also have to program it in low-level machine instructions that can be
interpreted by the chip hardware. This level of integration is not a problem using the ESP8266 as an
embedded controller chip in mass-produced electronics. It is a huge burden for hobbyists, hackers, or
students who want to experiment with it in their own IoT projects.

But, what about Arduino? The Arduino project created an open-source hardware design and software SDK
for their versatile IoT controller. Similar to NodeMCU, the Arduino hardware is a microcontroller board
with a USB connector, LED lights, and standard data pins. It also defines standard interfaces to interact
with sensors or other boards. But unlike NodeMCU, the Arduino board can have different types of CPU
chips (typically an ARM or Intel x86 chip) with memory chips, and a variety of programming
environments. There is an Arduino reference design for the ESP8266 chip as well. However, the flexibility
of Arduino also means significant variations across different vendors. For example, most Arduino boards
do not have WiFi capabilities, and some even have a serial data port instead of a USB port.

NodeMCU Specifications

27
The NodeMCU is available in various package styles. Common to all the designs is the base ESP8266 core.
Designs based on the architecture have maintained the standard 30-pin layout. Some designs use the more
common narrow (0.9″) footprint, while others use a wide (1.1″) footprint – an important consideration to be
aware of.

The most common models of the NodeMCU are the Amica (based on the standard narrow pin-spacing) and
the LoLin which has the wider pin spacing and larger board. The open-source design of the base ESP8266
enables the market to design new variants of the NodeMCU continually.

 Processor: L106 32-bit RISC microprocessor core based on the Tensilica Diamond Standard 106Micro

running at 80 or 160 MHz[5]
 Memory:[6]
o 32 KiB instruction RAM
o 32 KiB instruction cache RAM
o 80 KiB user-data RAM
o 16 KiB ETS system-data RAM
 External QSPI flash: up to 16 MiB is supported (512 KiB to 4 MiB typically included)
 IEEE 802.11 b/g/n Wi-Fi
o Integrated TR switch, balun, LNA, power amplifier and matching network
o WEP or WPA/WPA2 authentication, or open networks
 17 GPIO pins[7]
 Serial Peripheral Interface Bus (SPI)
 I²C (software implementation)[8]
 I²S interfaces with DMA (sharing pins with GPIO)
 UART on dedicated pins, plus a transmit-only UART can be enabled on GPIO2
 10-bit ADC (successive approximation ADC)

Amica NodeMCU measures 49mm x 26mm with a standard pin space of 0.1″ between pins and 0.9″
between rows.

The Amica NodeMCU is approximately 25% smaller in size than a closely compatible LoLin style
NodeMCU

28
 Official Amica NodeMCU
on Carrier Board

Amico NodeMCU mounted to a 102mm x 51mm carrier board with dual DB-09 male/female connectors
Lolin
NodeMCU

LoLin style NodeMCU measures 58mm x 32mm with a pin spacing of 0.1″ between pins and 1.1″ between
rows
NodeMCU Technical Specifications
NodeMCU Pinout and Functions Explained

29


 Power Pins There are four power pins. VIN pin and three 3.3V pins.

 VIN can be used to directly supply the NodeMCU/ESP8266 and its peripherals. Power delivered
on VIN is regulated through the onboard regulator on the NodeMCU module – you can also supply
5V regulated to the VIN pin
 3.3V pins are the output of the onboard voltage regulator and can be used to supply power to
external components.

 GND are the ground pins of NodeMCU/ESP8266

 I2C Pins are used to connect I2C sensors and peripherals. Both I2C Master and I2C Slave are
supported. I2C interface functionality can be realized programmatically, and the clock frequency is
100 kHz at a maximum. It should be noted that I2C clock frequency should be higher than the
slowest clock frequency of the slave device.

30
 GPIO Pins NodeMCU/ESP8266 has 17 GPIO pins which can be assigned to functions such as I2C,
I2S, UART, PWM, IR Remote Control, LED Light and Button programmatically. Each digital
enabled GPIO can be configured to internal pull-up or pull-down, or set to high impedance. When
configured as an input, it can also be set to edge-trigger or level-trigger to generate CPU interrupts.

 ADC Channel The NodeMCU is embedded with a 10-bit precision SAR ADC. The two functions
can be implemented using ADC. Testing power supply voltage of VDD3P3 pin and testing input
voltage of TOUT pin. However, they cannot be implemented at the same time.

 UART Pins NodeMCU/ESP8266 has 2 UART interfaces (UART0 and UART1) which provide
asynchronous communication (RS232 and RS485), and can communicate at up to 4.5 Mbps.
UART0 (TXD0, RXD0, RST0 & CTS0 pins) can be used for communication. However, UART1
(TXD1 pin) features only data transmit signal so, it is usually used for printing log.

 SPI Pins NodeMCU/ESP8266 features two SPIs (SPI and HSPI) in slave and master modes. These
SPIs also support the following general-purpose SPI features:
 4 timing modes of the SPI format transfer
 Up to 80 MHz and the divided clocks of 80 MHz
 Up to 64-Byte FIFO

 SDIO Pins NodeMCU/ESP8266 features Secure Digital Input/Output Interface (SDIO) which is

used to directly interface SD cards. 4-bit 25 MHz SDIO v1.1 and 4-bit 50 MHz SDIO v2.0 are
supported.

 PWM Pins The board has 4 channels of Pulse Width Modulation (PWM). The PWM output can be
implemented programmatically and used for driving digital motors and LEDs. PWM frequency
range is adjustable from 1000 μs to 10000 μs (100 Hz and 1 kHz).

 Control Pins are used to control the NodeMCU/ESP8266. These pins include Chip Enable pin (EN),
Reset pin (RST) and WAKE pin.
 EN: The ESP8266 chip is enabled when EN pin is pulled HIGH. When pulled LOW the chip works
at minimum power.
 RST: RST pin is used to reset the ESP8266 chip.

31
 WAKE: Wake pin is used to wake the chip from deep-sleep.

 Control Pins are used to control the NodeMCU/ESP8266. These pins include Chip Enable pin
(EN), Reset pin (RST) and WAKE pin.
 EN: The ESP8266 chip is enabled when EN pin is pulled HIGH. When pulled LOW the chip works
at minimum power.
 RST: RST pin is used to reset the ESP8266 chip.
 WAKE: Wake pin is used to wake the chip from deep-sleep.
 AURDINO SUITE
 INTRODUCTION TO THE ARDUINO IDE
 It is a single-board microcontroller solution for many DIY projects; a look into the
Integrated Development Environment (IDE) that is used to program the Aurdino is given below.
The installer is downloaded, IDE installation is done. Arduino IDE is an open source software that
is mainly used for writing and compiling the code into the Arduino Module. It is an official Arduino
software, code compilation is made easy enough that even a common person with no prior technical
knowledge can make use of the software. IDE allows program writing, code verification, compiling,
and uploading to the Arduino development board.  Intended for artists, designers, hobbyists, or
anyone interested in creating interactive objects or environments.
 The Arduino IDE is incredibly minimalistic, yet it provides a near-complete environment for
most Arduino-based projects. The middle section of the Arduino IDE comprises of a simple text
editor, where the program code is inputted. The bottom section of the IDE is dedicated to an output
window that is used to see the status of the compilation, i.e., how much memory been used, any
errors found in the program, and various other useful messages.
 Projects made using the Arduino are called sketches, and such sketches are usually written
in a cut-down version of C++ (a number of C++ features are not included). Programming a
microcontroller is different from programming a computer, there are a number of device-specific
libraries (e.g., changing pin modes, output data on pins, reading analog values, and timers). The
Arduino is programmed in C++. It uses unique libraries for the device.
 While more advanced projects take advantage of the built-in tools in the IDE, most projects rely on
the six buttons found below the menu bar.
 1. The check mark is used to verify the code. To be used once the code has been written.
 2. The arrow uploads the code to the Arduino to run.
 3. The dotted paper creates a new file.
32
  4. The upward arrow is used to open an existing Arduino project.
 5. The downward arrow is used to save the current file.
 6. The right corner button is a serial monitor, which transmits data from the Arduino to the PC for
debugging purposes.

PROGRAMMING LANGUAGE USED

Python is an interpreted high-level programming language used for the general-purpose
programming created by Guido van Rossum developed by Python Software Foundation and first released in
1991. Python has a design philosophy that emphasizes code readability, notably using significant
whitespace. It provides constructs that enable clear programming onboth small and large scales. Python
features a dynamic type system and automatic memory management. Python interpreters are available for
many operating systems. C Python, the reference implementation of Python, is open source software and
has a community-based development model; it performs nearly as all of Python’s other implementations.
Python works on different platforms like Windows, mac, Linux, Raspberry Pi, etc. and it has a simple
syntax that allows developers to write programs with fewer lines than some other programming languages.
Python uses new lines to complete a command, as opposed to other programming languages which often
use semicolons or parenthesis.

33
KEY FEATURES OF PYTHON
• Python language is more expressive means it is more understandable and readable.
• Python downloads with a large library that one can use so we don’t have to write our own code for every
single thing.
• There are libraries for regular expressions, documentation-generation, unit-testing, web browsers,
threading, databases, email, image manipulation, and lot of other functionality.
• Python is a dynamically-typed language means that the type for a value is decided at runtime, not in
advance.
• Hence, there is no need to specify the type of data while declaring it. Since, it is an interpreted language
the interpreter executes the code or statements line by line at a time.

PYTHON GUI
Python provides Graphical User Interface which exhibits one or more windows consisting of
controls known as components which facilitates user to accomplish interactive task. User need not want to
create script or write commands in command prompt. Instead user must be aware of how the programs are
performs to accomplish tasks. It includes Radio buttons, Toolbars, Sliders, Axes etc. Tools also help users
to read and write data and communicate with other GUI’s. Data are displayed in forms of tables or plots in
GUI.

34
JUPITER NOTEBOOK
• The notebook web application: An interactive web application for writing and running code
interactively and authoring notebook documents.

• Kernels: Separate processes started by the notebook web application that runs users’ code in a given
language and returns output back to the notebook web application. The kernel also handles things like
computations for interactive widgets, tab completion and introspection.
• Notebook documents: Self-contained documents that contain a representation of all content visible
in the notebook web application, including inputs and outputs of the computations, narrative text, equations,
images, and rich media representations of objects. Each notebook document has its own kernel.
Notebook web application
The notebook web application enables users to:
• Edit code in the browser, with automatic syntax highlighting, indentation, and tab
completion/introspection.
• Run code from the browser, with the results of computations attached to the code which generated
them.
• See the results of computations with rich media representations, such as HTML, LaTeX, PNG,
SVG, PDF, etc.
• Create and use interactive JavaScript widgets, which bind interactive user interface controls and
visualizations to reactive kernel side computations.
35
• Author narrative text using the Markdown markup language.
• Include mathematical equations using LaTeX syntax in Markdown, which are rendered in-browser
by MathJax.

Kernels
Through Jupyter’s kernel and messaging architecture, the Notebook allows code to be run in a range of
different programming languages. For each notebook document that a user opens, the web application starts
a kernel that runs the code for that notebook. Each kernel is capable of
Python(https://github.com/ipython/ipython
• Julia (https://github.com/JuliaLang/IJulia.jl)
• R (https://github.com/IRkernel/IRkernel)
• Ruby (https://github.com/minrk/iruby)
• Haskell (https://github.com/gibiansky/IHaskell)
• Scala (https://github.com/Bridgewater/scala-notebook)
• node.js (https://gist.github.com/Carreau/4279371)
• Go (https://github.com/takluyver/igo)
The default kernel runs Python code. The notebook provides a simple way for users to pick which of these
kernels is used for a given notebook.
Each of these kernels communicate with the notebook web application and web browser using a JSON over
ZeroMQ/WebSockets message protocol that is described here. Most users don’t need to know about these
details, but it helps to understand that “kernels run code.”
Notebook documents
Notebook documents contain the inputs and outputs of an interactive session as well as narrative text
that accompanies the code but is not meant for execution. Rich output generated by running code,
including HTML, images, video, and plots, is embeddeed in the notebook, which makes it a complete and
self-contained record of a computation
When you run the notebook web application on your computer, notebook documents are just files on your
local filesystem with a ``.ipynb`` extension. This allows you to use familiar workflows for organizing your
notebooks into folders and sharing them with others.
Notebooks consist of a linear sequence of cells. There are three basic cell types:
• Code cells: Input and output of live code that is run in the kernel

36
MACHINE LEARNING MODULE

LINEAR REGRESSION

Linear Regression is used to predict the real values using continuous variables. It is used in many areas
such as Economics, Finance, Biology, etc.

Assumptions in Linear Regression:

• Linear Relationship: The relationship between independent and dependent variables should be linear.
Using the scattered graph, the linearity is tested.

• Little or No Multi Co-linearity between the dependent variable and independent variable.

• Little or No Auto-Correlation: Auto co-relation is the replica of delay of its function. In linear
regression, it is assumed that there is no autocorrelation.

• Dependent Residual errors: It occurs when there is too much dependency among the independent

variables.

37
The equation of the line is given by Yp = Xi(a + b), Where Yp is predicted variable, Xi is independent
variable, a is slope and b is the intercept. The error E is,

which is the square of the difference between actual output to the predicted output, where AP is actual
output and PO is predicted output. The Fig shows the flow chart of LR used in calculating AQI.

CONCLUSION

In this project IoT based on measurement and display of Air Quality Index (AQI), Humidity and
Temperature of the atmosphere have been performed. From the information obtained from the
project, it is possible to calculate Air Quality in PPM. The disadvantage of the MQ135, MQ2, MQ4,
MQ7 sensor is that specifically it can’t tell the Carbon Monoxide or Carbon Dioxide level in the
atmosphere, but the advantage of MQ135, MQ2, MQ4, MQ7 is that it is able to detect smoke, CO,
CO2, NH4, etc harmful gases. After performing several experiments, it can be easily concluded that
the setup is able to measure the air quality in ppm, the temperature in Celsius and humidity in
percentage with considerable accuracy. The results obtained from the experiments are verified
through Google data. Moreover, the led indicators help us to detect the air quality level around the
setup. However, the project experiences a drawback that is it cannot measure the ppm values of the
pollutant components separately. This could have been improved by adding gas sensors for different
pollutants. But eventually, it would increase the cost of the setup and not be a necessary provision to
monitor the air quality. Since it’s an IOT-based project, it will require a stable internet connection
for uploading the data to the ThinkSpeak cloud. Therefore, it is possible to conclude that the
designed prototype can be utilized for air quality, humidity and temperature of the surrounding
atmosphere successfully.

FUTURE SCOPE

The future scope is that device which we are having can be done in a compact way by reducing the
size of the device for further implementation or the modifications which can be is that detecting the
vehicles amount of pollution which can be determined. In future the range can be made increased
38
according to the bandwidth for the high range frequencies. Further research can be made by making
the people in the right direction for their welfare. Therefore, there is another beneficiary by using
this device in an app so the all can be used in an GSM mobile phones for their daily updates by
increasing their range

BIBILOGRAPHY
[1] Air Pollution Prediction Using ML
AUTHORS: - Mushtak Sayyed, Adesh Salunkhe, Akshay Sarode and Swaraj Desai

[2] Air Quality Prediction of Data Log by Machine Learning

AUTHORS: - Venkat Rao Pasupuleti; Uhasri; Pavan Kalyan; Srikanth; Hari Kiran Reddy

[3] Prediction of Air Quality Index by Extreme Learning

Machines AUTHORS: - Burhan BARAN

[4] DETERMINATION OF AIR QUALITY MONITORING & PREDICTION

AUTHORS: - Purvesh Patil, Parth Modi, Ninad Kamble

[5] Air Pollution Prediction using Machine Learning

AUTHORS: - Shreyas Simu; Varsha Turkar; Rohit Martires; Vranda Asolkar; Swizel Monteiro

[6] Urban Air Quality Analysis and Prediction Using Machine

Learning AUTHORS: - K. Nandini; G. Fathima

[7] Air Quality Prediction and Monitoring using Machine Learning Algorithm based
IoT sensor- A researcher's perspective
AUTHORS: - G. Kalaivani; P. Mayilvahanan

[8] Smart City Air Quality Prediction using Machine

Learning AUTHORS: - Rishanti, Murugan, Naveen
Palanichamy

[9] Machine Learning Techniques for Air Quality Forecasting and Study on Real-Time Air
39
Quality Monitoring
AUTHORS: - Varsha Hable-Khandekar; Pravin Srinath

[10] INDIAN AIR QUALITY PREDICTION AND ANALYSIS USING

MACHINE LEARNING
AUTHORS: - Mrs. A. Gnana Soundari, Mrs. J. Gnana Jeslin, Akshaya A.C.

40
APPENDIX A
ACRONYMS

Acronyms are the words which are formed from the first letters of other words, and
which are pronounced as words. The abbreviations used in our project report is as follows:

1. AQI -Air Quality Index

2. RSPM - Respirable Suspended Particulate Matter

3. SDLC - System Development Life Cycle

4. IEEE - Institute of Electrical and Electronics Engineers

41
APPENDIX B
REFERENCES

References contains the bibliographic information about every source cited in

the report. Research materials are not included in the list of references, but rather in
the parts of the report dealing with the research implementation, data, and methods.
All sources cited must be relevant to the work in question. Their use indicates the
extent of study and knowledge associated with the report. An attempt should be
made to use original sources for both domestic and foreign works. Reference is a
note in a report that tells where a piece of information comes from. The main
purpose of including references in project report are as follows:
• To enable readers to retrieve and use the sources.

42