G H RAISONI INSTITUTE OF ENGINEERING AND TECHNOLOGY, NAGPUR

(Approved by AICTE, New Delhi and Recognized by DTE, Maharashtra)

An Autonomous Institute Affiliated to Rashtrasant Tukadoji Maharaj Nagpur University, Nagpur
Accredited by NAAC with A+ Grade
Department of Computer Science Engineering
PRESENTATION ON

Training + Air Pollution

6 Months Internship at “AOTOM TECHNOLOGY”

Progress Seminar I
College Guide Name:
Presented by Prof. Amreen Khan
1. Dewam Katole (VIII, A, Roll No - 19.) Department of Computer Science Engineering

Company Guide Name:

Mr. Rihal kalbende
Aotom Technology
 Contents

Company Introduction
Introduction (Project)
Literature Review
Problem Statement
Design and Methodology
Tools and Platform used
Work done till Date
Conclusion
References

References
 Company Introduction

Aotom Technology is the tech oriented development and

service provider company in the field of Drone
Technology, Geophysical services, AI technology, Data
analytics, Face recognition technology and Blockchain
technology.

India’s leading B2B market place, Jd Mart ensures

engaging in business activities is a seamless process for
small and medium enterprises as well as large
businesses. In a wake to enable these businesses to
reach their audience, this portal lets them showcase their
offerings in terms of the products and/or services through
a digital catalogue.

This business has a wide range of product offerings and

the product/catalogue list includes Business Center
Services, Business Centre Services, Commercial Hub,
iPhone Application Development Services, IOS Mobile
App Development etc.
 Training

What is Machine Learning?

Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the
use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Machine Learning is a system of computer algorithms that can learn from examples through self-
improvement without being explicitly coded by a programmer. Machine learning is a part of artificial
intelligence which combines data with statistical tools to predict an output that can be used to make
actionable insights.

Machine learning is divided into mainly three types, which are:

Supervised Machine Learning

Unsupervised Machine Learning
Reinforcement Machine Learning
 Training
Supervised Machine Learning
As its name suggests, Supervised machine learning is based on supervision. It means in the supervised learning
technique, we train the machines using the "labelled" dataset, and based on the training, the machine predicts the
output. Here, the labelled data specifies that some of the inputs are already mapped to the output. More
preciously, we can say; first, we train the machine with the input and corresponding output, and then we ask the
machine to predict the output using the test database

Categories of Supervised Machine Learning

1.Classification
Classification algorithms are used to solve the classification problems in which the output variable is categorical,
such as "Yes" or No

2.Regression
Regression algorithms are used to solve regression problems in which there is a linear relationship between input
and output variables. These are used to predict continuous output variables,
such as market trends, weather prediction
 Training
Unsupervised Machine Learning
Unsupervised learning is different from the Supervised learning technique; as its name suggests, there is no
need for supervision. It means, in unsupervised machine learning, the machine is trained using the unlabeled
dataset, and the machine predicts the output without any supervision.

Reinforcement Learning
Reinforcement learning works on a feedback-based process, in which an AI agent (A software component)
automatically explore its surrounding by hitting & trail, taking action, learning from experiences, and improving its
performance
 Training
BLOCKCHAIN TECHNOLOGY

Blockchain is a trending and booming word in today’s technology and this technology is described as the most
disruptive technology of the decade.

Thus, Blockchain is used for the secure transference of items like money, contracts, property rights, stocks, and
even networks without any requirement of Third Party Intermediaries like Governments, banks, etc.

Once the data is stored in the Blockchain it becomes very difficult to manipulate the stored data. A Blockchain is
a Network Protocol like SMTP.

However, Blockchain cannot be run without the Internet. Block Chain is useful in many areas like Banking,
Finance, Healthcare, Insurance, etc.
 Training
What is Blockchain?
A blockchain is an open, distributed ledger that can record transactions between two parties efficiently and in a
verifiable and permanent way without the need for a central authority
Blockchain can be defined as the Chain of Blocks that contain some specific Information. Thus, a Blockchain is a
ledger i.e file that constantly grows and keeps the record of all transactions permanently. This process takes
place in a secure, chronological (Chronological means every transaction happens after the previous one) and
immutable way. Each time when a block is completed in storing information, a new block is generated.
Key Characteristics:

Open: Anyone can access blockchain.

Distributed or Decentralised: Not under the control of any single authority.

Efficient: Fast and Scalable.

Verifiable: Everyone can check the validity of information because each node maintains a copy of the
transactions.

Permanent: Once a transaction is done, it is persistent and can’t be altered

 Training
Distributed Systems

Understanding distributed systems is essential to our understanding blockchain, as blockchain was a distributed
system at its core. It is a distributed ledger that can be centralized or decentralized. A blockchain is originally
intended to be and is usually used as a decentralized platform. It can be thought of as a system that has
properties of the both decentralized and distributed paradigms. It is a decentralized-distributed system.

In a distributed system, data and computation are spread across multiple nodes in the network. Sometimes, this
term is confused with parallel computing. While there is some overlap in the definition, the main difference
between these systems is that in a parallel computing system, computation is performed by all nodes
simultaneously in order to achieve the result; for example, parallel computing platforms are used in weather
research and forecasting, simulation, and financial modeling. On the other hand, in a distributed system,
computation may not happen in parallel and data is replicated across multiple nodes that users view as a single,
coherent system. Variations of both of these models are used to achieve fault tolerance and speed. In the parallel
system model, there is still a central authority that has control over all nodes and governs processing. This
means that the system is still centralized in nature. The critical difference between a decentralized system and
distributed system is that in a distributed system, there is still a central authority that governs the entire system,
whereas in a decentralized system, no such authority exists.
 Introduction (project)

The Environment is nothing but everything that encircles us. The environment is getting polluted due to
human activities and natural disaster, very severe among them is air pollution.

The concentration of air pollutants in ambient air is governed by the meteorological parameters such as
atmospheric wind speed, wind direction, relative humidity, and temperature.

If the humidity is more, we feel much hotter because sweat will not evaporate into the atmosphere.
Urbanization is one of the main reasons for air pollution because, increase in the transportation facilities
emits more pollutants into the atmosphere and another main reason for air pollution is Industrialization.

The major pollutants are Nitrogen Oxide (NO), Carbon Monoxide (CO), Particulate matter (PM), SO2
etc. Carbon Monoxide is produced due to the deficient Oxidization of propellant such as petroleum, gas,
etc. Nitrogen Oxide is produced due to the ignition of thermal fuel; Carbon monoxide causes headaches,
vomiting; Benzene is produced due to smoking, it causes respiratory problems; Nitrogen oxides causes
dizziness, nausea; Particulate matter with a diameter 2.5 micrometer or less than that affects more to
human health.Measures must be taken to minimize air pollution in the environment.

Sr. No Paper Title and its Author
1 Djebbri, Nadjet, and
MouniraRouainia.
”Artificial neural
networksbased air pollution
monitoring inindustrial
sites.”
2 Ayele, TemeseganWalelign,
and RutvikMehta.”Air
pollution monitoring and
prediction using IoT.”
Literature Review
Details of Publication
In 2017 International
Conference on Engineering
and Technology (ICET), pp.
1-5. IEEE,2017.
In 2018 Second International
Conference on Inventive
Communication (ICICCT),
pp. 1741-1745. IEEE,2018.
Findings
proposed artificial based Regressive model which is nonlin
to predict 2 major air pollutants such as carbon monoxide a
nitrogen oxides. They have considered the variables such as
speed of the air, temperature, and moisture . They have us
RMSE and MAE to determine the performance, but t
method considered only 2 pollutants such as NO and CO
other major pollutants such as sulfur dioxide, PM2.5, PM10
not considered.
proposed an IoT based technique to obtain air quality data s
They have used Long Short-term Memory [LSTM] techniq
in-order to predict the air quality the proposed techniq
achieved better accuracy by reducing the time taken to train
model. But still, the accuracy can be improved by compar
other techniques such as the Random forest method.

Sr. Paper Title and its Author
N
o
3 Verma, Ishan, Rahul Ahuja,
HardikMeisheri, andLipikaDey.
”Air pollutant severity rediction
using Bi-directional LSTM
Network.”
4 Figures Zhang, Chao, Baoxian Liu,
Junchi Yan, Jinghai Yan, Lingjun
Li, Dawei Zhang, XiaoguangRui,
and RongfangBie. ”Hybrid
Measurement of Air Quality as a 5
Fig. 8. RH w.r.t tin oxide Fig. 9.
RH w.r.t C6H6 Mobile Service: An
Image Based Approach.”
Literature Review
Details of Publication Findings
In 2018 described the benefits of the Bidirectional Long - Short
IEEE/WIC/ACM Memory method to forecast the severity of air pollution. The
International proposed technique achieved better prediction which models
Conference on Web the long term, short term, and critical consequence of PM2.5
Intelligence (WI), pp. severity levels. In the proposed method prediction is made at
651-654. IEEE, 2018. 6h, 12h, 24h.
In 2017 IEEE proposed web service methodology to predict air quality. They
International provided service to the mobile device, the user to send photos
Conference on Web of air pollution 2 modules a) GPS location data to retrieve the
Services (ICWS), pp. assessment of the quality of the air from nearby air quality
853- 856. IEEE,2017. stations. b) they have applied dictionary learning and
convolution neural network on the photos uploaded by the
user to predict the air quality but this method has a
disadvantage in learning stability due to this the results are
less accurate.
 Problem Statement

• The project aims to develop the remote air quality monitoring device which are easy to be
dispatched and can help us to monitor air quality from a distance

• To build a dashboard where we can see the results about the air quality and obtain greater
results
 Design and Methodology

India
 Tools & platform used
• Programming Languages:-Python

• Database:- Sql

• Visualization:- power bi,pandas, matplotlib

• Hardware Devices:-
• Arduino Uno
• Mq135
• Mq7
• Mq3

• Dataset:- Microsoft excel

• For more Details of sensor and their information Please visit this link:-
https://www.techtarget.com/whatis/definition/sensor#:~:text=A%20sensor%20is%20a
%20device,number%20of%20other%20environmental%20phenomena.
 Work done till Date
Work done till Date

• Studied the basics of Machine learning

• Studied the basics of Distributed systems and blockchain

• Successfully collected the data set using sensors.

• Successfully completed paper review .

• Completed data cleaning and pre-processing required such as outlier removal techniques etc.

• We have done visualization for getting using insights from the dataset.
 Conclusion

The concentration of air pollutants in ambient air is governed by the meteorological

parameters such as atmospheric wind speed, wind direction, relative humidity,
temperature and many more. We have used various attributed to measure the
quality of air. The proposed work is a machine learning and deep learning approach
using different algorithms such as random forest ,linear regression , lstm etc . The
result show the prediction of air quality.
 References
[1] Kumar, Dinesh. ”Evolving Differential evolution method with random forest for prediction of Air Pollution.”
Procedia computer science 132 (2018): 824-833.
.

[2] Yang, Ruijun, Feng Yan, and Nan Zhao. ”Urban air quality based on Bayesian network.” In 2017 IEEE 9th
Fig. 10. RH w.r.t NO Fig. 11. RH w.r.t NO2 INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY
RESEARCH VOLUME 9, ISSUE 04, APRIL 2020 ISSN 2277-8616 123 IJSTR©2020 www.ijstr.org International
Conference on Communication Softwareand Networks (ICCSN), pp. 1003-1006. IEEE,2017.

[3] Jiang, Ningbo, and Matthew L. Riley. ”Exploring the utility of the random forest method for forecasting ozone
pollution in SYDNEY.” Journal of Environment Protection and Sustainable Development 1.5 (2015): 245-254.

[4] Djebbri, Nadjet, and MouniraRouainia. ”Artificial neural networksbased air pollution monitoring inindustrial
sites.” In 2017 International Conference on Engineering and Technology (ICET), pp. 1-5. IEEE,2017.
Thank you !