International Journal of Innovative Technology and Exploring Engineering (IJITEE)
ISSN: 2278-3075, Volume-8, Issue-9S4, July 2019
206
Published By:
Blue Eyes Intelligence Engineering
& Sciences Publication
Retrieval Number: I11320789S419/19©BEIESP
DOI:10.35940/ijitee.I1132.0789S419
Abstract: Generally, Air pollution alludes to the issue of toxins
into the air that are harmful to human well being and the entire
planet. It can be described as one of the most dangerous threats
that the humanity ever faced. It causes damage to animals, crops,
forests etc. To prevent this problem in transport sectors have to
predict air quality from pollutants using machine learning
techniques. Subsequently, air quality assessment and prediction
has turned into a significant research zone. The aim is to
investigate machine learning based techniques for air quality
prediction. The air quality dataset is preprocessed with respect to
univariate analysis, bi-variate and multi-variate analysis, missing
value treatments, data validation, data cleaning/preparing. Then,
air quality is predicted using supervised machine learning
techniques like Logistic Regression, Random Forest, K-Nearest
Neighbors, Decision Tree and Support Vector Machines. The
performance of various machine learning algorithms is
compared with respect to Precision, Recall and F1 Score. It is
found that Decision Tree algorithm works well for predicting air
quality. This application can help the meteorological
Department in predicting air quality. In future, this work can be
optimized by applying Artificial Intelligence techniques.
Keywords: classification, air quality index, python, accuracy,
forecasting.
I. INTRODUCTION
Machine learning is to predict the future from past data.
Computer studying (ML) is a style of artificial intelligence
(AI) that delivers computers the capability to gain
knowledge of without being explicitly programmed.
Machine finding out makes a speciality of the progress of pc
applications that can alternate when exposed to new
information and the basics of laptop studying,
implementation of a easy laptop finding out algorithm
utilising python. Process of coaching and prediction
involves use of specialised algorithms. It feed the training
data to an algorithm, and the algorithm uses this training
knowledge to offer predictions on a brand new test
information. Machine finding out can be roughly separated
in to three classes. There are supervised learning,
unsupervised finding out and reinforcement finding out.
Supervised studying software is each given the input
knowledge and the corresponding labeling to be trained data
must be labeled with the aid of a person previously.
Unsupervised learning isn't any labels.
Revised Manuscript Received on July 13, 2019.
K. Mahesh Babu, UG Student, Department of Computer Science &
Engineering, Saveetha School of Engineering.
J. Rene Beulah, Assistant Professor, Department of Computer Science
& Engineering, Saveetha School of Engineering
It provided to the learning algorithm. This algorithm has
to figure out the clustering of the input knowledge.
Subsequently, Reinforcement learning dynamically interacts
with its environment and it receives positive or bad
suggestions to toughen its efficiency.
Data scientists use many one of a kind types of computing
device learning algorithms to observe patterns in python that
lead to actionable insights. At a high stage, these specific
algorithms can also be labeled into two companies situated
on the way they “gain knowledge of” about data to make
predictions: supervised and unsupervised learning.
Classification is the method of guessing the class of given
information points. Lessons are in many instances referred
to as goals/ labels or classes. Classification predictive
modeling is the task of approximating a mapping function
from enters variables(X) to discrete output variables(y). In
computer studying and facts, classification is a supervised
studying technique in which the pc software learns from the
information input given to it after which makes use of this
studying to classify new statement. This data set could
without problems be bi-classification (like deciding upon
whether the man or woman is male or female or that the
mail is unsolicited mail or non-spam) or it may be multi-
classification too. Some examples of classification problems
are: speech consciousness, handwriting awareness, bio
metric identification, file classification and so forth.
II. EXISTING SYSTEM
Urban air pollutant attention forecast is coping with a
surge of large ecological monitoring data and intricate
alterations in air pollution. This necessitates effective
estimating methods to strengthen prediction accuracy and
avoid grave contamination episodes, thereby improving
ecological administration resolution-making capacity. A
brand new contaminant concentration estimation process is
established on sizeable amounts of ecological knowledge
and deep learning approaches. This integrates colossal data
using two forms of deep networks. This system is situated
on a design that uses a Convolutional Neural community as
the bottom layer, routinely extracting features of enter
information. An extended quick term reminiscence network
is used for the output layer to keep in mind the time
dependence of pollution. It consists of these two deep
networks. With performance optimization, the model can
predict future particulate topic (PM2:5) concentrations as
time series. Sooner or later, the estimation outcome are
related with the outcome of numerical models. The
applicability and benefits of the mannequin are also
analyzed.
Air Quality Prediction based on Supervised
Machine Learning Methods
K. Mahesh Babu, J. Rene Beulah