Analysis of Air Pollution Data for Prediction of Air Quality levels.

Abstract

Air pollution is a major threat to the society. The air quality is deteriorating day by day due to
irresponsible and careless approach, so causing a serious impact on human health. Chennai is
one of the important metropolitan city with continuous developments, which is struggling
hard to control air pollution. Air Pollution is on the rise year by year due to problems like
vehicle emission, exhaust fumes from industries, factories, deforestation, and other unnatural
activities. The present study was conducted to find out the air quality based on air pollutant in
Chennai city using Data mining techniques such as Naive Bayes, Support Vector Machine,
Logistic Regression, Random Forest and Decision Tree. Air pollutants like SO2, NO2, and
RSPM were measured in the central part of Chennai such as AnnaNagar, Adyar, Kilpauk, and
T.Nagar from the year 2009 to 2019. The data set were divided into two namely trained data
set for the year 2009-2015 and test data set for the year 2016-2019.In this work , analysis was
done on air pollution data containing pollutants SO2, NO2 and RSPM for predicting Air
Quality levels. Out of five algorithms used, Decision tree algorithm gave better result.