COMPARISON OF PREDICTIVE MODELS IN DATA MINING AND IMPACTS OF AIR POLLUTION IN METROPOLITAN CITIES

Abstract

In the past decades, as a result of the enormous environmental load, the air quality in the city has worsened in India. The remarkable increase in vehicle population and industries has led to the concentration of air pollutants in major metropolitan cities. The behavior of the air pollutants has a severs mash on human health and environment. To safeguard human health, the health risks posed by the increasing rate of air pollution on a wide scale must be projected and predicted. Monitoring and forecasting the vast amounts of data generated from numerous monitoring stations across the city has been a topic of debate. This led to the scientist to look for several predicting data mining techniques and big data analytics to monitor and predict the urban air quality. Data mining combines statistical, machine learning, and graphical approaches to extract information into a format that can be used in a variety of real-world applications. This study applies data mining to uncover the hidden knowledge of air pollution distribution in the voluminous data retrieved from monitoring stations National Air Monitoring Program (NAMP) station , National Ambient Air Quality (NAAQ) standards, Central Pollution Control Board. This article covers several ways to predicting urban air quality using data mining techniques such as linear regression, back propagation, and big data analytics such as Map reduction and Geostatistical algorithms