Air Quality Analysis and Smog Detection in Smart Cities for Safer Transport using Machine Learning (ML) Regression Models

Abstract

A smart city is a technologically modern urban area in which different electronic methods, and multiple advanced features based on Information and Communication Technologies (ICT) are developed. The Smart Transport is one of the important functions of a smart city which facilitates a smooth movement of vehicles and allows citizens a safe and luxurious journey experience. The two major reasons that are responsible for accidents and mishaps on urban highways are the excess pollution of the air and the smog. The smog is a mixture smoke and fog, and it is composed of ozone (O3) and the particulate matter like pollen, dust, sulphur oxides, etc. Thus, if the air pollutants and their concentration is determined, we can easily detect the presence of the smog in the air. In this paper different machine learning regression models namely Polynomial Regression Model, Decision Tree Regression Model, Random Forest Regression Model, and Support Vector Regression Model are used for the prediction of Air Quality Index (AQI) from which the pollutant concentration can be determined, which will help to detect the smog. The results of the implementation show that the Random Forest Regression Model gives a better result of prediction amongst all the five models.