Prediction and Analysis of Air Quality Index using Machine Learning Algorithms

Pollution is the most indispensable and upsetting issues faced in today’s day to day life in the world. Over 5000 individuals will lose their life daily due to the various infections of pollution. Air contamination has been perceptible as one of the main issues of metropolitan regions all over the globe, solely in Delhi, Beijing and Tehran and so on. The Air Quality Index (AQI) is a metric used for recording the day-to-day air quality. It indicates the public precisely the percentage of air contamination and also informs the allied health effects associated with it. With the fast improvement in the accessibility of information and computational advancements, different machine learning algorithms have been proposed for anticipating air contamination. The primary view of the general work is to initially ascertain the air quality file values which turns into the objective information, later use it to dissect and anticipate the air quality file by utilizing different various machine learning algorithms such as Decision Tree Regression (DTR), Linear Regression (LR), Random Forest Regression (RFR) and Support Vector Regression (SVR)and to make a relative investigation for better performance and accuracy. The outcomes show that RFR performs better when compared with different methods.