Published Paper Details:

In the context of smart cities, dealing with air pollution is a significant environmental challenge. Real-time monitoring of pollution data enables local authorities to analyze the current the situation of the city and make decisions accordingly. However, a comparison of various strategies is needed to better understand how long they take to process different datasets. Existing research has used a variety of machine learning algorithms for pollution prediction. There are various regression techniques for this purpose and a comparative study to determine the best model for accurately predicting air quality with reference to data size and processing time. In this project, we have selected the algorithms with fewer errors and higher accuracy, and the study combines those algorithms and creates a sample algorithm using the combination of these algorithms which involves the Random Forest Algorithm, Support Vector Machine Algorithm, Linear Regression, Decision Tree, etc. Using this, prediction of the level of pollution will be efficiently done