Dealing with air pollution presents a major environmental challenge in smart city environments. Real-time monitoring of pollution data enables local authorities to analyze the current traffic situation of the city and make decisions accordingly. Deployment of the Internet of Things-based sensors has considerably changed the dynamics of predicting air quality. Existing research has used different machine learning tools for pollution prediction; however, comparative analysis of these techniques is required to have a better understanding of their processing time for multiple datasets. In this paper, we have performed pollution prediction using four advanced regression techniques and present a comparative study to determine the best model for accurately predicting air quality with reference to data size and processing time. We have conducted experiments using Apache Spark and performed pollution estimation using multiple datasets. The Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) have been used as evaluation criteria for the comparison of these regression models. Furthermore, the processing time of each technique through standalone learning and through fitting the hyperparameter tuning on Apache Spark has also been calculated to find the best-fit model in terms of processing time and lowest error rate.

Air pollution is a major environment issue in smart cities. Millions of people around the world are at health risk due to the air pollution. Real-time monitoring of Air Quality helps to identify the current situation of city which helps the government and inhabitants to take precautionary measures. Internet of things (IoT) based sensors have changed the way for monitoring of Air Quality Index (AQI). However, requirements of architecture for analyzing and monitoring of large data generated by the IoT devices are not fulfilled. In this article, we have proposed Apache Spark based architecture for smart urban planning which makes use of the big data analytics in classifying the air quality. The proposed architecture is implemented on the data set of vehicles pollution of Aarhus city in Denmark. The results show that the proposed architecture is efficient and accurate for analyzing and classifying the AQI.

Maintaining and understanding large software systems is a complex and time consuming process.Understanding the internal structure of such systems is not an easy task due to the invisible nature of software.Source Code Visualization, i.e. measuring the code metrics and then visualizing them, provides an efficient solution to this problem.There are many tools available which gives an insight to the internal structure of the software.But all of them don"t provide visualizations of hierarchical relationships and code complexity of the source code.In this paper, we present a tool named "SourceViz".This application computes different software metrics, code complexity, class-relations and then visualizes the calculated metrics in different metaphors.This visual analysis assists the project managers and software developers in understanding the static structure of the software by presenting project-level as well as class-level view.