A Classification of Urban Air Pollution and Respiratory Diseases in the Metropolitan Region using Data mining concept.
Data mining is the process of analyzing large data sets (Big Data) from different perspectives and finding hidden facts and patterns to summarize them into useful information. Nowadays data mining is combined with many latest techniques such as artificial intelligence, statistics, data science, database theory and machine learning. It includes few important data mining techniques such as Classification, clustering, regression, association rules, outer detections, sequential patterns, and prediction. In this paper, we study relation between air pollution in urban area and relevant disease of human in different living conditions using data mining concept. The gaseous air pollutants of primary concern in urban settings include sulfur dioxide, nitrogen dioxide, and T-carbon monoxide. To achieve the study, a retrospective study data was collected from primary health centers in Bangalore industry areas where the most air pollutant happening. The goal of this study is to better understand the regional patterns of air pollution and respiratory illnesses. The inventories from different area in cities in the Bangalore Metropolitan Region were used to demonstrate data preparation and multivariate analysis. In order to forecast epidemics, a predictive model with high accuracy was built. This result shows that the exposure of the pollution level significantly influenced the respiratory illness in human.