SVM Aggregation Modelling for Spatio-temporal Air Pollution Analysis

This study is concerned with computation methods for environmental data analysis in order to enable facilitate effective decision making when addressing air pollution problems. A number of environmental air pollution studies often simplify the problem but fail to consider the fact that air pollution is a spatio-temporal problem. This research addresses the air pollution problem as spatio-temporal problem by proposing a new decentralized computational technique named Online Scalable SVM Ensemble Learning Method (OSSELM). Special consideration is given to distributed ensemble in order to resolve the spatio-temporal data collection problem i.e., the data collected from multiple monitoring stations dispersed over a geographical location. Moreover, the air pollution problem is address systematically including computational detection, examination of possible causes, and air-quality prediction.