International Symposium on Networks, Computers and Communications (ISNCC), İstanbul, Türkiye, 18 - 20 Haziran 2019
Air pollution (AP) is a major problem for public health. To reduce effect of AP, air quality monitoring stations are deployed world-wide. But in addition to monitoring, by predicting air pollution levels, peoples exposure to pollution can be further reduced. In this work, we firstly review air quality (AQ) prediction literature in an algorithmic point-of-view. Then we introduce a new AQ prediction framework. The proposed framework utilizes Complex Event Processing to process huge amount of data in near real time. Fog Computing is utilized to achieve scalability, extendibility and Software Defined Network utilized to enhance manageability of the network. In this paper, we explain the network architecture and methodology behind the framework. The proposed framework can operate in near real time and does not need any human assistance.