Context-Aware Framework for Enhanced Smart Urban Pollution Monitoring and Control

Smart pollution monitoring approaches based on wireless sensor networks (WSNs) have progressed significantly over the past decade. More recently, intelligent computational strategies based on internet-of-things (IoT) and cloud computing (CC) have gained much momentum in the related studies. In this study, a smart context-aware environmental pollution monitoring and control scheme is presented for an urban setting to demonstrate how effective pollution mitigation and control can be achieved by the integration of known hardware and software approaches in a feedback control system. As a main contribution, this work shall describe in detail how the hardware infrastructure that consists of internet-of-things (IoT) and either cellular or non-cellular communications, is combined with machine learning (ML) software algorithms to provide informed environment control decisions/signals for dynamically and optimally updating the status of our environmentally controlled mitigation strategies. Finally, the importance of this work is clear as the framework and architecture can also be applied to other urban settings and mitigation strategies that can be optimized using intelligent and context-aware control signals.