Technical and Social sensor aggregation for smart environment enhancement

The uptake of urban city monitoring systems has been synonymous with the rise of Internet of Things (IoT) technologies since their conception. These systems are increasingly incorporated in a wide range of domains, such as disaster awareness, management, and prevention by contextualizing events. In this study, we have developed a platform capable of capturing and associating data from both social media and sensing devices, towards early discovery of disaster-related events by authorities and citizens alike. Establishing these points of association, which we dub as the 'Feedback Loop', forms the basis of our research endeavors. In this paper, we present the architectural components put in place to realize this, at the hardware and software level, as well as the challenges we had to overcome in deploying these at scale within the Engomi Business Region of Nicosia, Cyprus. Pivotal to its final form involved the utilization of Big Data processing technologies to allow for flexibility of sensor deployment and high availability throughout its lifetime. Coupled with state-of-the-art Natural Language Processing (NLP) and anomaly detection algorithms, geared towards spatiotemporal sensor data and natural language processing, our eco-system features a holistic solution towards enhanced decision support.