Integration and Exploitation of Sensor Data in Smart Cities through Event-Driven Applications

Abstract

Smart cities are urban environments where Internet of Things (IoT) devices provide a continuous source of data about urban phenomena such as traffic and air pollution. The exploitation of the spatial properties of data enables situation and context awareness. However, the integration and analysis of data from IoT sensing devices remain a crucial challenge for the development of IoT applications in smart cities. Existing approaches provide no or limited ability to perform spatial data analysis, even when spatial information plays a significant role in decision making across many disciplines. This work proposes a generic approach to enabling spatiotemporal capabilities in information services for smart cities. We adopted a multidisciplinary approach to achieving data integration and real-time processing, and developed a reference architecture for the development of event-driven applications. This type of applications seamlessly integrates IoT sensing devices, complex event processing, and spatiotemporal analytics through a processing workflow for the detection of geographic events. Through the implementation and testing of a system prototype, built upon an existing sensor network, we demonstrated the feasibility, performance, and scalability of event-driven applications to achieve real-time processing capabilities and detect geographic events.

Interoperable Open Specifications Framework for the Implementation of Standardized Urban Platforms

“…Continuing with data integration research results, authors of [32] analyses an approach for spatiotemporal data representation integrated into a reference architecture for event-driven applications. Again, heterogeneity and multi-domain data are particularly challenging in order to provide unified decision-making tools.…”

“…In this sense, geographic information is important, being not fully addressed in current solutions for spatial data analysis. However, the results from [32] show services that are triggered by a geographic event (e.g., traffic accident), while a city requires different levels of analytics: real-time processing without the need of a trigger, event, schedule . .…”

“…, which is considered within the proposed framework in this paper. In fact, according to the comparison performed within [32] for multiple smart city platforms [33][34][35][36][37]; scalability, privacy and security, processing at different levels (batch, real-time) and analytics are features that are still not fully addressed, then failing in the holistic view of the Urban Platform as Smart City solution. It establishes SensorThingsAPI as a more efficient communication protocol than the previous ones.…”

“…It establishes SensorThingsAPI as a more efficient communication protocol than the previous ones. Finally, RASCA architecture [32] is proposed where some aspects are neglected such as privacy, security or northbound interoperability, among others.…”

Smart Cities Big Data Algorithms for Sensors Location

“…The classification is carried out in parallel with the training process-while some data are classified, others are used for training to observe possible changes in the patterns, or to decrease process time by a possible reduction in the number of variables of the model. In this phase, a frequency matrix is generated that works in conjunction with a neighboring sensor matrix in order to identify the hot-zones and present their visualization in a geo-referenced map [19,20].…”