Multi-disciplinary approaches to intelligently sharing large-volumes of real-time sensor data during natural disasters

Authors: Middleto, S.E., Sabeur, Z.A., Löwe, P., Hammitzsch, M., Tavakoli, S. and Poslad, S.

Journal: Data Science Journal

Volume: 12

eISSN: 1683-1470

DOI: 10.2481/dsj.WDS-018

Abstract:

We describe our knowledge-based service architecture for multi-risk environmental decision-support, capable of handling geo-distributed heterogeneous real-time data sources. Data sources include tide gauges, buoys, seismic sensors, satellites, earthquake alerts, Web 2.0 feeds to crowd source 'unconventional' measurements, and simulations of Tsunami wava propagation. Our system of systems multi-bus architecture provides a scalable and high performance messaging backbone. We are overcoming semantic interoperability between heterogeneous datasets by using a self-describing 'plug-in' data source approach. As crises develop we can agilely steer the processing server and adapt data fusion and mining algorithm configurations in real-time.

Source: Scopus