Semantic reasoning for intelligent emergency response applications

Abstract

Emergency response applications require the processing of large amounts of data, generated by a diverse set of sensors and devices, in order to provide for an accurate and concise view of the situation at hand. The adoption of semantic technologies allows for the definition of a formal domain model and intelligent data processing and reasoning on this model based on generated device and sensor measurements. This paper presents a novel approach to emergency response applications, such as fire fighting, integrating a formal semantic domain model into an event-based decision support system, which supports reasoning on this model. The developed model consists of several generic ontologies describing concepts and properties which can be applied to diverse context-aware applications. These are extended with emergency response specific ontologies. Additionally, inference on the model performed by a reasoning engine is dynamically synchronized with the rest of the architectural components. This allows to automatically trigger events based on predefined conditions. The proposed ontology and developed reasoning methodology is validated on two scenarios, i.e. (i) the construction of an emergency response incident and corresponding scenario and (ii) monitoring of the state of a fire fighter during an emergency response.