Danger-system: Exploring new ways to manage occupants safety in smart building

Safety has always been a main concern in complex buildings: automated solutions to respond to crisis events limiting damages and victims have been researched and adopted in commercial and private buildings since late 19th century. However, the methods available have some limitations: for example the impossibility to promptly detect false alarms and to provide context-dependent notification, which are fundamental to persuade tenants to a fast egress. In this paper we present the architecture of a system for the detection and management of emergencies in smart buildings. The designed architecture shows some novelties and key features which distinguish it from already existing solutions. Indeed, the proposed architecture exploits the existing building management systems leveraging mobile crowd sensing to collect valuable information during a crisis. The new generation of mobile devices are used to dispatch notification and collect users feedback. In order to test and validate the system, we have built a simulation framework which simulates the building environment.