Distributed Perception Networks for Crisis Management

Abstract

Situation assessment in crisis management applications can be supported by automated information fusion systems, such as Distributed Perception Networks. DPNs are self-organizing fusion systems that can infer hidden events through interpretation of huge amounts of heterogeneous and noisy observations. DPNs are a logical layer on top of existing communication, sensing, processing and data storage infrastructure. They can reliably and efficiently process information of various quality obtained from humans and sensors through the existing communication systems, such as mobile phone networks or internet. In addition, modularity of DPNs supports efficient design and maintenance of very complex fusion systems. In this paper, a fully functional prototype of a DPN system is presented that fuses information from gas sensors and human observations. The task of the system is to compute probability values for the hypothesis that a particular gas is present in the environment. It is discussed how such a system could be used for crisis management.