1A: Awareness: Disaster and emergency detection and monitoring
We define disaster situation awareness as the ability of the authorities to effectively and efficiently detect the negative effects of disasters so that aid operations can be planned and executed in a timely manner. In general, the objective is twofold: To understand the type and magnitude of the damage caused and to determine the conditions and locations of the persons that need help.
Examples of research topics are:
Modelling and deriving different kinds of disasters based on core models. Examples of such models can be for example, GIS based topologies, disaster cause models (such as fault lines, sea levels, water ways, etc.), conditions of buildings, ground mechanics, structure of urbanization, etc.
Prediction of disaster and emergency conditions.
Modeling and interfacing a large set of sensors and data sources, such as: Airborne data sources: UAVs, swarm of UAVS, airplanes, Ultrasonic sensors, Space borne data sources: Satellites, GPS trackers, Base stations, Mobile applications, Collapse detectors, Seismic sensors, Water leakage sensors, Gas detectors, Fire and smoke detectors, Camera-based detectors (optical, infrared, etc.), Motion detectors, Face recognizers, People counters, Utility meters (electricity, gas, water), Various kinds of sensors for flooding, Microphones, CO2 meters, Microwave radars, Registration databases, Mobile analysis LABs.
Determining effectiveness and efficiency of the data sources based on disaster and emergency detection criteria. For example:
Maximizing the detection of the effect of disasters and emergency conditions in static and changing conditions
Maximizing the accuracy of the location of alive humans and other relevant living creatures
Minimizing costs
Minimizing the speed of processing (keeping under the timing deadlines)
Sensor and data fusion analysis and design environments
Synthesis op optimal sensor and data fusion configurations
Pattern recognition/classification techniques for different detection types and objectives
Adaptable strategies and mechanisms
Stream processing, complex event processing
Embedded and distributed systems for data gathering and strorage
Edge computing techniques for data processing
Storage of data and big data analytics
Sensor and data source ontologies
IoT networks
Data gathering for improving data processing techniques
Reconfigurable topologies
Machine learning techniques in improving the effectiveness and efficiency in data processing
Modeling emergent disaster and emergency behavior
Detecting/learning the relevant conditions when emergent behavior appears
Detecting/learning the relevant conditions when emergent behavior diminishes
Standardization of sensor and data source interfaces and communication and processing interfaces and protocols