This paper describes the architecture and requirements of an integrated system that is needed to support command and control for the interoperability-capability focus area. The architecture is designed to enhance situational awareness during emergencies such as earthquakes, volcanic eruptions, wild fires, floods, tsunamis, mud slides, storms, tornadoes, hurricanes, extreme heat, extreme cold, massive disease outbreaks, wars, terrorist attacks, power outages, cyber-attacks on utility grids and civil unrest. A net-centric approach that emphasizes cognitive aspects, such as cognitiveinformation operations, in decision support ensures information superiority by networking sensors and human-factors monitoring. This enables decision makers to achieve shared awareness. Linking knowledgeable entities effectively leads to increased speed of command and a higher tempo of operations with a degree of self-synchronization. The resulting system will decrease cognitive overload and improve cognitive monitoring by providing a more systematic and less labor-intensive method to manage information from and for first responders at the local, tribal, state, and federal levels.

Recognizing that a community's capability to respond to and recover from disaster depends partly on the strength and effectiveness of its social networks, social network analysis (SNA) has risen to a field having important implications. In particular, many disaster and emergency recovery operations now consider the information provided by social networks to be one of their prime sources of data. The task of integrated social information engineering is to fuse that data to yield meaningful knowledge devoid of contradiction and provide a pathway for discovery of related information. Computing with Words represents an attempt to fuse linguistic information using possibilistic analysis. The approach entails machine learning that fuses contexts consisting of essentially symbolic information for the prediction of an appropriate action(s). SNA is facilitated because the method allows large contexts and crowd sourced approaches, consisting of distinct textual phrases, to be mapped to similar prior experiential knowledge. If this knowledge proves to be erroneous for any reason, then it is a simple matter to supply the correct knowledge for non monotonic learning to occur. The method also supplies an associated possibility, allows for proper responses to be forthcoming, and can be trained / run in parallel. In summary, the paper proper considers the burgeoning field of social information engineering and the automation of its integration by way of transformative reuse.