Distributed classification in a multi-source environment

Current methods of determining the classification of objects (such as aircraft) across the battlespace in military systems are by design, stovepiped, platform-centric designs. Classification data and information are generally either sent at a very low level (e.g. every contributing response) or worse, as a decision such as "FRIEND" or "F-16" without metrics to quantify the level of assurance of the decision. The former method potentially overwhelms a large network when many nodes are simultaneously reporting and receiving information. The latter method leaves each receiving node with no information to help resolve differences between its local decisions, and those coming from other nodes. In this paper, a method to share information that allows for distributed decisions across multiple nodes is given. It is based on a "classification vector" that conveys probabilistic and evidential object information, as well as measurements of information content and confusion.