Evidence directed generation of plausible crime scenarios with identity resolution

Given a set of collected evidence and a predefined knowledge base, some existing knowledge-based approaches have the capability of synthesizing plausible crime scenarios under restrictive conditions. However, significant challenges arise for problems where the degree of precision of available intelligence data can vary greatly, often involving vague and uncertain information. Also, the issue of identity disambiguation gives rise to another crucial barrier in crime investigation. That is, the generated crime scenarios may often refer to unknown referents (such as a person or certain objects), whereas these seemingly unrelated referents may actually be relevant to the common revealed. Inspired by such observation, this article presents a fuzzy compositional modeler to represent, reason, and propagate inexact information to support automated generation of crime scenarios. Further, the article offers a link-based approach to identifying potential duplicated referents within the generated scenarios. The applicability of this work is illustrated by means of an example for discovering unforseen crime scenarios.