College of Engineering and Computing
Permanent URI for this community
Browse
Browsing College of Engineering and Computing by Subject "Bayesian"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item DTB Project: A Behavioral Model for Detecting Insider Threats(MITRE Corporation, 2005-05) Costa, Paulo C. G.; Laskey, Kathryn B.; AlGhamdi, Ghazi; Barbará, Daniel; Shackelford, Thomas; Mirza, Sepideh; Revankar, MehulThis paper describes the Detection of Threat Behavior (DTB) project, a joint effort being conducted by George Mason University (GMU) and Information Extraction and Transport, Inc. (IET). DTB uses novel approaches for detecting insiders in tightly controlled computing environments. Innovations include a distributed system of dynamically generated document-centric intelligent agents for document control, object oriented hybrid logic-based and probabilistic modeling to characterize and detect illicit insider behaviors, and automated data collection and data mining of the operational environment to continually learn and update the underlying statistical and probabilistic nature of characteristic behaviors. To evaluate the DTB concept, we are conducting a human subjects experiment, which we will also include in our discussion.Item MEBN Logic: A Key Enabler for Network Centric Warfare(CCRP Publications, 2005-06) Costa, Paulo C. G.; Laskey, Kathryn B.; Takikawa, Masami; Pool, Michael; Fung, Francis; Wright, Edward J.Among the lessons learned from recent conflicts stands the dramatic change in the very way wars are fought. There are no more clear-cut enemies or allies; rules of engagement have become increasingly fuzzy; guerrilla and insurgent tactics are now commonplace: in short, the battlespace is a very different place from what it used to be. Furthermore, advances in sensor technology and network computing have brought a new element to the complex equation of warfare: information overload. Nowadays, instead of merely gathering information and displaying assets, command and control systems must be able to fill the gap between the glut of information arriving from a networked grid of sensors and the capacity of human commanders to make sense of it. In short, the quest today is for systems that work under the knowledge paradigm. Systems must automatically provide decision makers with a clear picture of what is happening, how it relates to the current situation, and what are the options and their respective consequences. Facing this challenge with technologies of the past is a recipe for failure. New, more powerful approaches are needed. The objective of this paper is to argue for two claims: (1) Bayesian decision theory is an appropriate technology for modeling human decision-making in complex, ambiguous scenarios; and (2) Bayesian reasoning technology is a promising enabler for Network Centric Warfare. To support both claims, we have applied Multi-Entity Bayesian Networks (MEBN) to model a historical tactical decision from the naval domain. MEBN is a breakthrough Bayesian reasoning system in which complex probabilistic models are constructed from modular components that can be replicated and combined in an infinite variety of ways. MEBN allows models to capture important and subtle aspects of objects and their interrelationships that would be impossible to model using existing technologies. We provide a brief overview of modeling in MEBN and then present our model and the outcome of applying it to a historical scenario. Our results clearly support the validity of our approach.Item PR-OWL: A Bayesian Framework for the Semantic Web(2005-11-07) Costa, Paulo C. G.; Laskey, Kathryn B.; Laskey, Kenneth J.This paper addresses a major weakness of current technologies for the Semantic Web, namely the lack of a principled means to represent and reason about uncertainty. This not only hinders the realization of the original vision for the Semantic Web, but also creates a barrier to the development of new, powerful features for general knowledge applications that require proper treatment of uncertain phenomena. We propose to extend OWL, the ontology language recommended by the World Wide Web Consortium (W3C), to provide the ability to express probabilistic knowledge. The new language, PR-OWL, will allow legacy ontologies to interoperate with newly developed probabilistic ontologies. PR-OWL will move beyond the current limitations of deterministic classical logic to a full first-order probabilistic logic. By providing a principled means of modeling uncertainty in ontologies, PR-OWL will serve as a supporting tool for many applications that can benefit from probabilistic inference within an ontology language, thus representing an important step toward the W3C’s vision for the Semantic Web.