Kuo-Chu Chang

PROGNOS: Predictive situational awareness with probabilistic ontologies

Information in the battlefield comes from reports from diverse sources, in distinct syntax, and with different meanings. There are many kinds of uncertainty involved in this process, e.g., noise in sensors, incorrect, incomplete, or deceptive human intelligence, and others, which makes it essential to have a coherent, consistent, and principled means to represent such phenomena among the systems performing Predictive Situation Awareness (PSAW). PROGNOS is a PSAW system being developed to work within the operational context such as U.S. Navys FORCENet. It employs probabilistic ontologies in a distributed system architecture as a means to provide semantic interoperability within an intrinsically complex and uncertain environment. This paper explores our current status in developing the system while addressing the major research challenges for making an effective PSAW system to support maritime operations.

High-level fusion: Issues in developing a formal theory

Network-centric operations demand an increasingly sophisticated level of interoperation and information fusion for an escalating number and throughput of sensors and human processes. The resulting complexity of the systems being developed to face this environment render lower level fusion techniques alone simply insufficient to ensure interoperability, as they fail to consider subtle, but critical, aspects inherent in knowledge interchange. A fundamental mathematical theory of high-level information fusion is needed to address (1) the representation of semantics and pragmatics, (2) the mathematical framework supporting its algorithmic and computing processes, and (3) scalability of products such as common and user-defined operational pictures. We argue that there is no silver bullet for addressing these elements, and therefore any successful approach to the problem of high-level fusion must be systemic. In this paper, we propose the development of mathematical foundations that systemically address this problem from a decision theoretic perspective, and might seed the development of such fundamental theory. As a case study illustrating these techniques we present our current development of PROGNOS, a HLF system focused on the maritime domain.

A Data Fusion Formulation for Decentralized Estimation Predictions under Communications Uncertainty

Uncertainty in communication channel characteristics is a significant factor for data fusion operations in wireless networks. Burst and random errors, message delays, user mobility, and link outages are significant factors that influence data fusion performance. These factors become even more significant in future mobile ad hoc networking environments. To date, however, those factors are not sufficiently addressed by formulations used for modeling and predicting data fusion performance. A stochastic-based fusion formulation that incorporates the effects of non-deterministic behaviors and stochastic communications characteristics is developed and proposed as a method for predicting estimation capabilities. The resulting stochastic fusion equations enable decentralized estimation capabilities to be evaluated in communication networks having non-idealized channel characteristics and ad hoc connectivity. The method is implemented in a simulation model for decentralized estimation in networks with time-varying ad hoc connectivity. The simulation results demonstrate the ability to closely predict expected fusion performance while greatly reducing model complexity and simulation time relative to current techniques. Those findings demonstrate the efficacy of a stochastic fusion formulation for prediction, and extending the approach to a wider range of data fusion domains and techniques is recommended

Scalable inference for hybrid Bayesian networks with full density estimations

The simplest hybrid Bayesian network is Conditional Linear Gaussian (CLG). It is a hybrid model for which exact inference can be performed by the Junction Tree (JT) algorithm. However, the traditional JT only provides the exact first two moments for hidden continuous variables. In general, the complexity of exact inference algorithms is exponential in the size of the largest clique of the strongly triangulated graph that is usually the one including all of discrete parent nodes for a connected continuous component in the model. Furthermore, for the general nonlinear non-Gaussian hybrid model, it is well-known that no exact inference is possible. This paper introduces a new inference approach by unifying message passing between different types of variables. This algorithm is able to provide an exact solution for polytree CLG, and approximate solution by loopy propagation for general hybrid models. To overcome the exponential complexity, we use Gaussian mixture reduction methods to approximate the original density and make the algorithm scalable. This new algorithm provides not only the first two moments, but full density estimates. Empirically, approximation errors due to reduced Gaussian mixtures and loopy propagation are relatively small, especially for nodes that are far away from the discrete parent nodes. Numerical experiments show encouraging results.