Spatio-Temporal Nonlinear Filtering with Applications to Information Assurance and Counter Terrorism
Abstract
The objective of this MURI project is to develop a general and systematic foundation and algorithms for spatial-temporal statistical inference and for fusion of heterogeneous information from multi-source, multi-sensor distributed sensor networks. Immediate applications of the proposed work are Network Centric Warfare, where new and emerging systems such as MASINT and FORCENet collect but do not adequately interpret vast amounts of data; and homeland security applications, including video monitoring, and near-field and far-field intelligence analysis. Our research will solve three central problems: (a) nonstationary, (b) integrating metric and symbolic information, and (c) very high dimensionality. Current methods for pattern recognition in monitoring and surveillance are designed for stationary patterns, and cannot cope with new patterns in ever-changing environments. We develop new statistical methods for the nonstationary environment, particularly spatio-temporal nonlinear filtering, change-point detection, and advanced fusion methods. A distinctive feature of our approach is that the spaces in which estimation, classification and tracking is performed are both metric and symbolic. Just as a moving vehicle may be tracked in a metric coordinate space by conventional filters, so can an unfolding terrorist plan be tracked in plan space by a hybrid metric-symbolic nonlinear filter.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2006
- Accession Number
- ADA482732
Entities
People
- A. Bertozzi
- A. Galstyan
- Alexander G. Tartakovsky
- Boris Rozovsky
- C. Papadopolous
- G. Medioni
- P. Cohen
- V. Veeravalli
Organizations
- University of Southern California