Combining Multiple Types of Intelligence to Generate Probability Maps of Moving Targets
Abstract
Drug addiction in the United States generates significant health, economic, and social costs. One of the prominent ways in which traffickers smuggle drugs into the United States is by maritime shipments from South America. In 1989 Joint Interagency Task Force South (JIATF-S) was established to fight these traffickers. JIATF-S collects information from multiple sources, which can be broadly classified into two categories. The first category is sensor-based sources that produce observations about possible targets (e.g., radar, sonar). These observations provide precise location and time but are susceptible to false positive and false negative errors regarding their content. The second category is human-based sources, including tips, messages and intercepted communications among humans. In addition to possible misinformation regarding the content of an event, such inputs are also susceptible to errors regarding the location and time of the event. In this thesis we develop a data fusion model that can assist JIATF-S in estimating the likelihood that a certain target (i.e., drug-smuggling vessel) is present at a certain location at a certain time and evaluate the reliability of the information source. The novelty of this thesis is manifested in a new probabilistic approach for utilizing human-generated intelligence, and in the way it is combined with sensor-generated intelligence.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2013
- Accession Number
- ADA589424
Entities
People
- Philip Zlatsin
Organizations
- Naval Postgraduate School