Date of Award

2010

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Esterline, Albert

Abstract

This thesis reports on work in progress on software that helps an analyst identify and analyze activities of actors (such as vehicles) in an intelligence-relevant scenario. A system is being developed to aid intelligence analysts, IAGOA ((Intelligence Analyst’s Geospatial and Ontological Assistant). Analysis may be accomplished by retrieving simulated satellite data of ground vehicles and interacting with software modules that allow the analyst to conjecture the activities in which the actor is engaged along with the (largely geospatial and temporal) features of the area of operation relevant to the natures of those activities. Activities are conceptualized by ontologies. The research relies on natural language components (semantic frames) gathered from the FrameNet lexical database, which captures the semantics of lexical items with an ontology using OWL. The software has two components, one for the analyst, and one for a modeler who produces HTML and parameterized KML documents used by the analyst. The most significant input to the modeler software is the FrameNet OWL file, and the interface for the analyst and, to some extent, the modeler is provided by the Google Earth API.

Download

Share

COinS