| 2005 Technology
Symposium > Intelligent Information Processing
Intelligent Information Processing
Intelligent Information Processing investigates technologies, tools,
and processes that support the discovery, processing, exploitation and
dissemination of information, tools and knowledge. Intelligent agents
are covered in this area.
ARDA Information Exploitation
Warren Greiff, Principal Investigator
Location(s):
Problem
^TOP
Audio Hot Spotting for Tactical and Intelligence Applications
Qian Hu, Principal Investigator
Location(s): Washington and Bedford
^TOP
BlogINT: Weblogs as a Source of Intelligence
John Griffith, Principal Investigator
Location(s): Washington and Bedford
Problem
Weblogs are an emerging source of information, including personal reports and images of events, but their value as a source of intelligence is unknown. Entries can be authored on mobile devices such as camera phones and published on the Internet within seconds. But how do weblogs compare to traditional media in terms of interest, uniqueness, accuracy, and timeliness?
Objectives
We will compare weblogs to traditional Web-based news and broadcast television in terms of content, accuracy, and timeliness. We will characterize the benefits, costs, risks, opportunities, and challenges associated with exploiting weblogs as potential sources of intelligence.
Activities
We will collect high volumes of information from weblogs and traditional television and Web-based news media. To characterize content, we will compare weblogs and traditional media using the method developed in MITRE's Retrospective Source Analysis project. We will build spatio-temporal models of events from weblogs and compare these to ground truth for another assessment of accuracy, level of detail, and value.
Impact
This project will produce an understanding of the value of weblogs as a source of intelligence. It will also produce a large, longitudinal data set and a prototype high-volume, real-time collection system.
^TOP
Coordinated Financial Crimes Investigation
Conrad Chang, Principal Investigator
Location(s): Washington and Bedford
Problem
Investigating financial crimes poses complex and varied problems, and often requires cooperation among multiple agencies. Various organizations within the U.S. Treasury Department are closely involved in tracking financial activities. Successful information coordination and exchange among these organizations and others are vital to winning the global war on terror and are also critically important to prosecution of more traditional financial crimes.
Objectives
Our goal is to research a means for connecting multiple participants to facilitate information sharing. To accomplish this goal, we will research and develop technologies using realistic data sets. We will demonstrate how connections can be made among agents, what information can be shared, and how ontologies can be used in this process.
Activities
We will establish contact with relevant agencies and analyze their information sharing requirements. We will then develop an appropriate ontology for financial crime investigation, build an information sharing prototype, and research and develop an appropriate information sharing policy for the prototype. We will evaluate the prototype's effectiveness using customer-provided and open source data, and document our findings.
Impact
This research can immediately benefit multiple agencies, especially those involved in tracking terrorism financing, and also those investigating more traditional financial crimes. This project will, at a minimum, illustrate a methodology for information sharing among multiple agencies in financial crime investigations. It will help sponsors understand what data need to be collected and disseminated to achieve effective information sharing.
^TOP
Distributed Resource Brokering in Complex Network Environments
Paul Silvey, Principal Investigator
Location(s): Washington and Bedford
Problem
Many challenging problems facing MITRE's sponsors require the coordinated use of large numbers of distributed IT resources. Hard computational problems such as data mining become tractable when thousands of computers are simultaneously brought to bear. Likewise, global information management architectures, like those envisioned for a Joint Battlespace Infosphere, require distributed infrastructures to be sufficiently scalable, fault-tolerant, and timely.
Objectives
We are investigating the performance of various proposed techniques for distributed resource discovery in peer-to-peer (P2P) networks by modeling and simulating them in realistic complex network environments. By studying many approaches in many situations, we aim to discover fundamental principles that designers of distributed IT systems can use to achieve desired levels of performance in particular real-world environments.
Activities
We are experimenting with strategies for simultaneously increasing efficiency and robustness in P2P networks that use flooding-based protocols for distributed search and indexing. By making the networks self-organizing and self-healing, we can demonstrate mechanisms that allow networks of resource brokers to adapt as their environments change. Our modeling and simulation studies are looking at adaptive network topologies and network joining protocol behaviors.
Impact
Our sponsors will be affected by the changes that network-centric, distributed, and P2P technologies are bringing to resource discovery and management problems. Dynamic information management in intelligence, logistics, weather reporting, and command and control all face scalability and timeliness challenges that centralized content indexing approaches will not completely solve. This research is helping to improve our understanding of key issues.
^TOP
ISR Forensics: Retrospective Analysis of ISR Data
Curtis Brown, Principal Investigator
Location(s): Washington and Bedford
Problem
Forensic analysis will become one of the future drivers of both exploitation tool development and multi-INT data archives. To be successful in exploiting the ISR data in large multi-INT databases, forensics analysts will need to combine ground moving target indicator data with data from other sources of intelligence and will require easy-to-use tools to access, navigate, and process it.
Objectives
Our objective is to create visualization tools to support the forensic analysis of ISR data. These tools will provide a framework for exploring automation through the incorporation of advanced tracking technology.
Activities
We will develop a set of tools that exploit geospatial and temporal data, and then apply the tools to synthetic ground truth data sets that we will generate. Advanced tracking technology, including Multiple Hypothesis Tracker traceback, will be developed and integrated to aid the analyst. We will document lessons learned and demonstrate the forensic environment at the Technology Symposium.
Impact
We will make our exploitation tools available to analysts. Lessons learned will be fed back both to multi-INT database efforts as well as exploitation tool development efforts.
^TOP
Meeting Content Capture Tools
Gayle Sobanek, Principal Investigator
Location(s): Washington and Bedford
Problem
It is typically difficult to capture value from meeting interactions completely and accurately. CI&T has been looking at tools that support the capture of meetings as corporate information assets. Meeting capture tools such as Jubilant, Media Site, and Quindi Meeting Companion enable organizations to record, index, organize, and share content such as briefings, notes, and audio from meetings, teleconferences, and even video teleconferences. Thus, an accessible meeting record with associated artifacts remains available to those who may have missed the meeting or who may need to hear what was said in the context in which it was presented. The tools allow for real-time content capture, post-meeting editing, and publication of the files to a central area such as a Community Share or Web site or for sharing. CI&T's Innovation & Harvesting program staff is currently evaluating and experimenting with these products and influencing the vendors' development of desired product capabilities, with the goal of recommending the use of specific meeting capture tools for the MITRE community. In addition to looking at the technologies to support meeting capture, we are examining the policies and practices that lead to successful meeting capture and reuse.
^TOP
Meteor—MITRE's Entry in the DARPA
Grand Challenge
Ann Jones, Principal Investigator
Location(s): Washington
Problem
Congress has mandated that at least a third of all operational ground military vehicles be unmanned by the year 2015. Significant technology advances are needed to achieve this goal. The DARPA Grand Challenge focuses on challenges in sensing, obstacle avoidance, and system robustness. The specific challenge will be to autonomously navigate roughly 175 miles of desert roads.
Objectives
The MITRE team will integrate COTS sensors and a commercially available vehicle to provide a platform for algorithm development in sensing and avoiding obstacles. The platform, named Meteor, will be capable of autonomously navigating 175 miles in 10 hours by traveling from waypoint to waypoint while sensing and avoiding obstructions.
Activities
By March, most of Meteor's sensing and computing capability will be integrated and the vehicle will be able to navigate from waypoint to waypoint, avoid simple obstacles, and monitor its performance. By early May, when DARPA pays a site visit to MITRE, most of Meteor's functionality will be implemented. We will test and refine algorithms from then until the competition begins on 8 October.
Impact
The Grand Challenge is intended to provide technologies and innovations to DoD sponsors as they move toward greater reliance on unmanned vehicles. This activity provides MITRE with additional opportunities to develop our unmanned vehicle expertise while offering a significant system and sensor integration challenge.
^TOP
MII Google Expertise Finding Tool Suite
Robert Joachim
, Principal Investigator
Location(s): Washington and Bedford
Problem
MITRE has adopted the Google Search Appliance as its enterprise search engine. In conjunction with this implementation, we have developed special repositories and applications that aid in identifying and finding expertise within the corporation. This suite of products includes the MII Google Expertise Finder, which presents users with a staff roster (as well as an organizational view) based on keyword queries. The repositories feeding the Expertise Finder include MITRE transfer folders, Project Share folders, and Community Share (SharePoint) document libraries. A recent pilot tool is the MII Google Email List Search, which provides users with search results based on MITRE Listserv list messages. An additional prototype enhancement to this pilot includes a "List finder" to answer user questions such as "Which MITRE mail list covers topic X?"
^TOP
Robot Swarms
Bob Grabowski, Principal Investigator
Location(s): Washington
Problem
Most unmanned systems today are not autonomous; they are teleoperated by human supervisors. Some tasks, such as reconnaissance, naturally call for teams of multiple robots. We seek to reduce the number of human supervisors required to accomplish these tasks. To accomplish this reduction of human effort, the robots must possess considerable autonomy in order to enable effective collaboration.
Objectives
We will develop mechanisms that support the construction of effective, reliable robot teams. The project is called "Robot Swarms" because we will consider using the simple mechanisms present in collections of social insects. We will also consider possible countermeasures for defeating our teams, and investigate mechanisms for reliable operation in the presence of those countermeasures.
Activities
We will participate in the RoboCup/AAAI Search and Rescue Competitions, and we will, in parallel, develop a demonstration of autonomous building-clearing by a team of robots.
Impact
In the future, our sponsors (military, intelligence gathering, homeland security) will need to deploy robot systems and have them function together. The research in this project will provide mechanisms by which the robots can work together effectively.
^TOP
Structured ISR Fusion
Walter Kuklinski, Principal Investigator
Location(s): Washington and Bedford
Problem
The importance of developing fusion algorithms to improve the warfighting capability derived from Intelligence Surveillance and Reconnaissance (ISR) systems is well documented. Many operational requirements mandate levels of performance that can only be obtained by fusing data from multiple sensors and platforms. However, only limited attempts have been made to develop formal design procedures for data fusion systems.
Objectives
The objective of this MSR is to use formal mathematical methods such as Random Set Theory and Category Theory as frameworks to design and implement fusion algorithms and to predict fusion system performance. We will develop and implement a widely applicable methodology for fusion system design and analysis.
Activities
We will develop and evaluate, using both simulated and field data, multi-target tracking algorithms that fuse conventional radar SMTI data with additional data sources including SIGINT, COMINT and ELINT, using both Random Set Theory and Category Theory frameworks.
Impact
The successful completion of this MSR will both provide a significant advance in the general area of fusion system analysis and design and yield specific fusion algorithms applicable to the future fusion requirements of many MITRE sponsors.
^TOP
|
