TECHNOLOGY AREAS: Information Systems, Human Systems

ACQUISITION PROGRAM: PM Intel - MCSC

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), which controls the export and import of defense-related material and services. Offerors must disclose any proposed use of foreign nationals, their country of origin, and what tasks each would accomplish in the statement of work in accordance with section 3.5.b.(7) of the solicitation.

OBJECTIVE: The objective of the work is to develop mappings in a N-dimensional human network space to a relevant behavior space. The network space should characterize how a human node in a network is interacting with other nodes. Nodes can be people, places, events or concepts. The tool, once fully developed, would add behavior metadata to nodes within a human network based on the computed network metrics. The metadata should make it easier to expose nodes that are (for example) influential or at risk. The tool, packaged as a network application service, would be used to translate human network data to actionable intelligence. In order to accomplish this, the offeror must consider a taxonomy of behavior attributes that would add a level of insight about nodes and that can be calculated from network data. A mapping of behavior attributes to person types (influential, at risk, etc.) should also be considered.

DESCRIPTION: A human network representation consists of nodes and edges. Current tools define nodes based on little more than a unique identifier. Edges are defined by little more than frequency measurements. The translation of network data to behavioral understanding and prediction requires that new analysis tools be developed. The emphasis of this topic is to develop a tool that can add behavioral metadata to nodes in an automated manner, enabled by calculated network metrics. The topic requires cross domain expertise as the solution seeks advances in behavioral understanding informed by network data. To make progress, the performer will have to develop a taxonomy of behavioral attributes, relevant to behavior understanding that can be approximated from network metrics. While it is expected that classic measures such as closeness and betweeness will be considered, offerors are encouraged to consider novel network metrics in order to better represent each node as a unique vector. An offeror may use subject matter experts to hypothesize relationships between network metrics and behavior attributes and/or a structured learning approach. To meet the goals of the topic, the offeror will have to develop an analysis engine that computes chosen network metrics from raw data and from these values calculates chosen behavior attributes. The trajectory of a network metric may be as or more important than the absolute measure itself. Over time the tool should be matured to allow new attributes to be discovered and approximated. Calculated metadata, mapped to nodes, should be displayable on classic network node visualizations. The final analysis tool should also be capable of predicting the response of a network to a stimulus given the behavioral attributes mapped to nodes.

PHASE I: Offeror should clearly demonstrate that their chosen technical approach is tractable and ready for a phase II effort. Specific goals include:
* Develop a taxonomy of behavior attributes relevant to behavior understanding that can be computed from network metrics
* Develop and code algorithms to calculate selected behavior attributes
* Demonstrate against one data set with known ground truth

PHASE II: Develop and demonstrate a prototype of an application service that can map behavior attributes to network nodes. Developed visualizations should enhance analyst network understanding. Conduct testing on a diverse data sets with known ground truths, including some unclassified government furnished test data sets.

PHASE III: Develop an application service that can be transitioned to the Marine Corps intelligence enterprise. The application must be severable from the data and visualization layers and conform to service oriented architecture standards.

PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: The marketing industry would be able to use the technology developed under this topic to better understand their customers based on internet traffic. This enhanced understanding would help with new product development. Political consultants could also use the technology to be developed to design more effective voter outreach efforts.

REFERENCES:
1. http://netwiki.amath.unc.edu/ (data sets and code are available here)

2. http://en.wikipedia.org/wiki/Social_network

3. J.W. Polderman and J.C. Willems, 1998. Introduction to Mathematical Systems Theory: A Behavioral Approach, 424 pages, Springer, New York

KEYWORDS: Network metrics, social network analysis, behavior attributes, human modeling, human networks, service oriented architecture, behavior understanding

** TOPIC AUTHOR (TPOC) **

DoD Notice:   Between November 12 and December 7, 2008, you may talk directly with the Topic Authors to ask technical questions about the topics. Their contact information is listed above. For reasons of competitive fairness, direct communication between proposers and topic authors is not allowed starting December 8, 2008, when DoD begins accepting proposals for this solicitation.

However, proposers may still submit written questions about solicitation topics through the DoD's SBIR/STTR Interactive Topic Information System (SITIS), in which the questioner and respondent remain anonymous and all questions and answers are posted electronically for general viewing until the solicitation closes. All proposers are advised to monitor SITIS (09.1 Q&A) during the solicitation period for questions and answers, and other significant information, relevant to the SBIR 09.1 topic under which they are proposing.

If you have general questions about DoD SBIR program, please contact the DoD SBIR Help Desk at (866) 724-7457 or email weblink.