N121-092 TITLE: Rapid Crisis and Disaster Response Information Discovery

TECHNOLOGY AREAS: Human Systems

ACQUISITION PROGRAM: FNC is in development under proposed Theater Opening Enabling Capability

OBJECTIVE: Develop algorithms and processes for detecting rising crisis, partitioning information in unstructured data to separate noise from signal, and provide a means for evaluating the reliability of the information.

DESCRIPTION: Disasters and crises requiring international response and in particular, U.S. response due to strategic and national security concerns, have been made more complex and fast moving due to the technological and social changes wrought by mobile phones and information technologies. New information systems, from social media to YouTube, spread the word about rapidly evolving crisis with great speed however there exists tremendous noise, and the reliability of the information is highly variable. Information flows during crises (such as need for food, water, medical assistance or other aid) need to be monitored and information critical to the objective of the mission should be highlighted, summarized, and developed into actionable intelligence. Existing systems are slow and rely highly on human-in-the-loop for categorization and prioritization of information. There are no existing methods for trust, validation, or verification and few systems for fusing social media and existing data reservoirs to enhance the information flow so that it yields actionable intelligence.

The main objectives of this SBIR topic are developing actionable intelligence, finding the signal for a rapidly developing crisis in the "noise" of social media, and discovering and enhancing information so that it can be used in planning, monitoring, and pro-active execution of humanitarian missions. The highly desired end state is a system with the capability to fuse information from a variety of sources to create actionable intelligence, develop methods of trust and validation, with drill down, version control and capability to interact with a variety of mapping systems (e.g., Ushahidi, SAGE, ESRI) together with the ability to release some parts of the data into open-source and engage in information sharing operations in Phases II and III.

SPECIAL NOTE: THE ROLE OF SOCIAL SCIENCE. Offerors should understand that this is in part (perhaps 40-50%) a technology topic and part (50-60%) a problem of social science. The analysis of social media is about socio-technical behaviors: new behaviors that are made possible by the mobile phone and the extensions of information technology. In order to analyze information and its ramifications for social behavior, the approach taken will be most effective if social and cultural issues are delineated and addressed.

PHASE I: Design a system capable of ingesting massive amounts of unstructured data (such as more than 10,000 "tweets" per hour as an illustrative example), processing, and prioritizing information. The design should also include a good approach for the development of trust metrics for a military unit responsible for humanitarian assistance/disaster relief response. Unstructured social media information enhancement for verification, trust, and information fusion with other sources to develop actionable information pools (for example, to improve the ability to geo-locate humanitarian requests) and initial development of techniques for discerning signal from noise in social media for monitoring human-driven crisis is expected, to be elaborated in Phase II.

PHASE II: Develop a prototype of the system designed in Phase I that includes the following:
� Capability to fuse information from a variety of sources to create actionable intelligence
� New methods of trust and validation, with drill down, version control and capability to interact with a variety of mapping systems (Ushahidi, SAGE, ESRI, etc.)
� Capability to release some parts of the data into open-source and engage in information sharing operations
� Capability to allow crowdsourcing for information validation and prioritization
� Capability for micro-tasking, planning and coordination to leverage actionable intelligence generated by project using a crowdsourcing model
� Elaboration of signal discernment for detection of human-driven crisis

PHASE III: Fully deployable algorithms, methods and capabilities for:
� Aggregation, partition, and noise filtering for unstructured information from non-traditional open-sources (e.g., blogs, Ushahidi, Twitter, Facebook, possibly YOUTUBE, other social media, sms, email traffic) under lawful conditions and with ethical boundaries well defined
� Unstructured social media information enhancement for verification, trust, and information fusion with other sources to develop actionable information pools, for example, to improve the ability to geo-locate humanitarian requests
� Interaction with a variety of mapping systems (OpenStreetMap, Ushahidi, SAGE, ESRI, etc.) for improved data visualization
� Discernment of signal from noise in an incipient human-driven crisis through social media to detect emerging crisis

PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: Private sector application for this technology is considerable. Social media is a rapidly developing commercial area. Spin offs from this project might include mobile "apps" for smartphones for a variety of purposes including geo-location during emergencies, emergency reporting (for example, reports of flood, tornado), and specialized apps for police (local and state), first responders of all types, and even other agencies, from FEMA to USAID. The tools themselves would be useful for homeland defense at the state and possibly National level in situations of disaster such as Katrina, floods, tornados, and earthquakes.

REFERENCES:
1. J. Howe, "The rise of crowdsourcing," Wired Magazine, vol. 14, no. 6, pp. 1-4, 2006.

2. J. Howe, CROWDSOURCING. 2008.

3. H. Gao, G. Barbier and R. Goolsby, "Harnessing the crowdsourcing power of social media for disaster relief," IEEE Intelligent Systems, vol. 26, no. 4, pp.10-14, 2011.

4. J. Henselman and C. Waters, "Crowdsourcing crisis information in disaster affected Haiti," U.S. Institute of Peace, Washington, DC, Special Report 252, 2010.

5. E.T. Hall, Beyond Culture, New York, NY: Anchor Books, 1976.

KEYWORDS: humanitarian assistance; disaster relief; information fusion; crisis mapping; social media; crowdsourcing

** TOPIC AUTHOR (TPOC) **

DoD Notice:   Between November 9 and December 11, 2011, 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 12, 2011, 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 (12.1 Q&A) during the solicitation period for questions and answers, and other significant information, relevant to the SBIR 12.1 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.