Sensor Exploitation for Evidence and Discovery for Anticipatory Threat Analysis (SEE-DATA)

Sensor Exploitation for Evidence and Discovery for Anticipatory Threat Analysis (SEE-DATA)
Navy SBIR FY2014.2

Sol No.:	Navy SBIR FY2014.2
Topic No.:	N142-122
Topic Title:	Sensor Exploitation for Evidence and Discovery for Anticipatory Threat Analysis (SEE-DATA)
Proposal No.:	N142-122-0466
Firm:	Boston Fusion Corp. 1 Van de Graaff Drive Suite 107 Burlington, Massachusetts 01803-5176
Contact:	Connie Fournelle
Phone:	(617) 583-5730
Web Site:	www.bostonfusion.com
Abstract:	In addition to organic (i.e., military) sensors, non-organic (i.e., non-government) sensors are ubiquitous, but largely untapped. These sensors capture data that address critical information needs such as detecting emerging activities or pinpointing a target's location. What is needed is a novel sensor discovery and exploitation framework to harvest intelligence from "opportunistic" sensors and allow analysts to incorporate new sensor data and collaborate both with the system and other analysts-correlating new data with historical intelligence archives, persisting and sharing frame-level annotations, and refining sensor selection for changing needs. In response, we will design and develop an adaptable, plug-and-play system, SEE-DATA, to identify opportunistic sensors and extract features to characterize and exploit the data in real-time. In Phase I, we will: Develop methods to identify opportunistic sensors for information needs of users and algorithms, and update sensor selection for evolving operations. Design a system concept for opportunistic sensor identification and exploitation to provide plug-and-play, cloud-compatible tool integration for characterizing and exploiting real-time sensor data. Capture user requirements for specifying information needs, structuring analysis, and annotating data for search and collaboration. Demonstrate opportunistic sensor identification and exploitation using data from multiple sensors and sensor types to show the validity of our approach.
Benefits:	SEE-DATA will produce a generalized framework for rapidly identifying organic and non-organic sensors whose data contents provide critical information to real-time operations. SEE-DATA will use a plug-and-play architecture to maximize reuse and facilitate transition to users in multiple domains, with varying collections of sensors at their disposal, providing the essential infrastructure necessary to organize collaborative exploitation for real-time operations. The system will operate in two modes: developing anticipatory intelligence that identifies and exploits relevant sensors based on the expected information from them over specified timeframes, and providing reachback to historical data for forensic analysis. Our efforts in Phase I will produce: Methods to identify sensors, characterize streaming data, select and parameterize exploitation algorithms, correlate data with historical repositories, and refine information needs in real-time; A prototype design for an opportunistic sensor exploitation system, with support for identifying sensors, ingesting data, characterizing incoming streaming data, integrating the data with archived associations, and identifying relevant data in sensor streams; An evaluation plan, preliminary results, and documentation to describe the efficiency and scalability of our proposed system, and methods for evaluation in Phase II; and A proof-of-concept demonstration showing how the SEE-DATA system will manage real-time sensor data, and providing confidence in the proposed approach. The Phase I effort will demonstrate the feasibility of building an efficient and scalable opportunistic sensor exploitation system by leveraging information-theoretic sensor identification and management strategies, plug-and-play architectures for access to multimodal exploitation algorithms, and associative data management for efficient processing and persistence. Our Phase I effort will lay the groundwork for building an open-source, non-proprietary, scalable, and secure system for managing and facilitating discovery within data streams from opportunistic sensors, correlated with massive stores of historical association data for timely and anticipatory operational support.

Return