N231-019 TITLE: Big Data Analytics (BDA): Real-Time Data Mining and Track Fusion of National and Tactical Data

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Artificial Intelligence (AI)/Machine Learning (ML); Autonomy

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

OBJECTIVE: Develop advanced real-time, and near real-time, data mining and fusion algorithms to exploit all relevant multi-intelligence data sources and rapidly create fused sensor tracks of "maritime surface vessels" to improve classification confidence.

DESCRIPTION: Multiple services utilize the Minotaur Family of Services (MFoS) solution set to aggregate and correlate multi-intelligence sensor data on board aircraft. Modern Artificial Intelligence (AI), Machine Learning (ML), and data analytic techniques can provide an enhanced Maritime ISR Common Operating Picture (COP) needed for higher fidelity track quality to correlate and fuse tracks from multiple data sources to support operations blue water and littoral environments.

This SBIR topic focuses on data mining and sensor fusion of data derived from aircraft organic sensors and multi-intelligence (multi-INT) sources, including near real-time data streams and archived data sources, to rapidly provide reliable, valuable, and accurate decision support for maritime surface vessel classification. The technique needs to take into consideration the combined power of AI, ML, and BDA to exploit a priori information of the surface vessel and environmental background. See references 1, 2, & 3 for additional information. The a priori knowledge is critical in the detecting, tracking, and rapid classification (or re-establish the identification) of the surface vessels with respect to tactics used in non-cooperative situations. The ability to fuse data across multiple systems, high precision-low persistence (tactical data) with low precision-high persistence (national data) should be used to support the classification of unknown surface vessels; "dark" surface vessels; surface vessels with large gaps in track data; and surface vessels "spoofing" to mask their identity. See reference 6 for additional information. The database and fusion techniques need to take into consideration latency and pedigree of the data, creation of false tracks attributed to "data ringing" (i.e., duplicate tracks) and "data looping" (i.e., reporting of same source track to different locations), and prior fusion techniques of data. Understanding the root cause and documentation of the mitigation steps in addressing "data looping" and "data ringing" is required. Data-driven algorithms that can aggregate and fuse data from various sources, and identify the appropriate data and interface standards (e.g., style guides, ontology, ICDs, metadata, etc.) are required to generate interoperable data models. Data aggregation can include, and is not limited to, data collection; data processing; data cleansing; and data analysis. The database and fusion techniques are to leverage all data sources such as (but not limited to) Radar; Electronic Intelligence (ELINT); Communication Intelligence (COMINT); Automatic Identification Systems (AIS); and Imagery to accurately identify and fuse useful multi-INT, multisource data. The resultant solution will feed the MFoS, the Maritime ISR Common Operating Picture (COP) used by the U.S. Government.

Work produced in Phase II may become classified. Note: The prospective contractor(s) must be U.S. owned and operated with no foreign influence as defined by DoD 5220.22-M, National Industrial Security Program Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Counterintelligence and Security Agency (DCSA) formerly Defense Security Service (DSS). The selected contractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances. This will allow contractor personnel to perform on advanced phases of this project as set forth by DCSA and NAVAIR in order to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material IAW DoD 5220.22-M during the advanced phases of this contract.

PHASE I: Develop advanced real-time, and near real-time, data mining and fusion algorithms to exploit all relevant multi-INT data sources and rapidly create fused sensor tracks of "maritime surface vessels" to improve classification confidence. The study should include the ingestion of data and normalization to ensure consistent data models needed to accurately correlate, and temporally and spatially fuse the different data sources. Publicly accessible data can be used for the Phase I approach. The final report shall include a conceptual design and the prototype design plan for Phase II. Phase I analysis results from modeling and simulation should be included in the final report.

PHASE II: Continue to mature algorithms developed in Phase I to accept data sources from the U.S. Navy MFoS, in addition to data from near real-time sources and data lakes from other services and national data. Sensor sources will include maritime surface vessel track or location information, and will be supplied by the U.S. Government in the beginning of Phase II activities. Perform a study of the interface standards (e.g., style guides, ontology, ICDs, metadata, etc.) required for correlation and fusion of the track information and dissemination of data within MFoS. The algorithms will maintain or improve track accuracy and classification of the maritime surface vessels, and not degrade any uncertainties during the fusion process. The algorithms should maintain the interface standards required for the MFoS operating environment. Demonstrate the algorithms with the objective of showing a high level of confidence for fused tracks. Data looping and data ringing will be documented during Phase II, and the final report should include a summary of the studies, root cause, and mitigation steps in addressing data looping and data ringing. The final report will include the algorithms and data models required to interface with MFoS sensor data and sensor data from other sources (including national data sources and data lakes).

Work in Phase II may become classified. Please see note in Description paragraph.

PHASE III DUAL USE APPLICATIONS: Refine the design, test, and integrate the architecture and algorithms into MFoS. The final design will also focus on the sustainment of the algorithms. Phase III deliverables should include but not be limited to a Pre-Design Review (PDR) and Critical Design Review (CDR), performance requirement generation, associated testing and analysis of the software, ICDs, instructions, and manuals.

Big data mining and analytics will benefit both DoD and agencies using MFoS, while also providing commercial application ranging from exploring trends from sensors, devices, video, audio, web, and social media.

REFERENCES:

1.       Smagh, N. S. (2020, June 4). Intelligence, surveillance, and reconnaissance design for great power competition. Congressional Research Service. https://fas.org/sgp/crs/intel/R46389.pdf

2.       Research and Technology Organisation. (2003, October 20�22). RTO-MP-IST-040: Military data and information fusion. RTO Information Systems Technology (IST) Meeting Proceedings, Prague, Czech Republic. https://www.sto.nato.int/publications/STO%20Meeting%20Proceedings/Forms/Meeting%20Proceedings%20Document%20Set/docsethomepage.aspx?ID=36853&FolderCTID=0x0120D5200078F9E87043356C409A0D30823AFA16F602008CF184CAB7588E468F5E9FA364E05BA5&List=7e2cc123-6186-4c30-8082-1ba072228ca7&RootFolder=https://www.sto.nato.int/publications/STO%20Meeting%20Proceedings/RTO-MP-IST-040

3.       Newman, A. J., & Mitzel, G. E. (2013). Upstream data fusion: History, technical overview, and applications to critical challenges. Johns Hopkins APL technical digest, 31(3), 215-233. https://www.jhuapl.edu/Content/techdigest/pdf/V31-N03/31-03-Newman-Mitzel.pdf

4.       Defense Counterintelligence and Security Agency. (n.d.). https://www.dcsa.mil/

5.       Department of Defense. (2006, February 28). DoD 5220.22-M National Industrial Security Program Operating Manual (Incorporating Change 2, May 18, 2016). https://www.esd.whs.mil/portals/54/documents/dd/issuances/dodm/522022m.pdf

6.       Boger, Dan, Miller, Scot, Lavoie, Erik, & Wreski, Erin (2016). Unclassified Maritime Domain Awareness. https://calhoun.nps.edu/handle/10945/57705

 

KEYWORDS: Artificial Intelligence; AI; Machine Learning; ML; Big Data; Big Data Analytics; Analytics; Data Lakes; Fusion; Track Fusion; Classification; Maritime Classification; Maritime Situational Awareness; Minotaur; MFoS

---