Data Link Bottleneck Reduction Using Big Data Analytics

Navy SBIR 20.2 - Topic N202-101

Naval Air Systems Command (NAVAIR) - Ms. Donna Attick navairsbir@navy.mil

Opens: June 3, 2020 - Closes: July 2, 2020 (12:00 pm ET)

 

 

N202-101       TITLE: Data Link Bottleneck Reduction Using Big Data Analytics

 

RT&L FOCUS AREA(S): Artificial Intelligence/ Machine Learning, General Warfighting Requirements (GWR)

TECHNOLOGY AREA(S): Information Systems

 

OBJECTIVE: Develop innovative approaches utilizing big data analytics techniques to identify and extract critical content from sensor imagery products to reduce data-link bandwidth requirements dramatically, while maintaining or improving the rate at which actionable intelligence is generated.

 

DESCRIPTION: Navy imaging sensors, like optical, electro-optical, multispectral, hyperspectral, and radar sensors, are producing so much high-quality imagery that it overwhelms on-aircraft data link resources. Techniques to buffer, preprocess and compress data are incrementally improved as are the capabilities of data link hardware but these are not keeping pace with sensor improvements that are leading to a continuous rise in data traffic. This situation exists for both line of sight and beyond line of sight links. Significant research is underway in big data analytics techniques to facilitate rapid, more informed and smarter decision making when faced with vast and overwhelming quantities of information. This SBIR topic seeks to use those tools to analyze and extract critical content from imagery products generated by various sensor systems onboard the aircraft. The operational need for this is critical for unmanned aircraft but certainly not limited to those platforms. The big data analytics toolbox contains a range of techniques for the extraction of features, the automatic parsing, segmenting, indexing and tagging of critical imagery content. Multiple synergistic artificial intelligence (AI) techniques are being utilized to inform those actions in ways to best serve the user’s needs. This SBIR topic seeks to leverage these techniques to better serve time critical military operations.

 

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). The selected contractor and/or subcontractor 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: Demonstrate how big data analytics techniques could in principle be used to dramatically reduce data link bandwidth requirements while maintaining or improving the rate at which actionable intelligence is generated. Reductions on the order of 10x threshold and 100x objective are being sought. The scope of the demonstration can be rather limited but must be operationally relevant and sufficient to show feasibility of the proposed approach. The Phase I effort will include prototype plans to be developed under Phase II.

 

PHASE II: Complete detailed development and demonstrate an end-to-end approach for the intelligent real-time automated extraction of critical sensor imagery products from imaging sensors, like optical, electro-optical, multispectral, hyperspectral, and radar. Show how this will dramatically reduce data-link bandwidth requirements while maintaining or improving the rate at which actionable intelligence is generated.

 

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

 

PHASE III DUAL USE APPLICATIONS: Refine the solution, perform final testing, and integrate and transition the final solution to Navy airborne platforms. Typical host computational platforms are Ion Intel® Xeon® Scalable processors and successors with greater than 10 TB SSD storage.

 

The big-data analytics as applied to data-link information management are applicable to a wide range of applications including law enforcement and border-control surveillance operation.

 

REFERENCES:

1. Schulte, M. “Real-time feature extraction from video stream data for stream segmentation and tagging.” Diplomarbeit, Dortmund, January 22, 2013. http://www-ai.cs.tu-dortmund.de/schulte_2013a.pdf?self=%24dv5v9puha8&part=data

 

2. Griethe, W. “Advanced Broadband Links for Tier III UAV Communication.” DASIA 2011, San Anton, Malta, May 2011. https://www.researchgate.net/publication/261727128_ADVANCED_BROADBAND_LINKS_FOR_TIER_III_UAV_DATA_COMMUNICATION

 

KEYWORDS: Big Data Analytics, Data Links, Information Management, Radar, Electro-Optics, Data Mining, Artificial Intelligence, AI