You are here

Heterogeneous Data Discovery


TECHNOLOGY AREA(S): Information Systems

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 section 5.4.c.(8) of the solicitation and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct questions to the AF SBIR/STTR Contracting Officer, Ms. Gail Nyikon,

OBJECTIVE: To develop algorithms, methods and approaches that discover unanticipated events/targets of interest whose signatures are captured via an array of sensing modalities.

DESCRIPTION: The environment in which DoD intelligence, surveillance and reconnaissance (ISR) systems operate is changing dramatically due to the explosion of digital solid state hardware, advancements in arbitrary Radio Frequency (RF) waveform generation, software defined RF, cognitively controlled systems, the Internet of Things, and advanced tactics in Camouflage Concealment and Deception (CC&D) (to name a few). Any combination of these things is making it extremely difficult for a single stove-pipe exploitation system (e.g., SIGINT) to operate and produce meaningful results without degradation due to conditions such as Low Probability of Intercept (LPI) environments, co-channel dense spectral environments, distributed CC&D and poor collection geometries (refer to Ref. 1-4 , for examples).

This project seeks to overcome the deficiencies of a single stove-piped exploitation approach by harnessing the entire signature pallet, of an event, across all available sensors simultaneously. To maximize this potential, this project pushes for a revolutionary paradigm shift towards jointly combining/fusing sensor data upstream, or weakly processed data. The significance of processing the data in its rawest form, jointly in appropriate high dimensional mathematical manifolds, is that it allows the algorithm to improve event detection, uncover events often lost in the current data product paradigm, be amenable to autonomous operation, and separate events from advanced interference threats and CC&D conditions. This idea matches the Air Force vision for increased autonomy and the need for automated multi-sensor fusion and sensing as a service.

PHASE I: Identify advanced mathematical approaches for combining disparate heterogeneous sensors data for the purpose of unanticipated event/target detection and characterization in heterogeneous data. A few specific use case examples, along with benchmark level stove-pipe performance, will be developed in order to show a comparative advantage of the newly developed methods.

PHASE II: Further refine and develop the methods and algorithms used for joint heterogeneous data fusion. In particular, consider implementation aspects to allow the algorithm(s) to work across a distributed collection of sensors. Identify processing, channel capacity and latency requirements for developed algorithms. Consider a benchtop experiment, exploiting COTS equipment, to demonstrate the ability to perform such methods over a distributed network.

PHASE III DUAL USE APPLICATIONS: Develop and conduct an experiment on actual distributed sensing platforms in a realistic use case environment. Compare performance to the expectations from earlier phases. Commercial applications may include fields such as law enforcement, search and rescue, and automotive.


    • Demars, C., Roggemann, M., and Zulch, P., "Multi-Spectral Detection and Tracking in Cluttered Urban Environments," Proceedings of the 2015 IEEE Aerospace Conference, Big Sky, MT, 7-14 March 2015.


    • Vankayalapati, N., Kay, S., Ding, Q., "TDOA Based Direct Positioning Maximum Likelihood Estimator and the Cramer-Rao Bound," IEEE Transactions on Aerospace and Electronic Systems, Vol. 50, No. 3, pp. 1616-1635, July 2014.


    • Guerci, J.R., Bergin, J.S., Formundam, L., Zulch, P.A., "Terrain Encoded Geo-Location of Emitters," Proceedings of the 57th Meeting of the Military Sensing Symposium (MSS) Tri-Service Radar Symposium, Monterey, CA., 27-30 June 2011.


  • Bergin, J., Techau, P., Guerci, J., and Zulch, P., "Advanced Air Surveillance Radar Modes and Tactics," Proceedings of the 55th Meeting of the Military Sensing Symposium (MSS) Tri-Service Radar Symposium, Boulder, CO., 22-26 June 2009.

KEYWORDS: heterogeneous data fusion, structure of data, unanticipated event detection

  • TPOC-1: Peter Zulch
  • Phone: 315-330-7861
  • Email:
US Flag An Official Website of the United States Government