Radio Frequency Spectrum Patterns of Life

Navy SBIR 22.1 - Topic N221-073
ONR - Office of Naval Research
Opens: January 12, 2022 - Closes: February 10, 2022 (12:00pm est)

N221-073 TITLE: Radio Frequency Spectrum Patterns of Life

OUSD (R&E) MODERNIZATION PRIORITY: Artificial Intelligence (AI)/Machine Learning (ML);General Warfighting Requirements (GWR);Networked C3

TECHNOLOGY AREA(S): Electronics;Ground / Sea Vehicles;Sensors

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 an automated system that characterizes the Radio Frequency (RF) emitter behaviors and patterns of life for a geographic area with no to minimal operator intervention.

DESCRIPTION: The RF spectrum is a congested medium shared by a wide range of private, commercial, civil, and military users to communicate, navigate, and characterize the environment using increasingly diverse signal waveforms and shared-access methods. Spectrum use varies as a function of time, space, and frequency, resulting in a highly dynamic environment that challenges traditional methods of spectrum monitoring and evaluation. This lack of understanding limits the use of opportunistic spectrum applications (e.g., cognitive radio, dynamic spectrum access) and makes it difficult to detect anomalous spectrum use.

Despite the dynamic nature of spectrum use, most of the activity is routine, and therefore potentially predictable. In much the same way that human cognition works, learned models of expected or predictable features and feature dynamics of the environment can be used to focus attention primarily on new or unusual features. Such an approach is necessary when constrained resources are required to make sense of complex situations. By reducing the amount of information that must be processed at any given time, the limited available resources can be allocated more efficiently to characterize the most important aspects of the environment, not wasted by repeatedly evaluating the same features and behaviors.

To support this objective, this SBIR topic will explore algorithms that detect, characterize, and learn "normal" spectrum activity and behaviors. Learned models should be able to represent signal types and their temporal and spatial qualities sufficiently to predict when and where typical activity will occur. An important aspect of this research will be to demonstrate ways that the learned model can be used to focus attention on novel signals in the spectrum, as well as unusual spectral patterns of activity. Note that methods of interest must be able to generalize over a wide range of signal types, including those used by communications devices and radars. Approaches that operate only on limited or specific signal types are not of interest.

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 Security Agency (DCSA). The selected contractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances, in order to perform on advanced phases of this project as set forth by DCSA and ONR 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: Conduct a study to evaluate the technical feasibility of learning RF spectrum patterns of life to automatically bring to the operators attention novel and unusual activities in the RF environment. Given a simple radio receiver (e.g., single channel, <= 500 MHz instantaneous bandwidth, ~18+ GHz tuning range), develop an approach to learn spectrum patterns for a day in the life of a moderately congested RF environment (e.g., an airport, a littoral maritime environment). Demonstrate for a simulated environment that the learned model can discriminate between new signals and those normally present in the environment when a new signal shares several attributes (waveform, frequency, timing, etc.) with those signals typically present in the environment. For example, the system should be able to detect when an arbitrary but common communications signal appears at an unusual frequency or time of day, or when a radar changes itsí waveform or pulse repetition rate to something not previously observed. Develop a Phase II plan.

PHASE II: Given a set of 3-4 simple receivers geographically distributed to span an 100 SQ mile area of interest, develop an approach to learn spectrum patterns for a day in the life of a moderately congested RF environment. Demonstrate in a lab environment that the learned model can detect unusual signals and spectral activities that vary over space, time, frequency, and/or signal type. Build and deliver a prototype system that can monitor the RF spectrum, collect sufficient examples to train the learned model, and then operate in near-real-time to identify spectrum anomalies.

It is probable that the work under this effort will be classified under Phase II (see Description section for details).

PHASE III DUAL USE APPLICATIONS: Develop an improved spectrum patterns of life modeling system integrated onto a fielded RF sensor(s). The system will show that it achieves the objective capability described above. Deliver the prototype to be independently evaluated by the Government to determine if the technology has the potential to meet the Navyís performance goals for patterns of life modeling.

Develop an automatic capability for RF spectrum monitoring and analysis by commercial ventures who enforce Spectrum utilization for the Federal Communications Commission (FCC) and Homeland security. This capability can also be used by cell tower infrastructure companies to understand the RF environment they are placing new or existing cellular infrastructure in.

REFERENCES:

  1. Liu, Song; Greenstein, Larry J.; Trappe, Wade and Chen, Yingying. "Detecting anomalous spectrum usage in dynamic spectrum access networks." Ad Hoc Networks 10, no. 5, 2012, pp. 831-844. https://personal.stevens.edu/~ychen6/papers/Detecting%20Anomalous%20Spectrum%20Usage%20in%20Dynamic%20Spectrum%20Access%20Networks.pdf.
  2. Rajendran, Sreeraj; Meert, Wannes; Lenders, Vincent and Pollin, Sofie. "SAIFE: Unsupervised Wireless Spectrum Anomaly Detection with Interpretable Features." 2018 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), IEEE, 2018, pp. 1-9. https://arxiv.org/pdf/1807.08316.pdf.
  3. Zhijing, Li;, Xiao, Zhujun; Wang, Bolun; Zhao, Ben Y. and Zheng, Haitao. "Scaling Deep Learning Models for Spectrum Anomaly Detection." Proceedings of the Twentieth ACM International Symposium on Mobile Ad Hoc Networking and Computing, 2019, pp. 291-300. https://dl.acm.org/doi/pdf/10.1145/3323679.3326527.
  4. Selim, Ahmed; Paisana, Francisco; Arokkiam, Jerome A.; Zhang, Yi; Doyle, Linda and DaSilva, Luiz A. "Spectrum Monitoring for Radar Bands using Deep Convolutional Neural Networks." GLOBECOM 2017-2017 IEEE Global Communications Conference, 2017, pp. 1-6. https://arxiv.org/pdf/1705.00462.

KEYWORDS: Electronic Surveillance; Radio Frequency; RF; Spectrum Monitoring: Patterns of Life; Emission Classification; signals intelligence; SIGINT

** TOPIC NOTICE **

The Navy Topic above is an "unofficial" copy from the overall DoD 22.1 SBIR BAA. Please see the official DoD Topic website at rt.cto.mil/rtl-small-business-resources/sbir-sttr/ for any updates.

The DoD issued its 22.1 SBIR BAA pre-release on December 1, 2021, which opens to receive proposals on January 12, 2022, and closes February 10, 2022 (12:00pm est).

Direct Contact with Topic Authors: During the pre-release period (December 1, 2021 thru January 11, 2022) proposing firms have an opportunity to directly contact the Technical Point of Contact (TPOC) to ask technical questions about the specific BAA topic. Once DoD begins accepting proposals on January 12, 2022 no further direct contact between proposers and topic authors is allowed unless the Topic Author is responding to a question submitted during the Pre-release period.

SITIS Q&A System: After the pre-release period, proposers may submit written questions through SITIS (SBIR/STTR Interactive Topic Information System) at www.dodsbirsttr.mil/topics-app/, login and follow instructions. In SITIS, the questioner and respondent remain anonymous but all questions and answers are posted for general viewing.

Topics Search Engine: Visit the DoD Topic Search Tool at www.dodsbirsttr.mil/topics-app/ to find topics by keyword across all DoD Components participating in this BAA.

Help: If you have general questions about DoD SBIR program, please contact the DoD SBIR Help Desk via email at DoDSBIRSupport@reisystems.com

[ Return ]