TECHNOLOGY AREA(S): Information Systems

ACQUISITION PROGRAM: PEO C4I, PMW 120, Ships Signals Exploitation Equipment, Distributed Common Ground System-Navy

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 3.5 of 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: The PMW 120 Program Office desires a Radio Frequency Activity Modeling and Pattern Recognition (RF-AMPR) capability to perform pattern recognition, anomaly detection, and improved clustering of radio frequency (RF) signals. Specifically, it shall consist of a parametric RF classifier, a generative model of activity in the local electromagnetic environment, a machine learning-based anomaly detection method, and an RF data-clustering algorithm that classifies data that would otherwise be discarded by the parametric classifier.

DESCRIPTION: Current automated RF data analysis and information discovery methods necessitate discarding significant volumes of sensor data as �non-analyzable�. This SBIR topic seeks to apply machine learning methodologies to better characterize this discarded data, enabling a more complete understanding of RF activity present in a specific environment.

The RF-AMPR capability shall classify detected RF signals, build activity models, and detect/cluster anomalies. Anomaly classification shall include �known unknowns�, radio frequency events that are outliers of known classes, and �unknown unknowns�, anomalous RF events that represent new devices or activities. RF-AMPR must be able to accommodate RF data bursts / blooms. Solutions offered must also include an analysis of how they would scale as RF data rates and bandwidth increase.

It is highly likely that work produced in Phase II will 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 Security Service (DSS). The selected contractor and/or subcontractor 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 DSS and SPAWAR 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: Complete a feasibility study describing a novel design for an RF-AMPR capability capable of performing tasks specified above within an RF environment to be proposed by the Small Business Concern (SBC). Address feasibility of building RF activity models, anomaly detection within such models, and the clustering of anomalous RF data. Develop a Phase II plan describing the costs and technical effort required to implement the design described in the study.

PHASE II: Working with the Government team to define the specific RF environment in which the Phase II product will operate, develop an RF-AMPR prototype capability to implement the solution proposed in Phase I. This prototype shall perform the following tasks: 1) Generate models of RF-related activity within the environment jointly defined by the SBC and the Government team; 2) Detect patterns of interest and anomalies in stored data within specified database structures; and 3) Provide enhanced information (such as clustering of anomalies with known signal types) on the identity of anomalous RF activity within a given area. Specifications on data types will be provided to the SBC at the time of Phase II award.

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

PHASE III DUAL USE APPLICATIONS: Complete necessary engineering, system integration, packaging, and testing to field the capability into various PMW 120 PoRs. Commercialize the capability for technology transition to the wider defense and intelligence communities. Phase III of this SBIR effort will require classified research.

The capability described could have significant commercial potential for any telecommunications or RF spectrum user community and the broader commercial radio user market. As the electromagnetic spectrum Internet of Things (IoT) becomes more congested, automated means of optimizing its use becomes crucial for multiple business sectors around the world. In addition, this kind of signal analytic capability could improve device detection, recognition, and state changes for IoT devices operating within an internet protocol (IP) / local area network (LAN) construct.

REFERENCES:

1. Migliori, B., Zeller-Townson, R., Grady, D. and Gebhardt, D. �Biologically Inspired Radio Signal Feature Extraction with Sparse Denoising Autoencoders�. arXiv preprint arXiv:1605.05239, 2016. https://arxiv.org/abs/1605.05239

2. Walton, M., Gebhardt, D., Migliori, B. and Straatemeier, L. �Learning and Visualizing Modulation Discriminative Radio Signal Features�. 2016. Technical Report, Space and Naval Warfare Systems Center Pacific, San Diego, United States. http://www.dtic.mil/docs/citations/AD1022600

3. Goldstein, M. and Uchida, S., �A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data�. PLOS.org, 2016.� http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0152173

KEYWORDS: Machine Learning; Unsupervised Learning; Radio Frequency Analytics; Anomaly Detection; Software Defined Radio; Data Analytics