Generation of Synthetic Exemplar Data with Relevant Tactics

OUSD (R&E) MODERNIZATION PRIORITY: Artificial Intelligence/Machine Learning; General Warfighting Requirements (GWR) TECHNOLOGY AREA(S): Air Platform 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. Please direct questions to the Air Force SBIR/STTR HelpDesk: usaf.team@afsbirsttr.us. OBJECTIVE: Propose algorithms and methods for synthesizing multi-modal pilot training data to expedite development of novel analytics. DESCRIPTION: Security requirements for pilot training and readiness data sets hamper development and validation of analytics. Performers are often unable to access sufficient data, or they find the access controls inefficient and time consuming. This effort seeks: 1. Algorithms or techniques for synthesizing data sets including representative data formats, modalities, and behaviors suitable for developing and validating PBT-focused analytics 2. Characterization of the quality, scope, and limitations of the synthetic data sets; i.e., what types of analytics and stages of development/validation are suitable for the synthetic data set versus real data sets Consider applying scoring methods from the Generalized enrichment of pilot training data through automated classification of pilot training objectives, scenarios, and performance area to rate synthetic behavior PHASE I: This topic is intended for technology proven ready to move directly into a Phase II. Therefore, a Phase I award is not required. The offeror is required to provide detail and documentation in the Direct to Phase II proposal which demonstrates accomplishment of a Phase I-like effort, including a feasibility study. This includes determining, insofar as possible, the scientific and technical merit and feasibility of ideas appearing to have commercial potential. PHASE II: Eligibility for D2P2 is predicated on the offeror having performed a Phase I-like effort predominantly separate from the SBIR Programs. The goal of phase II is to develop, demonstrate, and validate software tools for generating synthetic data on-demand meeting varying requirements for suitability to analytics development and validation. Conduct a study characterizing limitations of synthetic data sets and make recommendations on which problems are well-suited to synthetic data. Document lessons learned, needs for further research, and strengths/limitations of the considered approaches. PHASE III DUAL USE APPLICATIONS: The contractor will pursue commercialization of the various technologies developed in Phase II for transitioning expanded mission capability to a broad range of potential government and civilian users and alternate mission applications. Direct access with end users and government customers will be provided with opportunities to receive Phase III awards for providing the government additional research & development, or direct procurement of products and services developed in coordination with the program. REFERENCES: Patki, N. (2016).The Synthetic Data Vault: Generative Modeling for Relational Databases. [Master's Thesis, Massachusetts Institute of Technology]; Anderson, J., Kennedy, K.E., Ngo, L., Luckow, A., Apon, A. (2014). Synthetic data generation for the internet of things. IEEE Conference on Big Data. KEYWORDS: pilot training; synthetic data; privacy; security; verification; validation