Fast Prediction of Human Safety Due to RF Exposure

TECH FOCUS AREAS: Directed Energy TECHNOLOGY AREAS: Biomedical OBJECTIVE: This topic seeks to design, develop, and test fast, automated tools for predicting safety of humans in Radiofrequency (RF) exposure environments for integration into DoD modeling, simulation, and analysis frameworks such as advanced framework for simulation, integration, and modeling (AFSIM). Technology approaches may take advantage of existing machine learning tools (e.g., Varied Interface & Phenomenology Engineering Relationship Suite Relationship Suite (VIPERS), TensorFlow), and existing software end-to-end frameworks (e.g., the Galaxy framework). DESCRIPTION: The government has access to a suite of tools for simulating the human body's thermal response to radio frequency (RF) exposure from nearby electronic equipment, radar, and other RF devices, with a focus on the safety of soldiers in these scenarios. Separate tools also exist for analysis of laser-tissue interaction at the physics-level. These tools are not currently integrated with mission-level applications such as AFSIM; however, the VIPERS tool, for example, enables AFSIM to directly drive arbitrary surrogate models. VIPERS also provides a linkage to Galaxy, which can be used to drive the physics simulations that produce data for the surrogate models. Therefore, while it is not necessary to integrate the thermal modeling tools with AFSIM, it is crucial that the thermal modeling workflows can be automated from frameworks such as Galaxy to be run on DoD clusters to produce input data for surrogates. Unfortunately, the process of combining physics-level thermal tools with machine learning applications and end-to-end simulation frameworks currently requires an analyst in the loop. These main-in-the-loop pieces include armature registration and posing for RF analysis of whole-body models, and uncertainty quantification across broad parameter spaces for RF and laser-tissue interactions. The government is interested in methodologies and implementations that will enable full automation of the thermal simulation workflow across whole populations of virtual humans, poses, and exposure scenarios. Current human body simulations can predict whole body energy deposition from microwave exposures at a 2-millimeter resolution in 10s of minutes, and large uncertainty quantification runs of RF and laser-tissue interaction may take days on high performance computing clusters. In order to be appropriate for use in DoD MS&A environments, quasi-real time operation (10s of seconds) of the developed surrogate models is desired, which should include the output of confidence intervals from the surrogate model simulations. PHASE I: Offerors should propose design methods for implementing existing tools for simulating the human body's thermal response to RF and laser exposure in quasi real-time (a >= 60x increase in execution speed). Methods should predict core and local temperature changes as a function of time, beam parameters, and body position. Method should also provide a measure of uncertainty quantification for the results. PHASE II: Phase II efforts will implement and deliver code to execute on DoD computing clusters. Accurate and quasi-real time performance on whole body thermal response to RF exposure will be demonstrated. PHASE III DUAL USE APPLICATIONS: Military applications include engagement modeling and simulation, risk assessment, and occupational health evaluations. Civilian applications include real time prediction of risks from RF occupational exposure. NOTES: 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 proposed tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement 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 Air Force SBIR/STTR Help Desk: usaf.team@afsbirsttr.us REFERENCES: Clive, Peter D; Johnson, Jeffrey A; Moss, Michael J; Zeh, James M; Birkmire, Brian M; et al. Advanced Framework for Simulation, Integration, and Modeling: Proceedings of the International Conference on Scientific Computing (CSC); Athens: 73-77. Athens: The Steering Committee of the World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp). (2015) KEYWORDS: Computation models; RF exposure; modeling environments