Award Data

Deep Neural Networks have become ubiquitous in the modern analysis of voluminous datasets with geometric symmetries. In the field of Particle Physics, experiments such as DUNE require the detection of particle signatures interacting within the detector, with analyses of over a billion 3D event images per channel each year; with typical setups containing over 150,000 different channels.  In an ...

In the setting of altitude-induced hypoxia, operator cognitive capacity degrades and can compromise both individual and team performance. This degradation is linked to falling brain energy (ATP) levels and an increased reliance on anaerobic energy production from glucose. Ketone bodies are the evolutionary alternative substrate to glucose for brain metabolic requirements; previous studies have sho ...

The objective of this proposal is to develop instrumentation and algorithms for acquiring facial features for facial recognition in low- and no-light conditions.We will use cross-spectrum matching by exploiting infrared polarimetric imagery which tends to show features that match more closely visible imagery than conventional infrared.In addition to thermal infrared, we will also test subjects in ...

On this effort Toyon Research Corp. and The Pennsylvania State University are developing deep learning-based algorithms for object recognition and new class discovery in look-down infrared (IR) imagery. Our approach involves the development of a hybrid classifier that exploits both transfer learning and semi-supervised paradigms in order to maintain good generalization accuracy, especially when li ...

Signature Research, Inc. (SGR) and Michigan Technological University (MTU) propose a Phase I STTR effort to develop a learning algorithm which exploits the spatio-spectral characteristics inherent within IR imagery and motion imagery.Our archive of modelled and labeled data sets will allow our team to thoroughly capture the variable elements that will drive machine learning performance.The overall ...

Cost-effective application of advanced commercial electronics technologies in DoD space systems requires early development of radiation-hardened-by-design (RHBD) techniques, and use of simulations is critical to the efficiency of this process. CFDRC has developed an integrated, mixed-mode simulation approach allowing their NanoTCAD device physics simulator to interface with commercial circuit simu ...

This program will demonstrate how additive manufacturing technologies can be used with reactive and high energy materials to create rapid and flexible fabrication of payload and munitions. Our primary approach to this problem will be to use powder bed binder printing techniques to print reactive structures. The anticipated feedstock will consist of composite particles containing all reactant spe ...

For effective protection against EMP and HPM threats, it is important to understand the physics of the threats, and also to quantify the effects they have on electrical systems. EMP and HPM vulnerability testing requires delivery of high peak power and electric fields to distant targets. The most practical solution to simulate such environments is to develop a modular, optically-isolated MV-antenn ...

The US DoD requires robust ways of neutralizing threats posed by hostile powers and terrorist organizations that may be in possession of dangerous weapons of mass destruction (WMDs). Unfortunately, the weapons currently available to the DoD do not offer a way for the WMD to be destroyed without risking the spread of that material throughout the area. The strategy for the defeat of biological weapo ...

Terrorist use of radioactive nuclear materials via nuclear and/or radiological dispersion devices (dirty bombs) is a serious threat. Therefore, it is critical to detect the proliferation of nuclear material. Critical challenges facing this objective include: (a) high sensitivity detection of signature emissions (e.g., gamma rays) from common radioactive isotopes behind shielding, and (b) cost-effe ...