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 ...

Under this STTR solicitation N20B-T028, the goal is to build on the strengths of HyPerComp’s development in the HDphysics suite of tools to meet NAVAIR’s requirements in solving large-scale problems in electromagnetics.  One area that will receive a major attention in this effort is the development of high order curved meshes for arbitrary geometries with small- and large-scale features that ...

Virtual EM is proposing a method to achieve orders of magnitude improvement in computational efficiency in full-wave CEM codes by using high-order curved elements. Virtual EM’s own commercial product VirAntenn™ will provide the CEM setting for both developing and implementing the new capability in Phase I and Phase II, respectively. Using multi-wavelength long cells with high-order basis forms ...

In this program, we propose to adapt a new, high-performance integration platform for RF photonics to operation at 1um, and to realize integrated optical transmitters that meet the requirements of the program.

In this program, Freedom Photonics and its research partner institution will demonstrate an analog optical link using novel record performance laser, modulator and photodiode technology. Preliminary designs for a miniature, deployable implementation will be conducted as well in Phase I.

Software and hardware flaws can be exploited to make programs perform unintended computations or leak sensitive data. We propose to counter these threats by isolating libraries and other program units inside a single process. The developer will insert source-level annotations that i) map code and data units to compartments and ii) capture how each compartment is intended to interact with others, i ...

We propose a suite of video processing algorithms utilizing the machine learning (ML) techniques of artificial intelligence (AI) reinforcement learning, deep learning, and transfer learning to process submarine imagery obtained by means of periscope cameras. Machine learning (ML) can help in addressing the challenge of human failure of assessing the data of periscope imagery. Though pre-tuned blac ...

Areté and the Machine Learning for Artificial Intelligence (MLAI) Lab at the University of Arizona (UofA) will develop and demonstrate new approaches that improve the performance of in situ machine learning (ML) algorithms as they evolve over time, adapt to new environments, and are capable of transferring their learned experiences across platforms.  Technological advances that will be brought t ...

Condition-based maintenance plus (CBM+), and cyber-physical systems (CPS) in general, depend on correct sensor data for analysis, decision making and control loops. If the sensor data that arrives at the point of processing is not correct, or more accurate, is outside its accepted error range, then any further processing will be incorrect as well. This could result in, in the case of CBM+, not det ...

High power generation at millimeter wave (mm-wave) frequencies is expensive and the concurrent need for wide bandwidths at these frequencies creates an extremely challenging problem. Currently the most stringent requirements for mm-wave power and bandwidth can only be practically met by vacuum electronics (VE) technology. At present, vacuum amplifiers with the required performance are prohibitivel ...