Award Data

The Phase I effort of this program builds on our experience in developing automated fault-injection and testing frameworks. We will expand upon the CPU-based fault injection methodology developed as part of the Dynamic Robust Single Event Upset Simulator (DrSEUs) to also target FPGA resources. This updated methodology will serve as the foundation for an automated fault injection platform that targ ...

Cellular devices contain several sensors required to enable functionality and detect environmental conditions.  A recent example of practical application of data generated by these sensors are SARS-CoV-2 (COVID-19) contact tracing.  Perhaps more interesting is Google’s development of algorithms to use Android devices as “mini seismometers” to detect earthquakes. When considered as a distr ...

This STTR Phase I project proposes novel deep learning models for generating realistic multi-spectral remote sensing imagery, specifically in the infrared (IR) and near-infrared (NIR) bands. The proposed system enables synthesis of semantically realistic imagery and provides parametric control of synthesizing objects-of-interest, type of terrain and land cover, time or season, weather, cloud cover ...

To address the challenge DTRA faces in identifying rare objects of interest to defeat improvised threat networks using multispectral imagery, small business ARiA and research institution Michigan Technological University (MTU) will develop and demonstrate the feasibility of the Generative Augmentation Process (GAP). The Phase I effort will (1) conduct a proof-of-concept study for GAP by developing ...

This Phase I SBIR project seeks to demonstrate a design-build-test-learn (DBTL) system for engineering nanocarriers (NCs) able to deliver molecular cargo across the blood-brain barrier (BBB) via receptor-mediated transport (RMT). The approach relies heavily on in silico design and characterization of NCs, with the ultimate goal of predicting BBB permeability of a given NC design with machine learn ...

Saltenna has developed several innovative, patented antenna systems which significantly increase capacity for RF signal transmissions through conductive media via efficient excitation of surface electromagnetic waves, which for the sake of brevity are usually called “plasmons”. As illustrated in Fig. 1, our proprietary battery-powered 2.45-GHz transmitting antenna is capable of doing seemingly ...

The goal of the proposed project is to create Kin-X, a novel software system to generate both rapid and deep intelligence from a wide variety of DNA types by inferring distant kinship relationships between individuals and reconstructing familial pedigrees. Kinship inference and pedigree reconstruction are both computationally intensive processes, and our proposed system is designed to achieve both ...

By combining modern ML statistical processing frameworks and with scalable secure communications DCTER provides a foundation for heterogenous sensor reasoning while leveraging advances in edge AI. This open source-driven processing foundation and standards based communication enables DTRA to leverage the rapidly evolving commercial edge AI/ML advancements while avoiding vendor lock-in (i.e., consi ...

Fenix Group’s COTS Banshee Tactical Radio (BTR) is a low visibility, jam-resistant RF radio system; it also provides an onboard TAK server to support applications and ATAK plug-ins locally. Operating over 2 simultaneous configurable bands, the BTR hosts up to 256 3GPP LTE connections to support voice, data, video streaming, and sensor connection at up to 300 Mbps download/100 Mbps upload. The BT ...

The project will develop numerically inspired deep neural nets (NINNs) in order to replace the stiff ordinary differential equation (SODE) solvers currently being used to integrate chemical species in high-fidelity computational fluid dynamics simulations. Unlike traditional deep neural nets, the architectures and optimization strategies used to learn the physics of a problem will be based on the ...