Award Data

The team of Signature Research, Inc. and Michigan Technological University will develop and demonstrate methods and metrics to evaluate the performance of machine learning-based computer vision algorithms with low numbers of samples of labeled EO imagery. We will use the existing xView panchromatic dataset to demonstrate a proof-of-concept set of tools. If successful, in Phase II, we will extend t ...

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 ...

The multidisciplinary area of GEOINT is changing and becoming more complex. A major driver of innovation in GEOINT collection and processing is artificial intelligence (AI). AI is being leveraged to help accomplish spatial analysis, change detection, and image or video triage tasks where filtering objects of interest from large volumes of data is critical. NGA is confronting the changing GEOINT l ...

Biomimetic Slope Adaptive Foot-Ankle Prosthesis This project will develop an innovative mechanical/hydraulic foot-ankle system that will help lower extremity prosthesis wearers to walk or run in a wider range of environments with close to normal walking biomechanics. The proposed system will have a unique combination of features, all mechanically implemented without electronics or external powe ...

The primary objectiveis to develop acommercially-viable prototype of theslopeadaptive prosthesis design and to iteratively improvethe design based on ISO standards testingand rigorous usein human subject field trials. The proposed work will build upon knowledgegained in PhaseI of the project,which established feasibility for this design approach in alightweight, passive hydraulicfoot-anklesystem. ...

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 ...

Deep Convolutional Neural Networks (DCNNs) have become ubiquitous in the analysis of large datasets with geometric symmetries. These datasets are common in medicine, science, intelligence, autonomous driving and industry. While analysis based on DCNNs have proven powerful, uncertainty estimation for such analyses has required sophisticated empirical studies. This has negatively impacted the effect ...

Research has identified that handoffs are particularly important communication processes, during which communication error can lead to patient safety situations. Organizations have created standard practices and training materials to encourage teamwork communication for handoffs, however these do not necessarily capture the needs of military medicine of combat casualty care. Combat casualty handof ...

This expansion effort will enable SoarTech to harden the C-CHAT prototype for use during field exercises and increase the current 4 TRL to a 7 TRL. Working with partners at the USMC Field Medical Training Battalion (FMTB) and the University of Central Florida (UCF), we will enhance C-CHAT to run as a stand-alone application on a DoD-approved Android smartphone (e.g., the Samsung Galaxy S20 Tactica ...

Combat casualty handoffs are critical communication moments during which responsibility for the patient and important casualty information is transferred between providers. The nature of these handoffs requires specialized training, for which no standardized framework currently exists. The proposed effort aims to develop a capability, compatible with current DoD systems, that provides caregivers w ...