Award Data

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 ...

There has been substantial development in data analytics. However, the complex mathematical formulation of “big data analytics” is difficult to populate in general manufacturing plants. There is a need for an SPC-like tool to enable the acceptance of the advanced data analytics and its visualization. The MD Compiler, a tool to bridge the gap between data available and the information demanded ...

Network measurement is a critical element in networks but it has largely been an afterthought and inadequately secured. With the emergence of Information-Centric Networking technologies, specifically the popular open source Named-Data Networking (NDN), there is the early stage opportunity to create a useful and flexible network measurement system that can accommodate a range of network probes. Thi ...

Steven Winter Associates, Inc. (SWA) hereby proposes to undertake research to develop a self-configuring residential conditioned air zoning system for low load energy homes. The Phase I prototype will feature zone nodes and a master controller. The zone nodes will measure and wirelessly report environmental conditions to the central controller, and modulate a damper based on commands received from ...

A dual plane Compton imager prototype system with large volume pixelated CZT detectors will be built for spectrally resolved MeV gamma ray tomographic applications. These two planes will be operated at independent clocks and they will be synchronized via a common periodical pulse. The common periodical pulse is self-generated so it does not rely on external pulse generator. Each detector will be c ...

In this SBIR effort, Nikira Labs Inc. proposes to develop a compact Raman fiber optic probe with inline spectral filtering that improves fiber-coupled Raman measurements by filtering out Raman scattering from the excitation fiber and elastically scattered laser light from the collection fibers. The technology will enable compact fiber probes for Raman studies and complement existing NIST Raman spe ...

To address the National Geospatial-Intelligence Agency (NGA) need for overhead imagery analysis algorithms that provide uncertaintymeasures for object recognition and aggregation, Intellisense Systems, Inc. (ISS) proposes to develop a new Variational Object Recognition andGrouping Network (VORGNet) system. It is based on the innovation of implementing a Bayesian convolutional neural network (CNN) ...

We propose to build ARGON, the ARet Ground-to-Overhead Network. The network will ingest analyst-supplied ground-level imagery ofobjects and retrieve instances of those objects in overhead collections, providing tips back to the analysts. A proprietary method of trainingthe network, leveraging in-house capabilities, data sources, and tools, will be critical to its success. During Phase I, we will p ...

Building interpretable, composable autonomous systems requires consideration of uncertainties in the decisions and detections theygenerate. Human analysts need accurate absolute measures of probability to determine how to interpret and use the sometimes noisy resultsof machine learning systems; and composable autonomous systems need to be able to propagate uncertainties so that later reasoningsyst ...