Award Data

Physical Sciences Inc. (PSI) proposes to develop an Advanced Learning-Enabled Threat Search (ALERTS) software to significantly enhance detection range and source classification accuracy during search for Special Nuclear Materials and other radioactive threats. The software will implement Machine Learning algorithms for automated extraction of spectral and temporal features by training on sets of g ...

"Deep Learning for standoff detection of Special Nuclear Material (DLeN) applies the same deep learning techniques that allow computers to beat human performance in image recognition and the game of Go to detecting Special Nuclear Material. Spectral analysis and signal processing can in some cases be augmented by the use of much larger neural nets that conduct much deeper analysis of features of t ...

To effectively counter Weapons of Mass Destruction (WMD) we must be able to accurately and sensitively detect the sites of WMD development. While the reagents and byproducts of nuclear activity may be rapidly depleted from environmental sites, those transient perturbations leave a lasting mark on the resident microbial communities by promoting and restricting the growth of different microorganisms ...

Aret Associates and Oak Ridge National Laboratory (ORNL) propose an interdisciplinary effort to meet the challenges of developing a soil microbiome-based nuclear activity biomonitoring application. Our approach combines Arets expertise in decision theory and bioinformatics with ORNLs subject matter expertise in microbial ecology and contaminant signatures. We will adapt and extend our high featu ...

"Increasing the distance for standoff detection of nuclear materials, beyond that capable with direct radiation detection, using alternative signatures, such as the concentration of ionization in the surrounding atmosphere, improves the ability to locate, track and monitor this material. Ionizing radiation generates free elections, ions, and exited states in the nearby atmosphere, even when the s ...

"SIFT will develop Plan Recognition for Multi-Source Reasoning Over Sources and Events (PRIMROSE) to provide high-performance, probabilistic plan recognition to DTRA, addressing the intelligence analysis problem of information overload. PRIMROSE will perform high-performance plan recognition and integrate the results into JIPOE-based intelligence processes. In PRIMROSE: (1) the YAPPR2 plan r ...

In Phase I of PLATO (Plan Learning Across Textual Observations ), Language Computer Corporation will explore how best to migrate state-of-the-art plan recognition techniques to the more complex genre of textual data addressing such issues as varied textual inputs, diverse subject matter domains, changes in agent plans and goals, unclear or underspecified temporal relationships between actions, an ...

"Anticipating future acts of creativity by our adversaries is very difficult. Yet, to avoid being blindsided by surprising new forms of WMD enabled by technology trends and scientific advances, DTRA must concern itself with exactly such future inventions. ATC-NY will develop the Archimedes system to give the DTRA an early heads up about anticipated technology, and scientific discoveries with po ...

We propose to develop Prediction of Emergent SCIENce & Technology (PRESCIENT), a system that mines a text corpus of scientific patents and publications to discovers emerging technologies that may impact WMD or CWMD. PRESCIENT will take as input a diverse corpus of patents and publications, including metadata about contributing authors and organizations, and will produce as output alerts with timel ...

Automatically identifying emerging technologies and research trends from the high volume of the worlds scientific publications is of great significance in order to stay ahead of the critical advances that impact the development of new and disruptive technologies. Semandex and Barnstorm will implement a prototype tool, INSIGHT, that will scan large datasets from web content services and perform ana ...