Award Data

Deep learning offers a powerful and extensible toolset to achieve or perhaps even exceed human-level accuracy for automatic object detection in stream of commerce data, and offers a path toward improving the effectiveness of scanners, reducing wait times, and radically increasing the accuracy of screening, where automatic object detection support is essential. A deep learning-based system for auto ...

The Synthetik team is uniquely placed to conduct this Phase II SBIR effort where we plan to extend and optimize our DeepSpektra high-resolution hyperspectral and deep learning-based non-contact detection technology to provide enhanced, targeted sampling for explosive and illegal drugs trace detection that was successfully demonstrated in Phase I.Synthetik's DeepSpektra technology directly addresse ...

Wildlife are a reservoir of diseases affecting both humans and domestic animals. These wildlife reservoirs represent a potential threat to public health, serving as a continuous and difficult to eradicate source of infection for zoonotic diseases, but may also represent a significant economic threat to US agriculture. In particular, wild ruminants including white-tail deer may harbor vector-bo ...

The United States Special Operations Command’s Special Boat Teams are routinely exposed to an environment prone to injury and the long-term effects of repetitive impact stress. The primary cause for injury and long-term degenerative musculoskeletal effects is the repetitive impacts incurred as the MK V and NSW RIB vessels impact the ocean’s surface. The goal of SOCOM02-007 Phase II research is ...

Currently fielded aviation passenger screening systems are large, fixed systems capable of detecting concealed objects on a person. While this approach is useful for standard passenger screening, there are additional requirements for a handheld system to enable concepts of operations that the fixed systems canNt accommodate.Previous systems have tended to be passive systems that lack the resolutio ...

Synthetik propose to leverage a new generation of high-resolution, low-cost (e.g. less than $1,000, 25-100x less than currently available systems) hyperspectral cameras in conjunction with state-of-the-art machine learning to rapidly image, process and predict locations where residues of interest are present to deliver a targeted, relevant and more dense samples to the trace detector.During Phase ...

Deep learning offers a powerful and extensible toolset to achieve or exceed human-level accuracy for automatic object detection in stream of commerce data. However, in order to train deep machine learning-models for 2D and 3D screening a significant quantity of high-quality ground-truth training data is required.We propose SoCPhysics: A Stream-of-Commerce Physics-Based Data Generation Application, ...

The Synthetik team is pleased to provide this Phase I SBIR proposal to develop a distributed, interoperable, ISO 18013-5-compliant and mdoc-based digital software badge (DSB). The DSB will provide the capability to prove a first responder personnel’s identity and qualifications onsite securely and efficiently in a disaster response operating environment.During Phase I we will demonstrate th ...

Arsenic contamination of groundwater is a problem facing many areas of the United States and the rest of the world. This problem has been highlighted by the U.S. Environmental Protection Agency¿s decision to mandate reductions in the acceptable level of arsenic in drinking water from 50 ppb to 10 ppb by the year 2006. In South Dakota alone, 18.6 percent of small and rural water supply systems w ...

Wildlife are a reservoir of diseases affecting both humans and domestic animals. These wildlife reservoirs represent a potential threat to public health, serving as a continuous and difficult to eradicate source of infection for zoonotic diseases, but may also represent a significant economic threat to US agriculture. In particular, wild ruminants including white-tail deer may harbor vector-bo ...