KNOWMADICS, INC. — Department of Defense SBIR Phase I: DTRA224-004

Description

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 distributed sensor network (i.e., all of the smartphones people carry with them all the time in a given geographic region), these sensor arrays provide unique potential to improve the quantity and quality of data available on low-yield explosions. To leverage this data and translate it into a unique source of intelligence data, Knowmadics, Inc. and our teammates at Gilded Ibex LLC, propose a Phase I effort to design, prototype, and conduct initial feasibility demonstration of the Baseline for Artificial Intelligence Learning of Indications and Warnings from a Cellular Kit (BAILIWICK).The full-scope BAILIWICK solution will provide a means for scaled collection of accurate and timely information on suspected nuclear-related activity in geographic areas of interest. The Phase I BAILIWICK effort will focus on establishing the feasibility of key BAILIWICK technology and deployment elements. The first line of effort (LOE) this will include is a market and technical analysis of cellular device sensor capabilities (e.g., accelerometers) and resolutions for two (threshold) to four (objective) targeted regions of of interest. These analyses will seek to characterize the feasibility of relying on the data from cellular devices that are prolific in specific regions of interest to identify the types of signatures that low-yield explosions produce. The second LOE of the Phase I feasibility demonstration will be defining a technical pathway to implement software development kits at scale, without reliance upon a specific app being downloaded or the use of specific hardware. This will include detailing a plan and a technical milestone to achieve cellular device saturation with the targeted regions of interest. The final LOE for Phase I will be to design and establish technical milestones to generate the synthetic and/or live data necessary to both test BAILIWICK functionality, and to enable development of artificial intelligence algorithms to process and analyze collected data to extract event signals of interest that can be used for event detection, location, and characterization and associated indicators and warnings. The success of these Phase I efforts to demonstrate the feasibility of both the technical elements and the scalability of BAILIWICK will yield a Phase II roadmap for development, testing, and evaluation of a full-scope BAILIWICK minimum viable product (MVP) solution to validate the quality of data it can acquire and the utility of that data to support US Forces and our interests.