DHS Awards $2M for Small Businesses to Develop Machine Learning for Detection Technologies – Homeland Security Today
The Department of Homeland Security (DHS) Small business innovation research (SBIR) program recently granted funding to two small businesses to develop contactless, low-cost training and classification technologies for machine learning. Integrated machine learning platforms can dramatically reduce time, redundancy, and costs, and improve accuracy in detecting threats such as explosives, chemical warfare agents, and narcotics.
“S&T leverages significant advances in artificial intelligence and machine learning and their ability to improve threat detection,” said Kathryn Coulter Mitchell, DHS Senior Official Performing the Duties of the Under Secretary for Science and Technology. “The SBIR program gives S&T the opportunity to work with innovative small businesses and develop machine learning tools that are critical to threat detection. I look forward to seeing the technologies that will be developed through this SBIR effort. “
Physical Sciences Inc. (PSI), based in Andover, MA, and Alakai Defense Systems, Inc. (Alakai), based in Largo, FL, each received approximately $ 1 million in SBIR Phase II funding to add technology develop that can quickly and accurately identify unknown spectrometer signals as safe or threatening. The DHS SBIR program, led by Program Director Dusty Lang and administered at DHS Science and Technology Technology Directorate (S&T) selected PSI and Alakai to participate in Phase II of the program after the feasibility of the compact, accurate and fast machine learning classification module for detection technologies from both companies was demonstrated in Phase I.
In phase II, PSI will further develop its deep learning algorithm for the detection and classification of traces of explosives, opioids and narcotics on surfaces for optical spectroscopic systems. PSI will expand the capabilities of the algorithm from infrared reflection spectroscopy to Raman spectroscopy as well as a proposed functional module prototype with a classification accuracy of more than 90 percent.
During its Phase II efforts, Alakai will continue to develop the Agnostic Machine Learning Platform for Spectroscopy (AMPS), which quickly and accurately detects traces of hazardous and related chemicals from a variety of spectroscopic instruments.
“Our impetus for the development of these machine learning modules stems from the operational requirements of the Transportation Security Administration for the fusion of threat signatures, the ability to learn, recognize and classify new threats without explicit programming and ultimately to increase the detection accuracy” said Thoi Nguyen, DHS S&T Program Manager for the Next Generation Explosive Trace Detection (NGETD) program. “With experienced industry partners like Alakai and PSI and our strong collaboration with TSA, we hope these efforts will contribute to broader machine learning applications across the Homeland Security mission room.”
Upon completion of the 24-month Phase II contract, the SBIR award winners will have developed a prototype to demonstrate the advancement of the technology and cite the potential for Phase III funding.
In Phase III, SBIR artists will seek funding from private and / or non-SBIR government sources with the ultimate goal of commercializing and bringing to market the technologies from Phase I and II.
Register now for the Insights Outreach: Getting started with SBIR Webinar on July 6, 2021 from 2 p.m. to 2 p.m. ET. During this live webinar, attendees will learn from the DHS SBIR Director how small businesses can participate in the SBIR program and how technologies developed by SBIR can support DHS component technology requirements.
For more information on the DHS SBIR program, please visit: https://www.dhs.gov/science-and-technology/sbir.
Further information on S & T’s innovation programs and tools can be found at: https://www.dhs.gov/science-and-technology/work-with-st.
(Visited 1 time, visited 1 time today)