Press Release: DHS to Support Machine Learning Development for Airport Security

S&T Public Affairs, 202-254-2385

Washington, D.C. – With a growing need to improve the security, efficiency and accuracy of passenger and baggage screening, the Department of Homeland Security (DHS) Small Business Innovation Research[1] (SBIR) Program is working with a small business to advance explosive detection equipment. Synthetik Applied Technologies was awarded funding to develop machine learning training data that simulates human travelers and baggage object models to support machine learning algorithms.

“As threats to our nation’s airports continue to evolve, we are committed to investing in technologies that will improve the security posture of aviation checkpoints, while minimizing the inconvenience to passengers,” said William N. Bryan, DHS Senior Official Performing the Duties of the Under Secretary for Science and Technology. “We look forward to seeing the technology developed through the SBIR Program that supports our vision for a passenger screening process that is reliable, less invasive, and efficient.”

The DHS SBIR Program, administered by DHS Science and Technology Directorate[2] (S&T), selected Synthetik Applied Technologies, based in Austin, Texas, to participate in Phase II of the program, based on the successful demonstration of feasibility in Phase I for their Synethic Data Training For Explosive Detection Machine Learning Algorithms[3] technology solution.

In Phase II, Synthetik Applied Technologies will continue their efforts to develop synthetic training data that will enhance machine learning object detection algorithms to improve detection and reduce false alarms. For machine learning algorithms to reach their peak performance, they must be trained on a very large amount of data, and collecting and preparing this data is typically an expensive and time-consuming process. Synthetic data generation creates the capability to generate complete, annotated datasets in a matter of minutes without handling dangerous materials or initiating human subjects’ protocols. This technology would streamline the security screening process, creating an improved passenger experience for the traveling public.

1 2 3