baggage scans (MicroOne/Shutterstock.com)

Harnessing machine learning for baggage scans

The Transportation Security Administration is looking to Silicon Valley startups to help it bring machine learning to security screening to improve the accuracy of airport baggage scanners.

Through an Other Transaction Solicitation, the Department of Homeland Security's Science & Technology Directorate and TSA's Office of Requirements and Capabilities Analysis are looking for a new way to detect evolving threats carried in airline passenger luggage.

Rapidly changing consumer electronics, the RFI said, are an example of a dynamic threat vector that evolves faster than next-generation detector hardware. TSA personnel looking at baggage scanner images might miss subtle new differences in how newly introduced consumer devices are wired or put together.

The agency wants developers to come up with AI-based methods that could automate detection algorithm training, allowing detection hardware to "intuitively recognize" such subtleties and new objects that come through airports in luggage. If that software can be easily plugged into existing detection gear at airports to identify subtle, but potentially devastating, threats to aircraft, TSA could move away from expensive and proprietary detection capabilities in its luggage screening hardware, while also avoiding labor-intensive hand searches.

The solicitation suggests a system using an image library combined with artificial intelligence could to learn to identify new items and distinguish between benign objects and potential threats.

The OTS would fund development efforts in four three- to six-month $200,000 sprints. TSA is holding an industry day in Menlo Park, Calif., on May 4.

Meanwhile, TSA is also investigating incorporating machine learning into the computer tomography scanners that are starting to be used at airport security checkpoints.

This article was first posted to FCW, a sibling site to GCN.

About the Author

Mark Rockwell is a senior staff writer at FCW, whose beat focuses on acquisition, the Department of Homeland Security and the Department of Energy.

Before joining FCW, Rockwell was Washington correspondent for Government Security News, where he covered all aspects of homeland security from IT to detection dogs and border security. Over the last 25 years in Washington as a reporter, editor and correspondent, he has covered an increasingly wide array of high-tech issues for publications like Communications Week, Internet Week, Fiber Optics News, tele.com magazine and Wireless Week.

Rockwell received a Jesse H. Neal Award for his work covering telecommunications issues, and is a graduate of James Madison University.

Click here for previous articles by Rockwell. Contact him at mrockwell@fcw.com or follow him on Twitter at @MRockwell4.


inside gcn

  • smart city (jamesteohart/Shutterstock.com)

    Toolkit for building a smart city plan

Reader Comments

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above

More from 1105 Public Sector Media Group