TSA plans to add machine learning to carry-on baggage scans
- By Susan Miller
- Apr 20, 2018
The Transportation Security Agency plans to incorporate machine learning into the computer tomography scanners that are starting to be used at airport security checkpoints.
To advance the Accessible Property Screening Systems program, TSA is looking for researchers and industry partners to develop algorithms that could improve the automated detection of explosives and prohibited items among carry-on baggage and speed passengers through the checkpoints.
Although it has been used to screen checked luggage for explosives since 2001, CT scanning is a relatively new tool for examining carry-on baggage where it would have to identify prohibited items like knives and disassembled weapons. The 3-D imaging and detection software in the CT scanners would increase the speed and accuracy of the scans, flagging the threats operators should manually check. It may eliminate the need for passengers to put their electronics and liquids in separate screening bins, TSA said prior to a June 2017 test of the technology.
With or without the machine learning, the CT scanners are expensive. Scanners made by Analogic cost $300,000, about double the cost of X-ray scan machines, according to a report in Wired. The TSA's fiscal year 2019 budget request included $71.5 million that would allow the agency to purchase and deploy at least 145 scanners and expert staff, Administrator David P. Pekoske said.
TSA is also working with university and industry partners to more accurately identify prohibited items. The agency's Innovation Task Force is giving CT vendors real-world operational data and end-user feedback and to advance the technology, Pekoske said in a Jan. 18 testimony before the House Homeland Security Committee.
At a May 8 industry day, TSA will discuss the scope, requirements and milestones for screening machine learning activities.
More information is available here.
Susan Miller is executive editor at GCN.
Over a career spent in tech media, Miller has worked in editorial, print production and online, starting on the copy desk at IDG’s ComputerWorld, moving to print production for Federal Computer Week and later helping launch websites and email newsletter delivery for FCW. After a turn at Virginia’s Center for Innovative Technology, where she worked to promote technology-based economic development, she rejoined what was to become 1105 Media in 2004, eventually managing content and production for all the company's government-focused websites. Miller shifted back to editorial in 2012, when she began working with GCN.
Miller has a BA and MA from West Chester University and did Ph.D. work in English at the University of Delaware.
Connect with Susan at firstname.lastname@example.org or @sjaymiller.