A new Automatic Prohibited Item Detection (APID) machine learning-based algorithm for identifying non-explosive weapons and other items prohibited aboard commercial aircraft will now move into the certification and qualification process, following successful testing at Las Vegas’ McCarran International Airport earlier this year.
APID is intended to integrate with existing CT X-ray scanners to accelerate the detection of prohibited items and reduce the frequency of secondary screenings and Transportation Security Officer intervention, the Science and Technology Directorate said Thursday.
The algorithm was developed and matured by Leidos through funding by the Department of Homeland Security S&T’s Screening at Speed Program.
“Using machine learning algorithms to create rapid inspection processes at the nation’s airport checkpoints will not only improve overall security, but boost TSO screening efficiency and cognitive load and enhance traveler satisfaction with the airport security-screening experience,” said Dr. John Fortune, manager of the S&T Screening at Speed Program.
The Screening at Speed Program conducts transformative research and development efforts aimed at improving passenger experiences while increasing the effectiveness of aviation security.
TSA’s Office of Requirements and Capability Analysis ran a two-week study in August to study the algorithm in an operational environment, gain TSO feedback and evaluate the effectiveness of the operations concept.
Following the successful review, the Screening at Speed Program will now direct its efforts to testing and maturing the algorithm for certification to meet TSA’s detection and operational standards, with the future goal of enterprise-wide integration and use.
