The system employs artificial intelligence and machine learning to screen and interpret images from X-ray machines used to check cabin baggage. - CHANGI AIRPORT GROUP
SINGAPORE: Security checks for passengers flying out of Changi Airport could be up to 50 per cent quicker, if a trial to automatically detect prohibited items in carry-on luggage takes off.
Changi Airport Group (CAG) is currently testing a system at Terminal 3 that employs artificial intelligence (AI) and machine learning to screen and interpret images from the X-ray machines used to check cabin baggage at the boarding gate.
This reduces the time needed to process these images and the chances of human error, said the airport operator.
The initial results have been promising, CAG added, with the new AI-powered system performing as well as, or even better than, human security screeners in flagging some of the prohibited items that it has been trained to detect.
Items that are not allowed in carry-on bags include dangerous substances such as insecticides, cigarette lighters and sharp objects such as pocket knives.
CAG declined to provide more details about the trial when asked, citing security reasons.
Reports elsewhere suggest that X-ray images from bag scanners can be screened up to five times faster with AI algorithms than a human operator. According to the magazine Airport World, multiple trials of such algorithms are under way in places such as China, the Netherlands and the United States.
CAG said the development and trial of the new security screening technology – which is known in the industry as an Automated Prohibited Items Detection System (Apids) – is still in its early stages.
It is currently being used only to assist security officers at Changi Airport by highlighting items it recognises as a threat.
The eventual goal, however, is to increase the level of automation so that security officers need manually check and review only the bags that the system has flagged. This is similar to how security screening is conducted for checked baggage now.
“As the technology matures, Changi will decide whether to expand its use across the airport,” said CAG in the November issue of its e-magazine Changi Journeys.
“This is expected to further improve the speed of clearance by up to 50 per cent, as well as enabling manpower resources to be optimised and redeployed to other areas,” it added.
While it noted that security screening operations are one of the most manpower-intensive touchpoints at the airport, CAG declined to say how many security screeners currently work there.
Airports in other countries have faced security staff shortages, which have led to long lines for passengers as air travel rebounded.
Currently, security screeners at Changi Airport mainly rely on two-dimensional images produced by X-ray machines to detect whether there are dangerous items in carry-on luggage.
Newer bag scanners use computed tomography, or CT scans, to produce 3D images that provide more details, and allow passengers to keep electronics such as laptops inside their bags during the screening process.
However, with tens of thousands of carry-on bags passing through the airport daily and a wide variety of prohibited items that need to be detected, CAG said, security screening is a highly challenging and time-consuming role.
Apids, which can be used to process both 2D and 3D images, has been identified as a way for CAG to augment its capabilities and increase the productivity of airport security screeners.
CAG said its trials are currently focused on improving the system’s capabilities.
“With the number of bags increasing as air travel continues to recover strongly at Changi Airport and passengers packing more items into their bags, one key area of improvement for Apids is to reduce the rate of false alarms to make it operationally viable, as well as to expand the list of prohibited items that it can detect,” it added.
Passenger traffic at Changi Airport in September 2023 was at 89 per cent of pre-pandemic levels in 2019, with 4.87 million passengers passing through.
CAG said the AI system has to be trained to recognise benign items as well, so that it flags only items of concern or unknown objects.
More work is needed on the regulatory front too.
While protocols have been developed in Europe to assess if Apids can meet international security screening standards, CAG said further discussion is needed among international bodies and state regulators on policies for adopting this new technology. - The Straits Times/ANN
