University of Manchester Develop AI Verification

Researchers have developed an AI footstep recognition system that could be used to improve airport security.

17:32 30 May 2018

Researchers at the University of Manchester have developed a cutting-edge artificial intelligence (AI) verification  system in collaboration with the Universidad Autonoma de Madrid in Spain. The technology could be used as an alternative to intrusive airport verification protocols and improve airport security.

 

The system has been designed to measure an individual’s gait or walking pattern when they walk on a pressure pad in the floor. The results of initial tests have confirmed that on average, the AI system has correctly identified an individual 99.3per cent of the time.

 

Omar Costilla Reyes, from Manchester’s School of Electrical and Electronic Engineering, explains: “Each human has approximately 24 different factors and movements when walking, resulting in every individual person having a unique, singular walking pattern. Therefore monitoring these movements can be used, like a fingerprint or retinal scan, to recognise and clearly identify or verify an individual.”

 

“Focusing on non-intrusive gait recognition by monitoring the force exerted on the floor during a footstep is very challenging. That’s because distinguishing between the subtle variations from person to person is extremely difficult to define manually, that is why we had to come up with a novel AI system to solve this challenge from a new perspective.”