New York : Scientists in US are developing an automated system that will help to detect terrorists before they strike.
When a person is interrogated, the system will start tracking his or her behaviours and create a baseline data of the individual.
The system tracks individual characteristics of a person like face, voice, and physiology among other things, to help confirm personal identity of a person against scientifically tested behavioural indicators, scientists at the University of Buffalo said in a press release.
The system is developed to obtain a numerical score, which will determine whether an individual is about to commit a terrorist attack.
However, the researchers cautioned that no technology, no matter how precise it is, could be a substitute for human judgment.
“No behaviour always guarantees that someone is lying, but behaviours do predict emotions or thinking that can help the security officer to decide who to watch more carefully,” said associate professor of communication, Mark G. Frank.
He noted that individuals are randomly screened at the security checkpoints in airports and at border crossings.
A key advantage of the new system is that it will incorporate machine-learning capabilities, which will allow it to “learn” from its subjects during the course of a 20-minute interview.
That’s critical, because behavioural science research has repeatedly demonstrated that many behavioural clues to deceit are person-specific.
The system would reduce the shortcomings of humans during a screening process. “Human screeners have fatigue and bias, but the machine does not blink,” co-investigator of the project, Venu Govindaraju said.
“The system will fuse information from several biometrics, such as face, voice and body,” he said.