May 20, 2015 -
A research team led by Blair Armstrong of Basque Center on Cognition, Brain, and Language in Spain observed the brain signals of 45 subjects while they read a list of 75 acronyms, then used computer programs to identify any discrepancies between individuals, according to a report by New Scientist.
The subjects’ responses varied enough that the computer programs were able to identify the individuals with an accuracy rate of about 94 percent when the team repeated the test.
The research suggests that this kind of brainwave activity could serve as a method for security systems to verify individuals’ identity.
Though other methods of identifying people based on the electrical signals in their brain have been developed in the past, the noise related to the measurements of all the brain’s signals has made the data particularly difficult to analyze.
Armstrong’s method solves this issue by solely focusing on brainwaves from the area of the brain that relates to the function of reading and recognizing words, producing a clearer signal that can be measured faster.
These brain signals are generated when individuals access their semantic memories, which simply record the meanings of specific words.
Armstrong believes that this semantic memory-based method could be developed into a more personal and secure authentication alternative to fingerprint recognition or iris scanning.
“It stretches the boundaries of how we think about biometrics,” says Kevin Bowyer of the University of Notre Dame in Indiana. But he says that Armstrong’s method is currently far less accurate than scanning a fingerprint or iris, and – because of the need to place three electrodes on the scalp – it’s less convenient too.