Biometric authentication, such as fingerprint scanning and the iris, is a staple of any spy film, and trying to circumvent these security measures is often a staple of the plot. But these days technology is not limited to spyware, as fingerprint verification and facial recognition are now common features in many of our phones.
Now, researchers have developed a potentially fragrant new option for the biometric security toolkit: your breath. In a report published in Chemical Communications, researchers at the Institute of Chemistry and Materials Engineering at Kyushu University, in collaboration with the University of Tokyo, have developed an olfactory sensor capable of identifying individuals by analyzing them. composed of his breathing.
Combined with machine learning, this “artificial nose”, built with a 16-channel sensor array, was able to authenticate up to 20 people with an average accuracy of over 97%.
In this age of information and technology, biometric authentication is a critical way to safeguard valuable assets. From the usual suspects of fingerprints, palm prints, voices and faces to the less common acoustic options of the ear and veins of the fingers, there is a variety of biometric data that machines can use to identify you. .
“These techniques are based on the physical uniqueness of each individual, but they are not infallible. Physical characteristics can be copied, or even compromised by injury,” explains Chaiyanut Jirayupat, the study’s lead author. “Recently, human odor has emerged as a new class of biometric authentication, essentially using your unique chemical composition to confirm who you are.”
One of these targets has been percutaneous gas: compounds produced from the skin. However, these methods have their limits because the skin does not produce a sufficient concentration of volatile compounds for machines to detect.
So the team turned around to see if human breath could be used.
“The concentration of volatile compounds in the skin can be as low as several parts per million or trillion, while the compounds exhaled from the breath can reach as many parts per million,” Jirayupat continues. “In fact, human breath has already been used to identify if a person has cancer, diabetes and even COVID-19.”
The team began by analyzing the subjects’ breath to see which compounds could be used for biometric authentication. A total of 28 compounds were found to be viable options.
From there, they developed an array of 16-channel olfactory sensors, each of which could identify a specific range of compounds. The sensor data was then passed to a machine learning system to analyze each person’s breathing composition and develop a profile that will be used to distinguish an individual.
Testing the system with six-person breath samples, the researchers found that it could identify individuals with an average accuracy of 97.8%. This high level of accuracy remained constant even when the sample size was increased to 20 people.
“This was a diverse group of individuals of different ages, genders and nationalities. It is encouraging to see such high accuracy at all levels,” said Takeshi Yanagida, who led the study.
However, it admits that more work is needed before it reaches your next smartphone.
“In this work, we demanded that our subjects fast six hours before the test,” concludes Yanagida. “We have developed a good foundation. The next step will be to refine this technique so that it works independently of the diet. Fortunately, our current study showed that adding more sensors and collecting more data can overcome this hurdle.”
History source:
Materials provided by Kyushu University. Note: Content can be edited by style and length.