Today we are more than used to our mobiles recognizing us by fingerprint or by our face. Now, a group of researchers has taken biometric authentication a step further and has developed a sensor, which, when used together with artificial intelligence, is capable of authenticating up to 20 people with an average accuracy of over 97% .
In the age of information and technology in which we find ourselves, biometric authentication is a fundamental measure to safeguard valuable assets . Breath detection is now added to the wide variety of biometric data that machines can already use to identify us.
“These techniques are based on the physical uniqueness of each individual, but they are not foolproof . Physical characteristics can be copied, or even compromised by injury,” explains Chaiyanut Jirayupat, first author of the study published in Chemical Communications . “Recently, human scent has emerged as a new class of biometric authentication, essentially using your unique chemical composition to confirm who you are”.
Percutaneous gas is made up of compounds produced by the skin. The idea is that the machines detect them. However, the skin does not produce enough of the compounds for the machines to identify them. For this reason, the team considered using breath. “The concentration of volatile compounds in the skin can be as low as several parts per billion or trillion, while compounds exhaled through the breath can be as high as parts per million,” Jirayupat continues. “In fact, human breath has already been used to identify whether a person has cancer, diabetes, and even COVID-19.”
First, the scientists located compounds that could be used for biometric authentication. To do this, they analyzed the breath of the participants and found 28 compounds as viable options. They then developed a series of 16-channel olfactory sensors , each of which identified a specific range of compounds. The sensor data was fed into an AI to analyze the composition of each person’s breath and develop a specific profile for each person.
The system was tested on breath samples from six people. The result was a success and it identified the individuals with an average accuracy of 97.8%. When the sample was expanded to 20 people, the level of precision was maintained. “This was a diverse group of individuals of different ages, genders and nationalities. It is encouraging to see such high precision in all cases,” explains Takeshi Yanagida, who led the study.
However, the researcher acknowledges that we must continue working on the technology before it reaches our smartphones.
“In this work, we required our subjects to fast for six hours before testing,” Yanagida concludes. “We have developed a good foundation. The next step will be to refine this technique so that it works independently of diet. Fortunately, our current study has shown that adding more sensors and collecting more data can overcome this hurdle.”
Referencia: Jirayupat, C. et al. 2022. Breath odor-based individual authentication by an artificial olfactory sensor system and machine learning. Chemical Communications. DOI: https://doi.org/10.1039/d1cc06384g
