A new sensor uses respiration for biometric identification

0

The olfactory sensor developed for breath-based biometric authentication. Credit: Kyushu University

In today’s world, it is common to use your fingerprint, voice, and/or face as security credentials. Thanks to our smartphones, we have become so accustomed to using personal features as biometric authentication tools that most of us don’t think twice. But, as researcher Chaiyanut Jirayupat points out, these methods are not perfect.

“These techniques rely on the physical uniqueness of each individual, but they are not infallible,” said Jirayupat, a professor at Kyushu University (Japan) and first author of a recent study on biometric authentication methods. . “Physical characteristics can be copied or even compromised by injury.”

That’s why Jirayupat and his colleagues developed a new tool: an olfactory sensor for biometric authentication using human breath.

“Recently, human scent has emerged as a new class of biometric authentication, essentially using your unique chemical makeup to confirm who you are,” Jirayupat said.

This concept applied to biometrics and security may be new, but the general idea of ​​using breath as an analytical tool certainly is not. “Breathomics” – or the breath test for biomarkers – dates back to the 5e century BCE when Hippocrates linked “smelly” breath (aka acetone) to patients with diabetes. In the years since, researchers have used breath for everything from detecting the level of intoxication to diagnosing rare genetic diseases, monitoring vital signs of health, and even screening patients for COVID-19.

The Kyushu University team began their project by analyzing subjects’ breath to see which compounds might be viable for biometric authentication. They identified a total of 28 possible compounds, including benzophenone, decanal, octane, tetradecane and undecane, all of which have been shown in previous studies based on sweat odor to be specific markers for the individual.

Based on these results, the team developed an array of olfactory sensors with 16 channels, each of which can identify a specific range of compounds. The sensor data was then fed to a machine learning system to analyze the composition of each person’s breath and develop a profile to be used to distinguish an individual.

By testing the system with breath samples from six people, the researchers found that it could identify individuals with an average accuracy of 98%. This high level of precision remained constant even when the sample size was increased to 20 people.

Interestingly, scientists found that accuracy and reproducibility improved dramatically by increasing the number of sensors.

“The [study] the results indicate that more sensors are needed to discriminate complex odors,” the authors write in their study, published in Chemical communications. “In other words, further discrimination of breath odor would be possible by increasing the number of sensors used.”

Additionally, the tests were only performed on subjects after a six-hour fast. The researchers say it remains a challenge to demonstrate the system’s ability under interference from metabolites and compounds from food and drink.

“The barrier needs to be overcome by using more sensors and extracting more features from detection curves,” the authors conclude. “We believe that the results of this study provide an important basis for biometrics based on breath odor detection.”

Share.

Comments are closed.