User authentication system based on human exhaled breath physics

TL;DR

This work test the hypothesis that the structure of turbulence in exhaled human breath can be exploited to build biometric algorithms and shows surprisingly unique turbulent signatures in the exhaled breath that have not been discovered before.

Abstract

This work, in a pioneering approach, attempts to build a biometric system that works purely based on the fluid mechanics governing exhaled breath. We test the hypothesis that the structure of turbulence in exhaled human breath can be exploited to build biometric algorithms. This work relies on the idea that the extrathoracic airway is unique for every individual, making the exhaled breath a biomarker. Methods including classical multi-dimensional hypothesis testing approach and machine learning models are employed in building user authentication algorithms, namely user confirmation and user identification. A user confirmation algorithm tries to verify whether a user is the person they claim to be. A user identification algorithm tries to identify a user's identity with no prior information available. A dataset of exhaled breath time series samples from 94 human subjects was used to evaluate the performance of these algorithms. The user confirmation algorithms performed exceedingly well for the given dataset with over $97\%$ true confirmation rate. The machine learning based algorithm achieved a good true confirmation rate, reiterating our understanding of why machine learning based algorithms typically outperform classical hypothesis test based algorithms. The user identification algorithm performs reasonably well with the provided dataset with over $50\%$ of the users identified as being within two possible suspects. We show surprisingly unique turbulent signatures in the exhaled breath that have not been discovered before. In addition to discussions on a novel biometric system, we make arguments to utilise this idea as a tool to gain insights into the morphometric variation of extrathoracic airway across individuals. Such tools are expected to have future potential in the area of personalised medicines.

Figures (15)

• Figure 1: Calibration curve for the hot wire anemometer. A fourth order least square fit of the experimental data (shown as maroon dotted line) becomes the calibration curve for the hot wire anemometer in use. The polynomial equation of the fourth order fit is shown inside the plot.
• Figure 2: Experimental setup and recorded time series. (A) Depiction of the experimental setup for data collection. It consists of a disposable mouth-piece, a mouth-piece mount housing a hot wire anemometer and a data acquisition system. (B) A typical human exhalation velocity signal measured using a standard hot wire anemometer. The time signals were sampled at $10\mathrm{kHz}$ for $1.5~\mathrm{seconds}$.
• Figure 3: Comparison of multifractality of time signals. Plots showing the effect of random shuffling of exhaled breath time series acquired using a hot wire anemometer. Signals shown in (A) and (B) correspond to the actual breath data and the shuffled data respectively. Inset plots in (A) and (B) show a zoomed-in view of the first $1000$ data points of the signals. Note that the signal has been normalized using its mean and standard deviation. (C) Histogram showing the distribution of all $N$ data points of the breath signal. (D) Multifractal spectra for the original breath signal and the randomly shuffled white noise signal. Random shuffling causes loss of memory within the time series and losses the multifractality.
• Figure 4: Multifractal spectra for different segments of a time signal. The multifractral spectra corresponding to the entire time signal (maroon) and time segments X, Y and Z (black, bounded by gray band) in (A) are shown in (B). It is evident that few segments exhibit an inverted parabola shape and spectrum B has a distortion.
• Figure 5: The multifractal spectrum. Plot of the spectrum of singularities $f(\alpha)$ against the singularity strength $\alpha$, computed for an exhalation time series segment. The parameters $\beta$, $\omega$ and $\epsilon$ are the features that characterize a multifractal spectrum.