Biometric Recognition of PPG Cardiac Signals Using Transformed Spectrogram Images

Abstract

Nowadays, the number of mobile, wearable, and embedded devices integrating sensors for acquiring cardiac signals is constantly increasing. In particular, plethysmographic (PPG) sensors are widely diffused thanks to their small form factor and limited cost. For example, PPG sensors are used for monitoring cardiac activities in automotive applications and in wearable devices as smartwatches, activity trackers, and wristbands. Recent studies focused on using PPG signals to secure mobile devices by performing biometric recognitions. Although their results are promising, all of these methods process PPG acquisitions as one-dimensional signals. In the literature, feature extraction techniques based on transformations of the spectrogram have been successfully used to increase the accuracy of signal processing techniques designed for other application scenarios. This paper presents a preliminary study on a biometric recognition approach that extracts features from different transformations of the spectrogram of PPG signals and classifies the obtained feature representations using machine learning techniques. To the best of our knowledge, this is the first study in the literature on biometric systems that extracts features from the spectrogram of PPG signals. Furthermore, with respect to most of the state-of-the-art biometric recognition techniques, the proposed approach presents the advantage of not requiring the search of fiducial points, thus reducing the computational complexity and increasing the robustness of the signal preprocessing step. We performed tests using a dataset of samples collected from 42 individuals, obtaining an average classification accuracy of 99.16% for identity verification (FMR of 0.56% at FNMR of 13.50%), and a rank-1 identification error of 7.24% for identification. The results obtained for the considered dataset are better or comparable with respect to the ones of the best-performing methods in the literature.

A learning-based image processing approach for pulse wave velocity estimation using spectrogram from peripheral pulse wave signals: An in silico study

“…This study investigated a novel methodology to estimate the cf-PWV based on the application of the spectrogram representation of single PPG or BP signals extracted from a peripheral location. The use of the spectrogram representation for the analysis of biomedical signals such as PPG had been studied before as input for datadriven approaches like the classification of peripheral diseases by (Allen et al, 2021), or biometric recognition, (Donida Labati et al, 2021). For this reason, in this project, the use of the spectrogram from BP or PPG signals to estimate the cf-PWV values is investigated as a novel methodology to take advantage of the frequency and temporal information encoded in the spectrogram matrix.…”

“…The use of spectrogram representation on PPG signals has been studied in the past proving good performance over different applications. In 2020, (Donida Labati et al, 2021) used a SVM model with features extracted from the PPG spectrogram for biometric recognition. Another use of PPG spectrogram representation is presented by (Siam et al, 2021) where they use the spectrogram as an input image for Blood Pressure estimation using Siamese networks and Convolutional neural networks (CNN).…”

Pulse Oximetry Imaging System Using Spatially Uniform Dual Wavelength Illumination

“…The ratio of absorbances is calculated using the red (630 nm) and near-infrared (940 nm) time signals in the following equation: where AC is the pulsatile component, DC is the non-pulsatile component, and RR is the ratio of ratios of the absorbances at the two wavelengths. Previous studies [ 36 , 37 ] have shown that the pulsatile and non-pulsatile components correspond to the standard deviation and mean color intensities of the red and near-infrared frames, respectively. A nearly linear relationship exists between SpO 2 values and RR [ 38 ].…”

Video is All You Need: Attacking PPG-based Biometric Authentication

“…Temporal features of the PPG signals are sensitive to noises, including baseline wander, motion artifact, and respiration [23]. To improve the robustness against noise, frequency-based features are obtained by applying transform methods to the PPG signal like Fourier transform [10] and wavelet transform [44]. Recent state-of-the-art PPGbased biometric authentication uses deep learning to learn features automatically from the raw data [1,19].…”

“…There are various studies on PPG-based user authentication relying on temporal features [48], spectrum features [9], automated feature extraction through CNN-LSTM models [19], or many alike. Moreover, industry vendors are investigating new PPG-based biometric authentication.…”