Precision Biometrics Based on PPG Measured From an IoT Device With OPDs, Real-Time Quality Check Through PSD, DC Drift, and Deep Learning

• Published in: IEEE internet of things journal Vol. 11; no. 23; pp. 38767 - 38777
• Main Authors: Ngo, Duc Thang, Tseng, Yen-Ju, Nguyen, Duc Huy, Chao, Paul C.-P.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.12.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Artificial neural networks; Band-pass filters; Bandpass filters; Biological system modeling; Biometric; Biometric identification; Biometrics; Blood vessels; Blood volume; Deep learning; deep learning (DL); Direct current; Machine learning; Measuring instruments; Noise measurement; noninvasive; Photodiodes; photoplethysmography (PPG); Power spectral density; Quality assessment; quality check (QC); Real time; Real-time systems; Signal quality; Spectral emittance; Time measurement
• DOI: 10.1109/JIOT.2024.3454691
• ISSN: 2327-4662

A high-accuracy biometric identification system based on photoplethysmography (PPG) is proposed in this study. Equipped with continuous quality assessment on PPG in real-time by calculated power spectral density (PSD) and large-area organic photodetectors (OPDs) in the PPG sensor offering low-noise PPG, the deep learning model built herein is able to acquire delicate PPG features varying clearly from subject to subject, and then achieves high accuracy for biometric applications. It is known that PPG is a technology capable of measuring blood volume changes by emitting optical power into skin, reaching blood vessels and collects the reflected optical power back and out of skin, suitable for ensuring live body biometrics while many other biometrics are unable to. The raw PPG measured by the PPG device is first preprocessed by a bandpass filter, and then those with low PSD of PPG versus noise or large direct current drifts are screened out in real time to ensure the signal quality of PPG prior to biometrics. This preprocessing step is crucial to disregard all the unqualified PPG that may lead to wrongful result of biometrics later. The biometrics is next conducted by a built deep-learning (DL) model of a convolutional neural network (CNN) and long short-term memory (LSTM) layers. The DL model is trained by the PPG data collected from 42 subjects. Experimental results show an accuracy of 99.64% for binary while 98.8% for multiclass classification, outperforming other related works using PPG.