PBGAN: Learning PPG Representations from GAN for Time-Stable and Unique Verification System

被引：11
作者：
Hwang D.Y. [1 ]
Taha B. [1 ,2 ]
Hatzinakos D. [1 ]
机构：
[1] Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto
[2] Vector Institute for AI, Toronto, M5G 1M1, ON
来源：
IEEE Transactions on Information Forensics and Security | 2021年 / 16卷
基金：
加拿大自然科学与工程研究理事会;
关键词：
Biometrics; CNN; GAN; PPG; security; verification;
D O I：
10.1109/TIFS.2021.3122817
中图分类号：
学科分类号：
摘要：
Photoplethysmography (PPG) is a non-invasive physiological signal that captures the changes in blood volume resulted from heart activity. It carries unique person-specific characteristics that can be utilized for biometric systems. Currently, the use of a biometric system is paramount to ensure the security of the user's identity. Due to the high sensitivity of the PPG signal, it suffers from extreme variations within the same subject when obtained at different time instances. These variations impose a challenge to employ the PPG signal and hinder the algorithm generalization for many applications including verification and identification systems. In this work, we propose a PPG Biometric Generative Adversarial Network (PBGAN) to create synthetic person-specific and time-stable PPG signals for genuine samples. Two types of classification models are employed with the PBGAN where the focus is on verification scenarios. In addition, we expand our previously recorded PPG dataset from 100 to 170 participants where the new size guarantees the generalization capability of the proposed system. This database and another three public ones are employed to evaluate the performances in terms of uniqueness and time stability. Furthermore, we consider three different training strategies to simulate practical scenarios. The best results acquired from our collected database in terms of Equal Error Rate (EER) is 1.3% for the single-session and 11.5% for the two-sessions scenarios which demonstrate the effectiveness of the proposed method in improving the verification system's performance. Compared to our previous work, we achieve 1.3% and 1.4% EER improvements in two-sessions' databases with small computational times which reveals the superiority of our proposed approach for real applications. Later, the code and dataset can be accessed in https://github.com/eoduself. © 2005-2012 IEEE.
引用
收藏
页码：5124 / 5137
页数：13
相关论文
共 44 条
  • [21] Dwivedi R., Dey S., Score-level fusion for cancelable multibiometric verification, Pattern Recognit. Lett., 126, pp. 58-67, (2019)
  • [22] Hammada M., Wang K., Parallel score fusion of ECG and fingerprint for human authentication based on convolution neural network, Comput. Secur., 81, pp. 107-122, (2019)
  • [23] Zhu F., Ye F., Fu Y., Liu Q., Shen B., Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network, Sci. Rep., 9, 1, pp. 1-11, (2019)
  • [24] Golany T., Radinsky K., PGANS: Personalized generative adversarial networks for ECG synthesis to improve patient-specific deep ECG classification, Proc. Aaai Conf. Artif. Intell., 33, pp. 557-564, (2019)
  • [25] Brophy E., Wang Z., Ward T.E., Quick and Easy Time Series Generation with Established Image-based GANs, (2019)
  • [26] Hartmann K.G., Schirrmeister R.T., Ball T., EEG-GAN: Generative Adversarial Networks for Electroencephalograhic (EEG) Brain Signals, (2018)
  • [27] Kiyasseh D., Et al., PlethAugment: GAN-based PPG augmentation for medical diagnosis in low-resource settings, IEEE J. Biomed. Health Informat., 24, 11, pp. 3226-3235, (2020)
  • [28] Tang Q., Chen Z., Ward R., Elgendi M., Synthetic photoplethysmogram generation using two Gaussian functions, Sci. Rep., 10, 1, pp. 1-10, (2020)
  • [29] Karlen W., Raman S., Ansermino J.M., Dumont G.A., Multiparameter respiratory rate estimation from the photoplethysmogram, IEEE Trans. Biomed. Eng., 60, 7, pp. 1946-1953, (2013)
  • [30] Zhang Z., Pi Z., Liu B., TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise, IEEE Trans. Biomed. Eng., 62, 2, pp. 522-531, (2015)
12345