Similar articles

Abstract: Physiological signal based biometric analysis has recently attracted attention as a means of meeting increasing privacy and security requirements. The real-time nature of an electrocardiogram (ECG) and the hidden nature of the information make it highly resistant to attacks. This paper focuses on three major bottlenecks of existing deep learning driven approaches: the lengthy time requirements for optimizing the hyperparameters, the slow and computationally intense identification process, and the unstable and complicated nature of ECG acquisition. We present a novel deep neural network framework for learning human identification feature representations directly from ECG time series. The proposed framework integrates deep bidirectional long short-term memory (BLSTM) and adaptive particle swarm optimization (APSO). The overall approach not only avoids the inefficient and experience-dependent search for hyperparameters, but also fully exploits the spatial information of ordinal local features and the memory characteristics of a recognition algorithm. The effectiveness of the proposed approach is thoroughly evaluated in two ECG datasets, using two protocols, simulating the influence of electrode placement and acquisition sessions in identification. Comparing four recurrent neural network structures and four classical machine learning and deep learning algorithms, we prove the superiority of the proposed algorithm in minimizing overfitting and self-learning of time series. The experimental results demonstrated an average identification rate of 97.71%, 99.41%, and 98.89% in training, validation, and test sets, respectively. Thus, this study proves that the application of APSO and LSTM techniques to biometric human identification can achieve a lower algorithm engineering effort and higher capacity for generalization.

ECGID：一种基于自适应粒子群优化算法和双向LSTM网络的个体身份识别模型

[1]Agrafioti F, Hatzinakos D, 2008. ECG based recognition using second order statistics. Proc 6^th Annual Communication Networks and Services Research Conf, p.82-87.

[2]Ahmadi A, Mitchell E, Richter C, et al., 2015. Toward automatic activity classification and movement assessment during a sports training session. IEEE Int Things J, 2(1):23-32.

[3]Bassiouni MM, El-Dahshan ESA, Khalefa W, et al., 2018. Intelligent hybrid approaches for human ECG signals identification. Signal Image Video Process, 12(5):941-949.

[4]Biel L, Pettersson O, Philipson L, et al., 2001. ECG analysis: a new approach in human identification. IEEE Trans Instrum Meas, 50(3):808-812.

[5]Choi GH, Bak ES, Pan SB, 2019. User identification system using 2D resized spectrogram features of ECG. IEEE Access, 7:34862-34873.

[6]Chu YF, Shen HB, Huang KJ, 2019. ECG authentication method based on parallel multi-scale one-dimensional residual network with center and margin loss. IEEE Access, 7:51598-51607.

[7]da Silva Luz EJ, Moreira GJP, Oliveira LS, et al., 2018. Learning deep off-the-person heart biometrics representations. IEEE Trans Inform Forens Secur, 13(5):1258-1270.

[8]Hochreiter S, Schmidhuber J, 1997. Long short-term memory. Neur Comput, 9(8):1735-1780.

[9]Labati RD, Muñoz E, Piuri V, et al., 2019. Deep-ECG: convolutional neural networks for ECG biometric recognition. Patt Recogn Lett, 126:78-85.

[10]Liu JK, Yin LY, He CG, et al., 2018. A multiscale autoregressive model-based electrocardiogram identification method. IEEE Access, 6:18251-18263.

[11]Nuno B, Belo D, Gamboa H, 2020. ECG biometrics using spectrograms and deep neural networks. Int J Mach Learn Comput, 10(2):259-264.

[12]Oh SL, Ng EYK, Tan RS, et al., 2018. Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats. Comput Biol Med, 102:278-287.

[13]Palaniappan R, Krishnan SM, 2004. Identifying individuals using ECG beats. Proc Int Conf on Signal Processing and Communications, p.569-572.

[14]Pan JP, Tompkins WJ, 1985. A real-time QRS detection algorithm. IEEE Trans Biomed Eng, 32(3):230-236.

[15]Rodriguez A, Laio A, 2014. Clustering by fast search and find of density peaks. Science, 344(6191):1492-1496.

[16]Salloum R, Kuo CCJ, 2017. ECG-based biometrics using recurrent neural networks. Proc IEEE Int Conf on Acoustics, Speech and Signal Processing, p.2062-2066.

[17]Srivastava N, Hinton G, Krizhevsky A, et al., 2014. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res, 15(1):1929-1958.

[18]Tantawi MM, Revett K, Salem AB, et al., 2015. A wavelet feature extraction method for electrocardiogram (ECG)-based biometric recognition. Signal Image Video Process, 9(6):1271-1280.

[19]Wu B, Yang GP, Yang L, et al., 2018. Robust ECG biometrics using two-stage model. Proc 24^th Int Conf on Pattern Recognition, p.1062-1067.

[20]Yildirim Ö, 2018. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Comput Biol Med, 96:189-202.

[21]Yu JR, Si YJ, Liu X, 2017. ECG identification based on PCA-RPROP. Proc 8^th Int Conf on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management, p.419-432.

[22]Zhang QX, Zhou D, Zeng X, 2017. HeartID: a multiresolution convolutional neural network for ECG-based biometric human identification in smart health applications. IEEE Access, 5:11805-11816.

[23]Zhao ZD, Zhang YF, Deng YJ, et al., 2018. ECG authentication system design incorporating a convolutional neural network and generalized S-transformation. Comput Biol Med, 102:168-179.