隨著科技發展，許多個性化的服務帶給人們更便利的生活，然而在享受這便利的同時，保障個人資訊也成為重要的議題。但傳統的身分識別方法（如：鑰匙或密碼）卻不夠嚴謹，不但容易被盜用，更有遺失的可能，因此運用生物特徵為依據的生物辨識技術受到許多關注，而心電訊號是其中一具前景的生物特徵。心電訊號是一紀錄心臟活動的訊號，相較於外顯的生物特徵（如：指紋、臉孔）較難以竊取；此外，心電訊號是一個動態的訊號，僅在個體存活時能夠被測量。雖然心電訊號存在許多好處，但「動態」的特性增加心跳的變異率，也增加辨識的難度。本研究提出一種基於深度學習的心電識別系統，並解決現存系統中的兩個問題。首先，卷積神經網路能透過存在系統內的特徵向量與遷移學習微調系統，使我們不須召回已註冊者就能讓新使用者能註冊於系統。其次，識別系統將未知對象的特徵向量與數據庫中保存的特徵向量進行比較，使用Parzen Window估計概率，並通過均值和標準差來區分未註冊的對象。最後，以PTB資料庫中的255受測者驗證資料庫的識別效能與安全性，在開放式的識別下達到IR為97.5%且FPIR為2.5%。

As technology advances, many personalized services provide a comfortable and humane service. While enjoying the convenience of technology, protecting personal information has also become an important issue. However, traditional identification methods (e.g., keys or passwords) are not strict enough, and not only are they easy to be stolen, but it may also be lost. Therefore, an identification system based on biometrics has attracted considerable attention and using electrocardiograms (ECGs) as biometric is a promising option. ECGs are recordings of the heart's electrical activity and are hard to be stolen compared to extrinsic biometrics (e.g., fingerprints, faces, etc.). Besides, the ECG signal is a dynamic signal that can only be measured while the individual is alive. In this study, we propose a DL-based ECG identification scheme and address two problems of the current biometric system. First, with the help of “transfer learning,” new subjects can enroll our system by retraining the model with feature vectors. Second, the identification scheme will compare the feature vector of an unknown subject that will be compared with those saved in the database to estimate the probability with Parzen window, and discriminate an unregistered subject with mean and standard deviation. Finally, we verify the proposed open-set identification system with the PTB database of 255 subjects, and it achieves an IR of 97.5% and an FPIR of 2.5%.

[1] V. M. Mane and D. V. Jadhav, "Review of multimodal biometrics: applications, challenges and research areas," International Journal of Biometrics and Bioinformatics (IJBB), vol. 3, no. 5, pp. 90-95, 2009.
[2] M. O. Onyesolu and I. M. Ezeani, "ATM security using fingerprint biometric identifer: An investigative study," International Journal of Advanced Computer science and applications, vol. 3, no. 4, pp. 68-72, 2012.
[3] A. Rattani, W. J. Scheirer, and A. Ross, "Open Set Fingerprint Spoof Detection Across Novel Fabrication Materials," IEEE T. Inf. Foren. Sec., vol. 10, no. 11, pp. 2447-2460, 2015, doi: 10.1109/TIFS.2015.2464772.
[4] D. Wen, H. Han, and A. K. Jain, "Face Spoof Detection With Image Distortion Analysis," IEEE T. Inf. Foren. Sec., vol. 10, no. 4, pp. 746-761, 2015, doi: 10.1109/TIFS.2015.2400395.
[5] L. Biel, O. Pettersson, L. Philipson, and P. Wide, "ECG analysis: a new approach in human identification," IEEE Transactions on Instrumentation and Measurement, vol. 50, no. 3, pp. 808-812, 2001.
[6] J. M. Irvine, S. A. Israel, W. Todd Scruggs, and W. J. Worek, "eigenPulse: Robust human identification from cardiovascular function," Pattern Recogn., vol. 41, no. 11, pp. 3427-3435, 2008/11/01/ 2008, doi: https://doi.org/10.1016/j.patcog.2008.04.015.
[7] S.-C. Fang and H.-L. Chan, "Human identification by quantifying similarity and dissimilarity in electrocardiogram phase space," Pattern Recogn., vol. 42, no. 9, pp. 1824-1831, 2009/09/01/ 2009, doi: https://doi.org/10.1016/j.patcog.2008.11.020.
[8] J. Wang, M. She, S. Nahavandi, and A. Kouzani, "Human Identification From ECG Signals Via Sparse Representation of Local Segments," IEEE Signal Proc. Let., vol. 20, no. 10, pp. 937-940, 2013, doi: 10.1109/LSP.2013.2267593.
[9] A. K. Jain, A. Ross, and S. Prabhakar, "An introduction to biometric recognition," IEEE Transactions on circuits and systems for video technology, vol. 14, no. 1, pp. 4-20, 2004.
[10] A. Gacek and W. Pedrycz, ECG signal processing, classification and interpretation: a comprehensive framework of computational intelligence. Springer Science & Business Media, 2011.
[11] "The MAX86150 Evaluation System," Maxim Integrated, 2020.
[12] I. Odinaka, P.-H. Lai, A. D. Kaplan, J. A. O'Sullivan, E. J. Sirevaag, and J. W. Rohrbaugh, "ECG biometric recognition: A comparative analysis," IEEE Transactions on Information Forensics and Security, vol. 7, no. 6, pp. 1812-1824, 2012.
[13] S. A. Israel, J. M. Irvine, A. Cheng, M. D. Wiederhold, and B. K. Wiederhold, "ECG to identify individuals," Pattern recognition, vol. 38, no. 1, pp. 133-142, 2005.
[14] J. M. Irvine, S. A. Israel, W. T. Scruggs, and W. J. Worek, "eigenPulse: Robust human identification from cardiovascular function," Pattern Recognition, vol. 41, no. 11, pp. 3427-3435, 2008.
[15] A. D. Chan, M. M. Hamdy, A. Badre, and V. Badee, "Wavelet distance measure for person identification using electrocardiograms," IEEE transactions on instrumentation and measurement, vol. 57, no. 2, pp. 248-253, 2008.
[16] Y. Wang, F. Agrafioti, D. Hatzinakos, and K. N. Plataniotis, "Analysis of human electrocardiogram for biometric recognition," EURASIP journal on Advances in Signal Processing, vol. 2008, no. 1, p. 148658, 2007.
[17] V. M. Patel, N. K. Ratha, and R. Chellappa, "Cancelable biometrics: A review," IEEE Signal Processing Magazine, vol. 32, no. 5, pp. 54-65, 2015.
[18] S. Prabhakar, S. Pankanti, and A. K. Jain, "Biometric recognition: Security and privacy concerns," IEEE security & privacy, vol. 1, no. 2, pp. 33-42, 2003.
[19] A. Nagar, K. Nandakumar, and A. K. Jain, "Biometric template transformation: a security analysis," in Media Forensics and Security II, 2010, vol. 7541: International Society for Optics and Photonics, p. 75410O.
[20] X. Zhou and T. Kalker, "On the security of biohashing," in Media Forensics and Security II, 2010, vol. 7541: International Society for Optics and Photonics, p. 75410Q.
[21] S.-C. Wu, P.-T. Chen, and J.-H. Hsieh, "Spatiotemporal features of electrocardiogram for biometric recognition," Multidimensional Systems and Signal Processing, vol. 30, no. 2, pp. 989-1007, 2019.
[22] P.-L. Hong, J.-Y. Hsiao, C.-H. Chung, Y.-M. Feng, and S.-C. Wu, "ECG biometric recognition: template-free approaches based on deep learning," in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2019: IEEE, pp. 2633-2636.
[23] W. J. Scheirer, A. de Rezende Rocha, A. Sapkota, and T. E. Boult, "Toward open set recognition," IEEE transactions on pattern analysis and machine intelligence, vol. 35, no. 7, pp. 1757-1772, 2012.
[24] R. M. Nor, A. W. B. A. Rahman, K. A. Sidek, and A. A. Ibrahim, "Electrocardiogram identification: Use a simple set of features in QRS complex to identify individuals," in Recent Advances in Information and Communication Technology 2016: Springer, 2016, pp. 139-148.
[25] Z. Zhao, L. Yang, D. Chen, and Y. Luo, "A human ECG identification system based on ensemble empirical mode decomposition," Sensors, vol. 13, no. 5, pp. 6832-6864, 2013.
[26] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," nature, vol. 521, no. 7553, pp. 436-444, 2015.
[27] B. Xu, N. Wang, T. Chen, and M. Li, "Empirical evaluation of rectified activations in convolutional network," arXiv preprint arXiv:1505.00853, 2015.
[28] R. D. Labati, E. Muñoz, V. Piuri, R. Sassi, and F. Scotti, "Deep-ECG: convolutional neural networks for ECG biometric recognition," Pattern Recognition Letters, vol. 126, pp. 78-85, 2019.
[29] J. S. Kim, S. H. Kim, and S. B. Pan, "Personal recognition using convolutional neural network with ECG coupling image," Journal of Ambient Intelligence and Humanized Computing, pp. 1-10, 2019.
[30] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[31] G. D. Clifford, F. Azuaje, and P. McSharry, Advanced methods and tools for ECG data analysis. Artech house Boston, 2006.
[32] P. De Chazal, C. Heneghan, E. Sheridan, R. Reilly, P. Nolan, and M. O'Malley, "Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea," IEEE Transactions on Biomedical Engineering, vol. 50, no. 6, pp. 686-696, 2003.
[33] L. Sörnmo and P. Laguna, Bioelectrical signal processing in cardiac and neurological applications. Academic Press, 2005.
[34] S.-C. Wu, P.-T. Chen, A. L. Swindlehurst, and P.-L. Hung, "Cancelable biometric recognition with ECGs: subspace-based approaches," IEEE Transactions on Information Forensics and Security, vol. 14, no. 5, pp. 1323-1336, 2018.
[35] J. Pan and W. J. Tompkins, "A real-time QRS detection algorithm," IEEE transactions on biomedical engineering, no. 3, pp. 230-236, 1985.
[36] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in neural information processing systems, 2012, pp. 1097-1105.
[37] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov, "Improving neural networks by preventing co-adaptation of feature detectors," arXiv preprint arXiv:1207.0580, 2012.
[38] S. J. Pan and Q. Yang, "A survey on transfer learning," IEEE Transactions on knowledge and data engineering, vol. 22, no. 10, pp. 1345-1359, 2009.
[39] C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, "A survey on deep transfer learning," in International conference on artificial neural networks, 2018: Springer, pp. 270-279.
[40] P. E. McSharry, G. D. Clifford, L. Tarassenko, and L. A. Smith, "A dynamical model for generating synthetic electrocardiogram signals," IEEE transactions on biomedical engineering, vol. 50, no. 3, pp. 289-294, 2003.
[41] S. Theodoridis and K. Koutroumbas, "Pattern recognition and neural networks," in Advanced Course on Artificial Intelligence, 1999: Springer, pp. 169-195.
[42] B. W. Silverman, Density estimation for statistics and data analysis. CRC press, 1986.
[43] L. Goldberger Ary et al., "PhysioBank, PhysioToolkit, and PhysioNet," Circulation, vol. 101, no. 23, pp. e215-e220, 2000/06/13 2000, doi: 10.1161/01.CIR.101.23.e215.
[44] R. Bousseljot, D. Kreiseler, and A. Schnabel, "Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet," Biomed. Tech., vol. 40, no. s1, p. 317, 1995, doi: 10.1515/bmte.1995.40.s1.317.
[45] A. K. Jain, P. Flynn, and A. A. Ross, Handbook of biometrics. Springer Science & Business Media, 2007.
[46] B. DeCann and A. Ross, "Relating roc and cmc curves via the biometric menagerie," in 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), 2013: IEEE, pp. 1-8.
[47] Information technology -- Security techniques -- Biometric information protection, I. S. N. 24745:2011, 2011.