心臟因去極化及再極化而有收縮與舒張的現象，過程中所產生之電位訊號即為心電訊號（ECGs）。因個體心肌結構略有不同，所以每個個體間能產生不同的心電訊號，使得心電訊號可以作為生物辨識用之生物特徵。相較於其他生物特徵（如：指紋、臉孔），因心電訊號為體內產生之生理訊號，所以難以被竊取或盜用。本研究提出一個基於單導程心電訊號之生物辨識演算法，並將此演算法應用在身份識別模式中。我們提出的子空間過度取樣模板建置方法，能夠將心電訊號轉換為多樣化且不可逆之模板，以避免交叉比對的問題。透過子空間匹配的概念，我們不須提供任何隨機投影矩陣，即可進行心跳與模板之間的比對。最後，我們也提出了一個未註冊者的排除機制，以避免未註冊於資料庫中的登入者錯誤地被連結至任一已註冊者，此舉能夠大幅的增強系統的安全性。針對本研究提出之生物辨識演算法，我們將用300人的心電訊號資料庫驗證其辨識效能及安全性。

Electrocardiograms (ECGs) describe the electrical activity of the heart by electrodes placed on the skin. These electrodes detect small electrical changes which are caused by cardiac cells depolarization and depolarization during each cardiac cycle. Because muscular structures in myocardia between individuals are different, individuals can generate dissimilar ECGs, that makes ECGs a biometric modality for identity recognition. Compared with other extrinsic biometrics (such as fingerprints and faces), ECGs are difficult to steal or counterfeit. In this research, an identity recognition scheme based on single-lead ECG is proposed and applied on identification mode. To avoid the problem of cross-matching and privacy invasion, we propose a template construction to convert ECGs into diversified and irreversible templates through the concept of “subspace oversampling.” By the method of “subspace matching,” we can determine the identity of unknown subjects only with his/her beat bundles and templates in the database. Therefore, the information of template construction is not needed during identification. An exclusion of unregistered subjects is also implemented to prevent registered identity from being incorrectly linked by unregistered subjects, which can greatly enhance system security. Finally, an ECG database of 300 subjects is used to verify the identification performance and the security of the proposed scheme.

[1] A. Rattani, W. J. Scheirer, and A. Ross, "Open Set Fingerprint Spoof Detection Across Novel Fabrication Materials," IEEE T. Inf. Foren. Sec., vol. 10, pp. 2447-2460, 2015.
[2] D. Wen, H. Han, and A. K. Jain, "Face Spoof Detection With Image Distortion Analysis," IEEE T. Inf. Foren. Sec., vol. 10, pp. 746-761, 2015.
[3] A. K. Jain, A. Ross, and S. Prabhakar, "An introduction to biometric recognition," IEEE T. Circ. Syst. Vid., vol. 14, pp. 4-20, 2004.
[4] B. Schijvenaars, Intra-individual Variability of the Electrocardiogram: Assessment and exploitation in computerized ECG analysis. Erasmus University Rotterdam, 2000.
[5] K. N. Plataniotis, D. Hatzinakos, and J. K. M. Lee, "ECG Biometric Recognition Without Fiducial Detection," in Proc. Biometric Symp. (BSYM), 2006, pp. 1-6.
[6] F. Agrafioti, F. M. Bui, and D. Hatzinakos, "Secure Telemedicine: Biometrics for Remote and Continuous Patient Verification," J. Comput. Netw. Commun., vol. 2012, p. 11, 2012, Art. no. 924791.
[7] L. Biel, O. Pettersson, L. Philipson, and P. Wide, "ECG analysis: a new approach in human identification," IEEE T. Instrum. Meas., vol. 50, pp. 808-812, 2001.
[8] J. M. Irvine, S. A. Israel, W. Todd Scruggs, and W. J. Worek, "eigenPulse: Robust human identification from cardiovascular function," Pattern Recogn., vol. 41, pp. 3427-3435, 2008.
[9] S.-C. Fang and H.-L. Chan, "Human identification by quantifying similarity and dissimilarity in electrocardiogram phase space," Pattern Recogn., vol. 42, pp. 1824-1831, 2009.
[10] 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, pp. 937-940, 2013.
[11] J. R. Pinto, J. S. Cardoso, and A. Lourenço, "Evolution, Current Challenges, and Future Possibilities in ECG Biometrics," IEEE Access, vol. 6, pp. 34746-34776, 2018.
[12] Information technology — Vocabulary — Part 37: Biometrics, ISO Standard No. 2382-37:2017, 2017.
[13] L. Sörnmo and P. Laguna, Bioelectrical Signal Processing in Cardiac and Neurological Applications. Burlington: Academic Press, 2005.
[14] Y. Wang, F. Agrafioti, D. Hatzinakos, and K. N. Plataniotis, "Analysis of Human Electrocardiogram for Biometric Recognition," EURASIP J. Adv. Sig. Pr., vol. 2008, p. 148658, 2007.
[15] S. A. Israel, J. M. Irvine, A. Cheng, M. D. Wiederhold, and B. K. Wiederhold, "ECG to identify individuals," Pattern Recogn., vol. 38, pp. 133-142, 2005.
[16] O. Boumbarov, Y. Velchev, and S. Sokolov, "ECG personal identification in subspaces using radial basis neural networks," in Int. Worksh. Int. Data, 2009, pp. 446-451.
[17] M. N. Dar, M. U. Akram, A. Usman, and S. A. Khan, "ECG biometric identification for general population using multiresolution analysis of DWT based features," in Proc. 2nd Int. Conf. Inf. Secur. Cyber Forensics (InfoSec), 2015, pp. 5-10.
[18] A. D. C. Chan, M. M. Hamdy, A. Badre, and V. Badee, "Wavelet Distance Measure for Person Identification Using Electrocardiograms," IEEE T. Instrum. Meas., vol. 57, pp. 248-253, 2008.
[19] R. Matta, J. K. H. Lau, F. Agrafioti, and D. Hatzinakos, "Real-time continuous identification system using ECG signals," in Proc. 24th Can. Conf. Elect. Comput. Eng. (CCECE), 2011, pp. 001313-001316.
[20] M. Hejazi, S. A. R. Al-Haddad, S. J. Hashim, A. F. A. Aziz, and Y. P. Singh, "Feature level fusion for biometric verification with two-lead ECG signals," in Proc. IEEE CSPA, 2016, pp. 54-59.
[21] S.-C. Wu, P.-T. Chen, and J.-H. Hsieh, "Spatiotemporal features of electrocardiogram for biometric recognition," Multidim. Syst. Sign. P., vol. 30, pp. 989-1007, 2019.
[22] V. M. Patel, N. K. Ratha, and R. Chellappa, "Cancelable Biometrics: A review," IEEE Signal Proc. Mag., vol. 32, pp. 54-65, 2015.
[23] J. K. Pillai, V. M. Patel, R. Chellappa, and N. K. Ratha, "Sectored Random Projections for Cancelable Iris Biometrics," in IEEE Int. Conf. Acoust. Spee., 2010, pp. 1838-1841.
[24] A. B. J. Teoh, Y. W. Kuan, and S. Lee, "Cancellable biometrics and annotations on BioHash," Pattern Recogn., vol. 41, pp. 2034-2044, 2008.
[25] W. B. Johnson and J. Lindenstrauss, "Extensions of Lipschitz mappings into a Hilbert space," Contemp. Math., vol. 26, pp. 189-206, 1984.
[26] A. Kong, K.-H. Cheung, D. Zhang, M. Kamel, and J. You, "An analysis of BioHashing and its variants," Pattern Recogn., vol. 39, pp. 1359-1368, 2006.
[27] S.-C. Wu, P.-T. Chen, A. L. Swindlehurst, and P.-L. Hung, "Cancelable Biometric Recognition With ECGs: Subspace-Based Approaches," IEEE T. Inf. Foren. Sec., vol. 14, pp. 1323-1336, 2019.
[28] J. Pan and W. J. Tompkins, "A Real-Time QRS Detection Algorithm," IEEE T. Bio-Med. Eng., vol. BME-32, pp. 230-236, 1985.
[29] L. Goldberger Ary et al., "PhysioBank, PhysioToolkit, and PhysioNet," Circulation, vol. 101, pp. e215-e220, 2000.
[30] R. Bousseljot, D. Kreiseler, and A. Schnabel, "Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet," Biomed. Tech., vol. 40, p. 317, 1995.
[31] T. J. M. s. t. Lugovaya, Faculty of Computing Technologies and E. U. L. Informatics, Saint-Petersburg, Russian Federation, "Biometric human identification based on electrocardiogram," 2005.
[32] P. d. 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 T. Bio-Med. Eng., vol. 50, pp. 686-696, 2003.
[33] C. Levkov, G. Mihov, R. Ivanov, I. Daskalov, I. Christov, and I. Dotsinsky, "Removal of power-line interference from the ECG: a review of the subtraction procedure," Biomed. Eng. Online, vol. 4, p. 50, 2005.
[34] G. D. Clifford, F. Azuaje, and P. McSharry, Advanced methods and tools for ECG data analysis. Artech house Boston, 2006.
[35] M. Gomez-Barrero, C. Rathgeb, J. Galbally, C. Busch, and J. Fierrez, "Unlinkable and irreversible biometric template protection based on bloom filters," Inform. Sciences, vol. 370-371, pp. 18-32, 2016.
[36] Information technology -- Security techniques -- Biometric information protection, ISO Standard No. 24745:2011, 2011.
[37] P. E. McSharry, G. D. Clifford, L. Tarassenko, and L. A. Smith, "A dynamical model for generating synthetic electrocardiogram signals," IEEE T. Bio-Med. Eng., vol. 50, pp. 289-294, 2003.