Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2013 Aug 20;8(8):e71523.
doi: 10.1371/journal.pone.0071523. eCollection 2013.

Normalizing Electrocardiograms of Both Healthy Persons and Cardiovascular Disease Patients for Biometric Authentication

Affiliations
Free PMC article

Normalizing Electrocardiograms of Both Healthy Persons and Cardiovascular Disease Patients for Biometric Authentication

Meixue Yang et al. PLoS One. .
Free PMC article

Abstract

Although electrocardiogram (ECG) fluctuates over time and physical activity, some of its intrinsic measurements serve well as biometric features. Considering its constant availability and difficulty in being faked, the ECG signal is becoming a promising factor for biometric authentication. The majority of the currently available algorithms only work well on healthy participants. A novel normalization and interpolation algorithm is proposed to convert an ECG signal into multiple template cycles, which are comparable between any two ECGs, no matter the sampling rates or health status. The overall accuracies reach 100% and 90.11% for healthy participants and cardiovascular disease (CVD) patients, respectively.

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Figure 1
Figure 1. The ECG curves of the samples s0306lre and sel100 m, respectively.
(a) The original curve and (b) the 10 representing training and testing ECG cycles of s0306lre from the PTB database. And the same datasets (c) and (d) for sel100 m from the QT database. For (a) and (c), the horizontal axis is in seconds, and the vertical axis is in mV.
Figure 2
Figure 2. The heatmaps of TEC matching of 52 healthy persons.
(a) The original heatmap and (b) the binary heatmap.
Figure 3
Figure 3. The heatmaps of TEC matching of 91 CVD patients.
(a) The original heatmap and (b) the binary heatmap.
Figure 4
Figure 4. The heatmaps of TEC matching of 52+14 = 66 healthy persons and 91 CVD patients.
(a) The original heatmap and (b) the binary heatmap.
Figure 5
Figure 5. The ECG signal and processed ECG cycles of two samples.
(a)–(b) sel39 m, and (c)–(d) sele0136 m. The ECG cycles in the first 10 seconds of the two signals were plotted, to make a clearer curve of the two signals. For (a) and (c), the horizontal axis is in seconds, and the vertical axis is in mV.
Figure 6
Figure 6. The heatmaps of TEC matching of 52 healthy persons in PTB database.
(a) The original heatmap with 5 s and (b) binary heatmap with 5 s. (c) The original heatmap with 10 s and (d) binary heatmap with 10 s. (e) The original heatmap with 20 s and (f) binary heatmap with 20 s.

Similar articles

See all similar articles

Cited by 2 articles

References

    1. Biel L, Pettersson O, Philipson L, Wide P (2001) ECG analysis: a new approach in human identification. Instrumentation and Measurement, IEEE Transactions on 50: 808–812.
    1. Di Crescenzo G, Graveman R, Ge R, Arce G (2005) Approximate Message Authentication and Biometric Entity Authentication Financial Cryptography and Data Security. In: Patrick A, Yung M, editors: Springer Berlin/Heidelberg. 578–578.
    1. Sandhu R, Samarati P (1996) Authentication, access control, and audit. ACM Comput Surv 28: 241–243.
    1. Dai H, Jiang S, Li Y (2013) Atrial activity extraction from single lead ECG recordings: evaluation of two novel methods. Comput Biol Med 43: 176–183. - PubMed
    1. He C, Fan X, Li Y (2013) Toward ubiquitous healthcare services with a novel efficient cloud platform. IEEE Trans Biomed Eng 60: 230–234. - PubMed

Publication types

Grant support

It was supported in part by the Shenzhen Research Grant ZDSY20120617113021359, China 973 program (2011CB512003 and 2010CB732606–6) and NSFC 31000447. Computing resources were partly provided by the Dawning supercomputing clusters at Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

LinkOut - more resources

Feedback