귀 주변에서 측정한 유사 심전도 기반 개인 인증 시스템 개발 가능성 = Feasibility of Using Similar Electrocardiography Measured around the Ears to Develop a Personal Authentication System

다국어 초록 (Multilingual Abstract)

A personal authentication system based on biosignals has received increasing attention due to its relatively high security as compared to traditional authentication systems based on a key and password. Electrocardiography (ECG) measured from the chest or wrist is one of the widely used biosignals to develop a personal authentication system.
In this study, we investigated the feasibility of using similar ECG measured behind the ears to develop a personal authentication system. To this end, similar ECGs were measured from thirty subjects using a pair of three electrodes attached behind each of the ears during resting state during which the standard Lead-I ECG was also simultaneously measured from both wrists as baseline ECG. The three ECG components, Q, R, and S, were extracted for each subject as classification features, and authentication accuracy was estimated using support vector machine (SVM) based on a 5×5-fold cross-validation. The mean authentication accuracies of Lead I-ECG and similar ECG were 90.41 ± 8.26% and 81.15 ± 7.54%, respectively. Considering a chance level of 3.33% (=1/30), the mean authentication performance of similar ECG could demonstrate the feasibility of using similar ECG measured behind the ears on the development of a personal authentication system.

참고문헌 (Reference)

1 Chan AD, "Wavelet distance measure for person identification using electrocardiograms" 57 (57): 248-253, 2008

2 Wübbeler G, "Verification of humans using the electrocardiogram" 28 (28): 1172-1175, 2007

3 Klonowski M, "User authorization based on hand geometry without special equipment" 73 : 189-201, 2018

4 Crawford J, "Ten steps to recording a standard 12-lead ECG" 21 (21): 622-630, 2010

5 Erdogmus N, "Spoofing face recognition with 3D masks" 9 (9): 1084-1097, 2014

6 Hassan Z, "Review of fiducial and nonfiducial techniques of feature extraction in ECG based biometric systems" 9 (9): 23-26, 2016

7 Haware S, "Retina based biometric identification using SURF and ORB feature descriptors" 1-6, 2017

8 Gradl S, "Real-time ECG monitoring and arrhythmia detection using Android-based mobile devices" 2452-2455, 2012

9 Ma L, "Personal identification based on iris texture analysis" 25 (25): 1519-1533, 2003

10 Rajagopal G, "Personal authentication using multifeatures multispectral palm print traits" 2015 : 1-12, 2015

11 Shen TW, "One-lead ECG for identity verification" 1 : 62-63, 2002

12 Rai H, "Iris recognition using combined support vector machine and Hamming distance approach" 41 (41): 588-593, 2014

13 Shen TWD, "Implementation of a onelead ECG human identification system on a normal population" 2 (2): 12-21, 2010

14 Chen CH, "High performance iris recognition based on 1-D circular feature extraction and PSO-PNN classifier" 36 (36): 10351-10356, 2009

15 Cao K, "Hacking mobile phones using 2D printed fingerprints" Michigan State University 1-3, 2016

16 Isenor DK, "Fingerprint identification using graph matching" 19 (19): 113-122, 1986

17 Ahonen T, "Face description with local binary patterns : application to face recognition" 12 : 2037-2041, 2016

18 Saini I, "Electrocardiogram beat classification using empirical mode decomposition and multiclass directed acyclic graph support vector machine" 40 (40): 1774-1787, 2014

19 Israel SA, "ECG to identify individuals" 38 (38): 133-142, 2005

20 Übeyli ED, "ECG beats classification using multiclass support vector machines with error correcting output codes" 17 (17): 675-684, 2007

21 Kang SJ, "ECG authentication system design based on signal analysis in mobile and wearable devices" 23 (23): 805-808, 2016

22 Biel L, "ECG analysis : a new approach in human identification" 50 (50): 808-812, 2001

23 Sun, Y, "Deep learning face representation by joint identification-verification" 1988-1996, 2014

24 O’Haver T, "Command-line findpeaks MATLAB function"

25 Sun Y, "Characteristic wave detection in ECG signal using morphological transform" 5 (5): 28-, 2005

26 Hrechak AK, "Automated fingerprint recognition using structural matching" 23 (23): 893-904, 1990

27 Wang Y, "Analysis of human electrocardiogram for biometric recognition" 1 : 148658-, 2008

28 Jain AK, "An introduction to biometric recognition" 14 : 4-20, 2014

29 Da He D, "An ear-worn vital signs monitor" 62 (62): 2547-2552, 2015

30 Osselton JW, "Acquisition of EEG data by bipolar unipolar and average reference methods: a theoretical comparison" 19 : 527-528, 1965

31 Shaheed K, "A systematic review of finger vein recognition techniques" 9 (9): 213-, 2018

32 Acır N, "A support vector machine classifier algorithm based on a perturbation method and its application to ECG beat recognition systems" 31 (31): 150-158, 2006

33 Zhang Q, "A machine learning-empowered system for long-term motion-tolerant wearable monitoring of blood pressure and heart rate with Ear-ECG/PPG" 5 : 10547-10561, 2017