단일 리드 심전도를 이용한 개인 식별
Identification of Individuals using Single-Lead Electrocardiogram Signal
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
We propose an individual identification method using a single-lead electrocardiogram signal. In this paper,lead I ECG is measured from subjects in various physical and psychological states. We performed a noise reductionfor lead I signal as a preprocessing stage and this signal is used to acquire the representative beat waveform for individualsby utilizing the ensemble average. From the P-QRS-T waves, features are extracted to identify individuals,19 using the duration and amplitude information, and 16 from the QRS complex acquired by applying Pan-Tompkinsalgorithm to the ensemble averaged waveform. To analyze the effect of each feature and to improve efficiency whilemaintaining the performance, Relief-F algorithm is used to select features from the 35 features extracted. Some orall of these 35 features were used in the support vector machine (SVM) learning and tests. The classification accuracyusing the entire feature set was 98.34%. Experimental results show that it is possible to identify a person by featuresextracted from limb lead I signal only.
Abstract
We propose an individual identification method using a single-lead electrocardiogram signal. In this paper,lead I ECG is measured from subjects in various physical and psychological states. We performed a noise reductionfor lead I signal as a preprocessing stage and this signal is used to acquire the representative beat waveform for individualsby utilizing the ensemble average. From the P-QRS-T waves, features are extracted to identify individuals,19 using the duration and amplitude information, and 16 from the QRS complex acquired by applying Pan-Tompkinsalgorithm to the ensemble averaged waveform. To analyze the effect of each feature and to improve efficiency whilemaintaining the performance, Relief-F algorithm is used to select features from the 35 features extracted. Some orall of these 35 features were used in the support vector machine (SVM) learning and tests. The classification accuracyusing the entire feature set was 98.34%. Experimental results show that it is possible to identify a person by featuresextracted from limb lead I signal only.
참고문헌 (25)
- L. Biel., "ECG analysis : A new approach in human identification", Ieee Transactions on Instrumentation and Measurement, 50, pp.808~812 (2001)
- G. Di Crescenzo., "Financial Cryptography and Data Security", pp.240~254 (2005), Springer
- R. Sandhu., "Authentication, access control, and audit", Acm Computing Surveys, 28, pp.241~243 (1996)
- H. Dai., "Atrial activity extraction from single lead ECG recordings : evaluation of two novel methods", Comput Biol Med, 43, pp.176~183 (2013)
- Y. Can., "Investigation of human identification using two-lead Electrocardiogram(ECG)signals", 2010 Fourth IEEE International Conference on, pp.1~8 (2010)
- N. Poh., "Audio- and VideoBased Biometric Person Authentication. vol. 2091", pp.348~353 (2001), Springer Berlin Heidelberg
- R. Snelick., "Large-scale evaluation of multimodal biometric authentication using state-of-the-art systems", IEEE Trans Pattern Anal Mach Intell, 27, pp.450~455 (2005)
- K. Sidek., "An efficient method of biometric matching using interpolated ECG data", 2010 IEEE EMBS Conference on, pp.330~335 (2010)
- Y. J. Wang., "Analysis of human electrocardiogram for biometric recognition", EURASIP journal on Advances in Signal Processing, 2008, pp.19~ (2008)
- A. Lourenco., "ECG-based biometrics : A real time classification approach", 2012 IEEE International Workshop on, pp.1~6 (2012)
- Z. Zhidong., "ECG identification based on Matching Pursuit", 2011 4th International Conference on, pp.721~724 (2011)
- J. S. Lee., "Personal Identification Based on Vectorcardiogram Derived from Limb Leads Electrocardiogram", Journal of Applied Mathematics, 2012 (2012)
- I. Odinaka., "ECG Biometric Recognition : A Comparative Analysis", Ieee Transactions on Information Forensics and Security, 7, pp.1812~1824 (2012)
- A. Kaveh., "Temporal and spectral features of single lead ECG for human identification", 2013 IEEE Workshop on, pp.17~21 (2013)
- Z. Zhao., "A human ECG identification system based on ensemble empirical mode decomposition", Sensors(Basel), 13, pp.6832~6864 (2013)
- 임용규, "Monitoring Physiological Signals Using Nonintrusive Sensors Installed in Daily Life Equipment", Biomedical Engineering Letters (BMEL), 1(1), pp.11~20 (2011), 대한의용생체공학회[DOI]
- Yoon-Nyun Kim, "A New Method of ECG Feature Detection Based on Combined Wavelet Transform for u-health Service", Biomedical Engineering Letters (BMEL), 1(2), pp.108~115 (2011), 대한의용생체공학회[DOI]
- 윤형로, "Optimization Methods for Improving the Performance of Heart Rate Detection by a Wearable ECG System During High-intensity Exercise", Biomedical Engineering Letters (BMEL), 1(2), pp.143~150 (2011), 대한의용생체공학회[DOI]
- C. He., "Toward ubiquitous healthcare services with a novel efficient cloud platform", IEEE Trans Biomed Eng, 60, pp.230~234 (2013)
- J. Pan., "A real-time QRS detection algorithm", IEEE Trans Biomed Eng, 32, pp.230~236 (1985)
- L. Sörnmo, "Bioelectrical signal processing in cardiac and neurological applications" (2005), Academic Press
- J. S. Lee, "MSP430 utilizing signal acquisition and processing" (2012), ITC
- A. Smrdel., "An algorithm to estimate the ST segment level in 24-hour ambulatory ECG records", in Computers in Cardiology, 2008, pp.701~704 (2008)
- M. N. Murty, "Pattern recognition: An algorithmic approach" (2011), Springer
- I. Kononenko, "Machine Learning: ECML-94. vol. 784", pp.171~182 (1994), Springer Berlin Heidelberg