ECG based personal identification using extended Kalman filter

Chee Ming Ting; Sh Hussain Salleh

doi:10.1109/ISSPA.2010.5605516

ECG based personal identification using extended Kalman filter

Chee Ming Ting
, Sh Hussain Salleh

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

40 Citations (Scopus)

Abstract

This paper proposes a new approach for electrocardiogram (ECG) based personal identification based on extended Kalman filtering (EKF) framework. The framework uses nonlinear ECG dynamic models formulated to represent noisy ECG signal. The advantage of the models is the ability to capture distinct ECG features used for biometric recognition such as temporal and amplitude distances between PQRST points. Moreover the inherent modeling of additive noise provides robust recognition. Log-likelihood scoring is proposed for classification. The algorithm is evaluated on identification task on 13 subjects of MIT-BIH Arrhythmia Database using single lead data. Identification rate of 87.50% is achieved on 30s test recordings of normal beat. Experimental results using artificial additive white noise show that the model is robust to noise for SNR level above 20dB.

Original language	English
Title of host publication	10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010
Pages	774-777
Number of pages	4
DOIs	https://doi.org/10.1109/ISSPA.2010.5605516
Publication status	Published - 2010
Externally published	Yes
Event	International Conference on Information Science, Signal Processing and their Applications 2010 - Kuala Lumpur, Malaysia Duration: 10 May 2010 → 13 May 2010 Conference number: 10th https://ieeexplore.ieee.org/xpl/conhome/5605286/proceeding (Proceedings)

Conference

Conference	International Conference on Information Science, Signal Processing and their Applications 2010
Abbreviated title	ISSPA 2010
Country/Territory	Malaysia
City	Kuala Lumpur
Period	10/05/10 → 13/05/10
Internet address	https://ieeexplore.ieee.org/xpl/conhome/5605286/proceeding (Proceedings)

Keywords

Electrocardiography
Identification of persons
Kalman filtering

Access to Document

10.1109/ISSPA.2010.5605516

Cite this

@inproceedings{15f608f264de4c3fbd8b90065ef8f4e8,

title = "ECG based personal identification using extended Kalman filter",

abstract = "This paper proposes a new approach for electrocardiogram (ECG) based personal identification based on extended Kalman filtering (EKF) framework. The framework uses nonlinear ECG dynamic models formulated to represent noisy ECG signal. The advantage of the models is the ability to capture distinct ECG features used for biometric recognition such as temporal and amplitude distances between PQRST points. Moreover the inherent modeling of additive noise provides robust recognition. Log-likelihood scoring is proposed for classification. The algorithm is evaluated on identification task on 13 subjects of MIT-BIH Arrhythmia Database using single lead data. Identification rate of 87.50\% is achieved on 30s test recordings of normal beat. Experimental results using artificial additive white noise show that the model is robust to noise for SNR level above 20dB.",

keywords = "Electrocardiography, Identification of persons, Kalman filtering",

author = "Ting, \{Chee Ming\} and Salleh, \{Sh Hussain\}",

note = "Copyright: Copyright 2011 Elsevier B.V., All rights reserved.; International Conference on Information Science, Signal Processing and their Applications 2010, ISSPA 2010 ; Conference date: 10-05-2010 Through 13-05-2010",

year = "2010",

doi = "10.1109/ISSPA.2010.5605516",

language = "English",

isbn = "9781424471676",

pages = "774--777",

booktitle = "10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010",

url = "https://ieeexplore.ieee.org/xpl/conhome/5605286/proceeding",

}

Ting, CM & Salleh, SH 2010, ECG based personal identification using extended Kalman filter. in 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010. pp. 774-777, International Conference on Information Science, Signal Processing and their Applications 2010, Kuala Lumpur, Malaysia, 10/05/10. https://doi.org/10.1109/ISSPA.2010.5605516

TY - GEN

T1 - ECG based personal identification using extended Kalman filter

AU - Ting, Chee Ming

AU - Salleh, Sh Hussain

N1 - Conference code: 10th

PY - 2010

Y1 - 2010

N2 - This paper proposes a new approach for electrocardiogram (ECG) based personal identification based on extended Kalman filtering (EKF) framework. The framework uses nonlinear ECG dynamic models formulated to represent noisy ECG signal. The advantage of the models is the ability to capture distinct ECG features used for biometric recognition such as temporal and amplitude distances between PQRST points. Moreover the inherent modeling of additive noise provides robust recognition. Log-likelihood scoring is proposed for classification. The algorithm is evaluated on identification task on 13 subjects of MIT-BIH Arrhythmia Database using single lead data. Identification rate of 87.50% is achieved on 30s test recordings of normal beat. Experimental results using artificial additive white noise show that the model is robust to noise for SNR level above 20dB.

AB - This paper proposes a new approach for electrocardiogram (ECG) based personal identification based on extended Kalman filtering (EKF) framework. The framework uses nonlinear ECG dynamic models formulated to represent noisy ECG signal. The advantage of the models is the ability to capture distinct ECG features used for biometric recognition such as temporal and amplitude distances between PQRST points. Moreover the inherent modeling of additive noise provides robust recognition. Log-likelihood scoring is proposed for classification. The algorithm is evaluated on identification task on 13 subjects of MIT-BIH Arrhythmia Database using single lead data. Identification rate of 87.50% is achieved on 30s test recordings of normal beat. Experimental results using artificial additive white noise show that the model is robust to noise for SNR level above 20dB.

KW - Electrocardiography

KW - Identification of persons

KW - Kalman filtering

UR - https://www.scopus.com/pages/publications/78650283260

U2 - 10.1109/ISSPA.2010.5605516

DO - 10.1109/ISSPA.2010.5605516

M3 - Conference Paper

AN - SCOPUS:78650283260

SN - 9781424471676

SP - 774

EP - 777

BT - 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010

T2 - International Conference on Information Science, Signal Processing and their Applications 2010

Y2 - 10 May 2010 through 13 May 2010

ER -

ECG based personal identification using extended Kalman filter

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this