A system of biometric authentication based on ECG signal segmentation

One of the fundamental difficulties of ECG (Electrocardiogram) based biometric systems is intrabeat variation. In order to decrease these variations and increase the performance of the biometric system, we have proposed a new convolution based method for beat extraction and a waveshape based method for beat segmentation. In the feature extraction stage, thirty spatial and interval features are extracted and they are categorized in six groups using Feature Forward Selection (FFS) method. Feature classification is done by using four classifiers: Nearest Neighbor, Gaussian, Principal Component and Parzen Window data description. The experiment is done on MIT-BIH normal sinus rhythm database and the proposed method is achieved to %2.34±0.19 Equal Error Rate (EER) and %99.73±0.04 Area Under the ROC Curve (AUC) using Parzen Window classifier.

[1]  John J. Soraghan,et al.  ECG biometric authentication using Pulse Active Width (PAW) , 2011, 2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS).

[2]  John J Soraghan,et al.  Pulse Active Bit (PAB) feature extractor for ECG biometric authentication , 2011, 2011 18th International Conference on Systems, Signals and Image Processing.

[3]  John J. Soraghan,et al.  Pulse Active Ratio (PAR): A new feature extraction technique for ECG biometric authentication , 2011, 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[4]  T.W. Shen,et al.  Biometric Statistical Study of One-Lead ECG Features and Body Mass Index (BMI) , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[5]  Dimitrios Hatzinakos,et al.  Signal validation for cardiac biometrics , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Dimitrios Hatzinakos,et al.  Medical biometrics: The perils of ignoring time dependency , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[7]  Dimitrios Hatzinakos,et al.  HeartID: Cardiac biometric recognition , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[8]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[9]  Sanjay Kumar Singh,et al.  Evaluation of Electrocardiogram for Biometric Authentication , 2012, J. Information Security.

[10]  Noureddine Belgacem,et al.  ECG Based Human Authentication using Wavelets and Random Forests , 2012 .

[11]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[12]  M. Arthanari,et al.  ECG Feature Extraction Techniques - A Survey Approach , 2010, ArXiv.

[13]  M B Shamsollahi,et al.  A model-based Bayesian framework for ECG beat segmentation , 2009, Physiological measurement.

[14]  Sanjay Kumar Singh,et al.  Human Identification Using Heartbeat Interval Features and ECG Morphology , 2012, BIC-TA.

[15]  Srinivasan Jayaraman,et al.  Human Electrocardiogram for Biometrics Using DTW and FLDA , 2010, 2010 20th International Conference on Pattern Recognition.

[16]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.