Ubaid ur Rehman
ABSTRACT
Automatic identification of individuals using biometric features is an area that has gained high importance nowadays. The paper presents a novel approach for biometric identification through ECG signal using hybridization of different features and Radial Basis Function Neural Network (RBF-NN). Three different features namely ARIMA, Wavelet Entropy, and Sample Entropy are extracted from an ECG dataset. The features are then fed to an RBF-NN to identify different individuals. In the past, these features were used individually for person identification. This paper presents an approach for person identification by hybridization of the above mentioned features. The proposed approach shows promising results with an accuracy of 99.50% to identify 55 individuals correctly.
- Subban, R. and Mankame, D.P., 2013. A study of biometric approach using fingerprint recognition. Lecture notes on software engineering, 1(2), p. 209.Google Scholar
- Biometricupdate.com. (2018). {online} Available at: https://www.biometricupdate.com/wp/content/uploads/2014/05/Voice-Biometrics.pdf.Google Scholar
- Elsherief, S.M., Allam, M.E. and Fakhr, M.W., 2006, November. Biometric personal identification based on iris recognition. In Computer Engineering and Systems, The 2006 International Conference on (pp. 208--213). IEEE.Google Scholar
- Bhatia, R., 2013. Biometrics and face recognition techniques. International Journal of Advanced Research in Computer Science and Software Engineering, 3(5).Google Scholar
- Foteini. ECG in biometric recognition: Time dependency and application challenges. University of Toronto, 2011.Google Scholar
- Tawfik, M.M. and Kamal, H.S.T., 2011. Human identification using QT signal and QRS complex of the ECG. Online J Electron Electr Eng (OJEEE), 3, pp. 1--5.Google Scholar
- Saechia, S., Koseeyaporn, J. and Wardkein, P., 2005, November. Human identification system based ECG signal. In TENCON 2005 2005 IEEE Region 10 (pp. 1--4). IEEE.Google Scholar
- Bassiouni, M., Khaleefa, W., El-Dahshan, E.A. and Salem, A.B.M., 2016. A machine learning technique for person identification using ECG signals. Int. J. Appl. Phys, 1, pp. 37--41.Google Scholar
- Ye, C., Coimbra, M.T. and Kumar, B.V., 2010, August. Arrhythmia detection and classification using morphological and dynamic features of ECG signals. In Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE (pp. 1918--1921). IEEE.Google Scholar
- Shen, J., Bao, S.D., Yang, L.C. and Li, Y., 2011, August. The PLR-DTW method for ECG based biometric identification. In Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE (pp. 5248--5251). IEEE.Google Scholar
- Ouelli, A., ElhadadiL, B., Aissaoui, H. and Bouikhalene, B., 2012. AR modeling for automatic cardiac arrhythmia diagnosis using QDF based algorithm. International Journal of Advanced Research in Computer Science and Software Engineering, 2(5).Google Scholar
- Butterworth, S., 1930. On the theory of filter amplifiers. Wireless Engineer, 7(6), pp. 536--541.Google Scholar
- Rosso, O.A., Blanco, S., Yordanova, J., Kolev, V., Figliola, A., Schürmann, M. and Başar, E., 2001. Wavelet entropy: a new tool for analysis of short duration brain electrical signals. Journal of neuroscience methods, 105(1), pp.65--75.Google ScholarCross Ref
- Yentes, J.M., Hunt, N., Schmid, K.K., Kaipust, J.P., McGrath D. and Stergiou, N., 2013. The appropriate use of approximate entropy and sample entropy with short data sets. Annals of biomedical engineering, 41(2), pp.349--365.Google ScholarCross Ref
- Seenivasagam, V. and Arumugadevi, S., 2012. Radial Basis Function Neural Networks (RBFNN) For Fire Image Segmentation. International Journal of Advanced Research Computer Engineering & Technology (IJARCET), 1(6), pp.pp--212.Google Scholar
- The PTB Diagnostic ECG Database, physionet.org/physiobank/database/ptbdb/.Google Scholar
Index Terms
- Biometric Identification Through ECG Signal Using a Hybridized Approach
Recommendations
Biometric-oriented Iris Identification Based on Mathematical Morphology
A new method for biometric identification of human irises is proposed in this paper. The method is based on morphological image processing for the identification of unique skeletons of iris structures, which are then used for feature extraction. In this ...
Biometric Identification Based on Frequency Analysis of Cardiac Sounds
Part 2The performance of traditional biometric identification systems is, as yet, unsatisfactory in certain applications. For this reason, other physiological or behavioral characteristics have recently been considered, using new electrical or physical ...
Efficient Clustering-Based electrocardiographic biometric identification
AbstractThe correct identification of individuals through different biometric traits is becoming increasingly important. Apart from traditional biomarkers (like fingerprints), many alternative measures have been proposed during the last two ...
Highlights- We propose a novel efficient framework for ECG-based biometric identification.
- ...
Comments