IV Latin American Congress on Biomedical Engineering 2007, Bioengineering Solutions for Latin America Health pp 1178-1181 | Cite as
Caracterización dinámica de registros ECG para identificación de arritmias
Palabras claves
adaptive filter banks Teager algorithm arrhythmiasAbstract
We present a methodology for feature extraction by means of adaptive filter banks in case of automatic identification of arrhythmias using ECG recording. Proposed filter banks, which are supposed to track in more accurate way any change of parameters of time-varying sequence, is developed for biorthogonal wavelet bases using Teager algorithm. Besides, adaptive lifting schemes, which allow filter order change, are used for filter bank implementation. Lifting schemes are introduced because lower computational complexity and less processing time. As features, both maximum value and variance of different wavelet decomposition levels are selected for brain zone classification. Results are provided using MIT database, in case of 2, 4, and 6 wavelet vanishing moments, for classification of 10 different arrhythmias. As a result, classification performance level of 98.5% value, estimated by means of bayesian classifier with Mahalanobis distance, is reached which is better than in 5% in comparison to those obtained figures for filter banks but having fixed parameters.
Preview
Unable to display preview. Download preview PDF.
Referencias
- 1.G. Strang and T. Nguyen, Wavelets and Filter Banks. Wellesley, MA, USA: Wellesley-Cambridge Press, 1996.Google Scholar
- 2.H. Heijmans, B. Pesquet-Popescu, and G. Piella, “Building nonredundant adaptive wavelets by update lifting,” Applied and Computational Analysis, vol. 18, pp. 252–281, 2005.MATHCrossRefMathSciNetGoogle Scholar
- 3.Jansen, M.; Oonincx, P. Second generation wavelets and applications. Springer, 2005.Google Scholar
- 4.G. Piella and B. Pesquet-Popescu, “Content adaptive multiresolution analysis,” in Proceedings of Acivs 2004 (Advanced Concepts for Intelligent Vision Systems), Belgium, 2004.Google Scholar
- 5.R. L. Claypoole, R. G. Baraniuk, and R. D. Nowak, “Lifting constructions of non-linear wavelet transforms,” IEEE transactions on image processing, vol. 12(12), pp. 1449–1459, 2003.CrossRefMathSciNetGoogle Scholar
- 6.J. Kaiser, “On a simple algorithm to calculate the energy of a signal,” Proc. IEEE ICASSP, Albuquerque, vol. 1, pp. 381–384, 1990.Google Scholar
- 7.Jung, J.; Strauss, D.; Sinnwell, T.; Hohenberg, G.; Fries, R.; Wern, H.; Schieffer, H.; Heisel, A. “Identification of ventricular tachycardias by means of fast wavelet analysis”, Computers in Cardiology, 1998, Volume 13, Issue 16, Page(s):21–24, Sep 1998.Google Scholar
- 8.Sung-Nien Yu, Chung Cheng, “Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network”, Pattern Recognition Letters, Volume 28, Issue 10, July 2007.Google Scholar
- 9.Daniel Strauss, Jens Jung, Andreas Rieder and Yiannos Manoli, “Classification of Endocardial Electrograms Using Adapted Wavelet Packets and Neural Networks”, Annals of Biomedical Engineering, Volume 29, Number 6, June, 2001.Google Scholar