Correo Electrónico
DNINFOA - SIA
Bibliotecas
Convocatorias
Identidad U.N.
Published
Extracting ECG signal characteristics based on non-linear transformations and wavelets
Extracción de características de ECG basadas en transformaciones no lineales y wavelets
DOI:
https://doi.org/10.15446/ing.investig.v25n3.14661Keywords:
ECG, ischemic heart disease, feature extraction, wavelets, nonlinear transformations, PCA, KPCA (en)ECG, cardiopatía isquémica, extracción de características, wavelets, PCA, KPCA (es)
Downloads
Different extraction methods were compared regarding the characteristics of normal ECG signals and those emitted in the presence of events related to ischemic cardiopathy based on diagnosis measurements, wavelet transformation and nonlinear analysis of main components. Methods were developed for automatic recognition between normal and ischemic ECG signals. Two effective feature selection techniques were proposed; one used multivariate statistical methods and the second univariate ones. Linear discriminatory evaluation and vector support machines were used for evaluating the proposed feature extraction techniques, comparing error when classifying different states of cardiac functionality. Nonlinear PCA offered slightly better performance compared to wavelet representation but was much better compared to diagnosis measurement. There was up to 0.22% error compared to 6.78% in the case of wavelets and 24.22% in the case of diagnostic measurements. Support vector machines increased the performance for all analysed feature extraction methods; more discriminating characteristics were obtained when using wavelets applied to heartbeat having up to 0.1% classification precision compared to 0.12% in the case of nonlinear analysis of main components and 5.11% in the case of diagnostic measurements.
Se presentan diferentes métodos de extracción de características en señales ECG normales y en presencia de eventos relacionados con cardiopatía isquémica, basados en mediciones de diagnóstico, la transformada wavelet y el análisis no lineal de componentes principales. Con el fin de determinar las características que contribuyen de mejor manera con el modelo, se aplican dos técnicas de selección efectiva de características empleando métodos estadísticos multivariados y univariados. La evaluación de las técnicas de extracción propuestas se realiza mediante análisis discriminante lineal y máquinas de soporte vectorial, comparando el error en la clasificación de diferentes estados de funcionalidad cardiaca. Como resultado del análisis discriminante lineal se obtiene que las características más efectivas se consiguen empleando el análisis no lineal de componentes principales sobre un latido. En este caso, el error obtenido de clasificación es de hasta el 0.22%, contra 6.78% en el caso de las wavelets, y 24.22% en el caso de las mediciones de diagnóstico. Con las máquinas de soporte vectorial se obtiene que las características más discriminantes se obtienen empleando wavelets aplicadas al latido con una precisión de clasificación hasta del 0.1%, contra 0.12% en el caso del análisis no lineal de componentes principales y 5.11% en el caso de las mediciones de diagnóstico.
References
Aguirre, P; Cardelina, J. y Loeft, N. "Sistema de detección, clasificación e identificación en línea de complejos QRS". Tesis doctoral, Instituto de Ingeniería Eléctrica, Facultad de Ingeniería Universidad de la Republica, Montevideo, Uruguay, 2002.
Burges, C. "A tutorial on support vector machines for pattern recognition". Knowledge Discovery and Data Mining, Vol. 2, p. 22, 1998. [Online]. Disponible: http://www.kernel-machines.org/papers/Burges98.ps.gz
Doltsinis, I., Rau, F. y Werner, M. "Analysis of random systems". Stochastic analysis of multivariate systems in computational mechanics and engineering, 1ra ed., International Center for Numerical Methods in Engineering, 1999, pp. 9-159.
Fujimura, S. y Kiyasu, S. "Application of feature extraction scheme to the discrimination of electrocardiogram (ECG)". TIEE Japan, Vol. 121-A, No. 8, 2001, pp. 725-730. DOI: https://doi.org/10.1541/ieejfms1990.121.8_725
Gholamhosseini, H. y Nazeran, H. "Efficient features for ann-based ECG classifiers". School of Engineering, the Flinders University of South Australia, 1999.
Haraldsson, H., Edenbrandt, L. y Ohlsson, M. "Detecting acute myocardial infarction in the 12-lead ECG using hermite expansions and neural networks". Artif Intell Med, Vol. 32, No. 2, 2004, pp. 127-136. DOI: https://doi.org/10.1016/j.artmed.2004.01.003
Hughes, N., Tarassenko, L. y Roberts, S. "Markov models for automated ECG interval analysis". Advances in Neural Information Processing Systems 16, MIT Press, Cambridge, 2004.
Jager, F "Feature extraction and shape representation of ambulatory electrocardiogram using the Karhunen-Loève transform". Elektrotehniski Vestnik, Vol. 69, No. 2, 2002, pp. 83-89.
Jain, A.; Duin, R. y Mao, J. "Statistical pattern recognition: a review". IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 1, 2000. DOI: https://doi.org/10.1109/34.824819
Kunzmann, U. et al. "Parameter extraction of ECG signals in real-time". Biomedizinische Technik, Vol. 47, No. 1, 2002, pp. 875-878. DOI: https://doi.org/10.1515/bmte.2002.47.s1b.875
Ladino, M. "Análisis de los cambios presentados en el segmento ST relacionados con enfermedades coronarias". Tesis presentada a la Universidad Nacional de Colombia, sede Manizales, para optar al título de ingeniero electrónico, 2004.
Lemire, D. et al. "Wavelet time entropy, T wave morphology and myocardial ischemia". IEEE Transactions on Biomedical Engineering, Vol. 47, No. 7, 2000, pp. 967-970. DOI: https://doi.org/10.1109/10.846692
Morales, L. A. "Segmentación de ECG normal con wavelets en tiempo real sobre DSP". Tesis presentada a la Universidad Nacional de Colombia, sede Manizales, para optar al titulo de ingeniero electrónico, 2003.
Ojeda, F. "Extracción de características usando transformada wavelet en la identificación de voces patológicas". Tesis presentada a la Universidad Nacional de Colombia, sede Manizales, para optar al título de ingeniero electrónico, 2003.
Olszewsky, R. "Generalized feature extraction for structural pattern recognition in time-series data". Tesis doctoral, School of Computer Science, Carnegie Mellon University, Pittsburg, PA 15213, 2001.
Orozco, M. "Clasificación de arritmias cardiacas usando transformada wavelet y técnicas de reconocimiento de patrones". Tesis presentada a la Universidad Nacional de Colombia, sede Manizales, para optar al título de ingeniero electrónico, 2003.
Ramírez, J. "Reducción en tiempo real de perturbaciones en señales de ECG empleando la transformada wavelet sobre DSP". Tesis presentada a la Universidad Nacional de Colombia, sede Manizales, para optar al título de ingeniero electrónico, 2004.
Rencher, A. C. Methods of Multivariate Analysis, Wiley-Interscience, 1992.
Reyna, M. y JANE, R. "Análisis multi-wavelet para la detección de conductividad ventricular anormal en señales ECG de alta resolución". Biomédica, Vol. 12, No. 2, Abril/Junio 2001, pp. 98-110. DOI: https://doi.org/10.32776/revbiomed.v12i2.262
Rosado, A. et al. "Enhancing feature extraction for VF detection using data mining techniques". The 29th Annual Conference of Computers in Cardiology, 2002.
Schölkopf, B.; Smola, A. y Miller, K.-R. "Nonlinear component analysis as a kernel eigenvalue problem". Tech. Rep., Max-Planck-Institut für biologische Kybernetik, 1996.
Schélkopf, B.; Smola, A. Learning with kernels support vector machines, regularization, optimization and beyond. Cambridge, MIT Press, 2002.
Silipo, R. "Investigating electrocardiographic features in fuzzy models for cardiac arrhythmia classification". International Computer Science Institute, Berkeley, USA, 1999.
Stamkopoulos, T. et al. "ECG analysis using nonlinear PCA neural networks for ischemia detection". IEEE Transactions On Signal Processing, Vol. 46, No. 11, Nov., 1998, pp. 3058-3066. DOI: https://doi.org/10.1109/78.726818
Suárez, J. et al. "Métodos multivariados en la selección efectiva de características para la clasificación de voces patológicas". Universidad Nacional de Colombia, sede Manizales, 2004.
Vapnik, V. The nature of statistical learning theory, New York, Springer, 1995. DOI: https://doi.org/10.1007/978-1-4757-2440-0
Vila, J. "Análisis de la variabilidad de señales fisiológicas, integración en un sistema de monitorización inteligente". Tesis doctoral, Universidad de Santiago de Compostela, Departamento de Electrónica y Computación, 1996.
Wolfe, P "The simplex method for quadratic programming". Econometrica, Vol. 27, pp. 382-398, 1959. DOI: https://doi.org/10.2307/1909468
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
CrossRef Cited-by
1. Emmanuel Moncada, Vittoria Valzania, Luis Ríos, Norma Barboza. (2023). ECG Features Extraction to Semiautomatic Detection of Atrial Fibrillation. 2023 IEEE EMBS R9 Conference. , p.1. https://doi.org/10.1109/IEEECONF60929.2023.10525479.
Dimensions
PlumX
Article abstract page views
Downloads
License
Copyright (c) 2005 Victoria Eugenia Montes, Gustavo A Guarín, Germán Castellanos Domínguez
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors or holders of the copyright for each article hereby confer exclusive, limited and free authorization on the Universidad Nacional de Colombia's journal Ingeniería e Investigación concerning the aforementioned article which, once it has been evaluated and approved, will be submitted for publication, in line with the following items:
1. The version which has been corrected according to the evaluators' suggestions will be remitted and it will be made clear whether the aforementioned article is an unedited document regarding which the rights to be authorized are held and total responsibility will be assumed by the authors for the content of the work being submitted to Ingeniería e Investigación, the Universidad Nacional de Colombia and third-parties;
2. The authorization conferred on the journal will come into force from the date on which it is included in the respective volume and issue of Ingeniería e Investigación in the Open Journal Systems and on the journal's main page (https://revistas.unal.edu.co/index.php/ingeinv), as well as in different databases and indices in which the publication is indexed;
3. The authors authorize the Universidad Nacional de Colombia's journal Ingeniería e Investigación to publish the document in whatever required format (printed, digital, electronic or whatsoever known or yet to be discovered form) and authorize Ingeniería e Investigación to include the work in any indices and/or search engines deemed necessary for promoting its diffusion;
4. The authors accept that such authorization is given free of charge and they, therefore, waive any right to receive remuneration from the publication, distribution, public communication and any use whatsoever referred to in the terms of this authorization.
