Abstract
In this study, two methods for the electrocardiogram (ECG) QRS waves detection were presented and compared. One hand, a modified approach of the linear approximation distance thresholding (LADT) algorithm was studied and the features of the ECG were gained for the later work. The other hand, Mexican-hat wavelet transform was adopted to detect the character points of ECG. A part of the features of the ECG were used to train the RBF network, and then all of them were used to examine the performance of the network. The algorithms were tested with ECG signals of MIT-BIH, and compared with other tests, the result shows that the detection ability of the Mexican-hat wavelet transform is very good for its quality of time-frequency representation and the ECG character points was represented by the local extremes of the transformed signals and the correct rate of QRS detection rises up to 99.9%. Also, the classification performance with its result is so good that the correct rate with the trained wave is 100%, and untrained wave is 86.6%.
This Work Supported by the Natural Science Foundation of China (No.60074014).
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Cheng, W.J.: A Pattern classification system based on fuzzy neural network. Journal of computer research & development 36(1), 26–30 (1999)
Nugent, C.D., Lopez, J.A., Smith, A.E., Black, N.D.: Prediction models in the design of neural network based ECG classifiers: A neural network and genetic programming approach. BMC Medical Informatics and Decision Making 2, 1 (2002)
Dokur, Z., Olmez, T.: ECG beat classification by a novel hybrid neural network. Computer methods and programs in biomedicine 66, 167–181 (2001)
Paul, J., et al.: A QRS estimator using linear prediction approach. Signal processing (72), 15–22 (1999)
Cuiwei, L., Chongxun, Z., Changfeng, T.: Detection of ECG characteristic points using wavelet transform. IEEE Trans BME 42(1), 21–29 (1995)
Dokur, Z., Olmez, T., Yazagan, E., et al.: Detection of ECG waveforms by neural networks. Medical Engineering and physics 19(8), 738–741 (1997)
Stephen, M.: Singular Detection and Processing with wavelet. IEEE Trans Information Theory 38(2), 617–643 (1992)
Daskalov, I.K., Christov, I.I.: Electrocardiogram signal preprocessing for automatic detection of QRS boundaries. Medical Engineering & Physics 21, 37–44 (1999)
Changqing, L., Shuyan, W.: ECG detection method based on adaptive wavelet neural network. Journal of Biomedical Engineering 19(3), 452–454 (2002); Xing, H.X.: Basic Electrocardiograph, 35–42, 128–141. PLA Publishing, Beijing (1988)
Li, G., Feng, J., Lin, L., et al.: Fast realization of the LADT ECG data compression method. IEEE Eng. Med. Biol. Mag. 13(2), 255 (1994)
Qi, J., Mo, Z.W.: Number of classes from ECG and its application to ECG analysis. Journal of Biomedical Engineering 19(2), 225 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mozhiwen, Jun, F., Yazhu, Q., Lan, S. (2005). Neural Network Classifier Based on the Features of Multi-lead ECG. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3610. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539087_5
Download citation
DOI: https://doi.org/10.1007/11539087_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28323-2
Online ISBN: 978-3-540-31853-8
eBook Packages: Computer ScienceComputer Science (R0)