ANALYSIS OF ECG SIGNALS BY DIVERSE AND COMPOSITE FEATURES

Öz

  

Anahtar Kelimeler

• -

Kaynakça

1. “Feature extraction from ECG signals using wavelet transforms for disease diagnostics”, International Journal of Systems Science, Vol: , No: 13, pp. 1073-1085, 2002.
2. Baese, A., “Neural network-based EKG pattern recognition”, Engineering Applications of Artificial Intelligence, Vol: 15, pp. 253-260, Diamantaras, K., Pappas, C., Strintzis, M., “ECG pattern recognition and classification using non- linear transformations and neural networks: A review”, International Journal of Medical Informatics, Vol: 52, pp. 191-208, 1998. /e215]; 2000 (June 13).
3. Sternickel, K., “Automatic pattern http://circ.ahajournals.org/cgi/content/full/101/23 recognition in ECG time series”, Computer Pages; Methods and Programs in Biomedicine, Vol: 68, (23), e215-e220 [Circulation Electronic pp. 109-115, 2002.
4. Complex Physiologic Signals, Circulation Components of a New Research Resource for Güler, İ., Übeyli, E.D., “ECG beat H.E. Physiobank, Physiotoolkit, and Physionet: classifier designed by combined neural network Mietus, J.E., Moody, G.B., Peng, C.K., Stanley, model”, Pattern Recognition, Vol: 38, No: 2, pp. L., Hausdorff, J.M., Ivanov, P.Ch., Mark, R.G., 208, 2005. selection for classification problems”, IEEE
5. Transactions on Neural Networks, Vol: 3, No: 1, pp. 143-159, 2002. extraction from Doppler ultrasound signals for automated diagnostic systems”, Computers in
6. Biology and Medicine, Vol: 35, No: 9, pp. 735- , 2005.
7. Hinton, G.E., “Adaptive mixtures of local experts”, Neural Computation, Vol: 3, No: 1, pp. 87, 1991.
8. Daubechies, I., “The wavelet transform, time-frequency localization and signal analysis”, IEEE Transactions on Information Theory, Vol: , No: 5, pp. 961-1005, 1990.

9. W., Bauer, M.D., Kostis, J.B., “Noninvasive detection of coronary stenoses before and after angioplasty using eigenvector methods”, IEEE Transactions on Biomedical Engineering, Vol: , No: 11, pp. 1095-1104, 1990.
10. Übeyli, E.D., Güler, İ., “Comparison of eigenvector methods with classical and model- based methods in analysis of internal carotid arterial Doppler signals”, Computers in Biology and Medicine, Vol: 33, No: 6, pp. 473-493, 2003.
11. Chen, K., “A connectionist method for pattern classification with diverse features”, Pattern Recognition Letters, Vol: 19, No: 7, pp. 558, 1998.
12. Xu, L., Krzyzak, A., Suen, C.Y., “Methods of combining multiple classifiers and their applications to handwriting recognition”, IEEE Transactions on Systems, Man, and Cybernetics, Vol: 22, No: 3, pp. 418-435, 1992.
13. Chen, K., Wang, L., Chi, H., “Methods of combining multiple classifiers with different features and their applications to text- independent speaker identification”, International Journal of Pattern Recognition and Artificial Intelligence, Vol: 11, No: 3, pp. 417- , 1997.
14. Chen, K., Xu, L., Chi, H., “Improved learning algorithms for mixture of experts in multiclass classification”, Neural Networks, Vol: , No: 9, pp. 1229-1252, 1999.
15. Hong, X., Harris, C.J., “A mixture of experts network structure construction algorithm for modelling and control”, Applied Intelligence, Vol: 16, No: 1, pp. 59-69, 2002.
16. Jordan, M.I., Jacobs, R.A., “Hierarchical mixture of experts and the EM algorithm”, Neural Computation, Vol: 6, No: 2, pp. 181-214, Güler, İ., Übeyli, E.D., “A mixture of experts network structure for modelling Doppler ultrasound blood flow signals”, Computers in Biology and Medicine, Vol: 35, No: 7, pp. 565- , 2005.
17. Wolpert, D.H., “Stacked generalization”, Neural Networks, Vol: 5, pp. 241-259, 1992.
18. Elif Derya ÜBEYLİ graduated from Çukurova University in 1996. She took her M.S. degree in 1998, all in electronic engineering. She took her Ph.D. degree from Gazi University, electronics and computer technology.
19. Table 2. The power levels of the PSDs obtained by the eigenvector methods of four exemplary records from four classes ECG beat types Extracted Features Pisarenko PSD values values PSD values Normal beat Minimum -63.3942 Mean -29.0350 Standard deviation Maximum 15.4373 Minimum -58.5668 Mean -34.2724 Standard deviation Maximum 8.9680 Minimum -73.2121 Mean -44.5406 Standard deviation Maximum 19.4951 Minimum -62.0746 Mean -39.9064 Standard deviation 6.1429 48.5747 25.5815 6241 8120 54.1374 33.0135 0780 5634 66.8833 43.3792 2899 0237 54.3199 36.4000 9989 1709 4749