COMPARISON BETWEEN SVM AND ANN FOR MODELING THE CEREBRAL AUTOREGULATION BLOOD FLOW SYSTEM
Max Chacón, Claudio Araya, Marcela Muñoz, Ronney B. Panerai
2009
Abstract
The performance of SVMs and ANNs as identifiers of time systems is compared with the purpose of analyzing the Cerebral blood flow Autoregulation System, one of the main systems in the field of cerebral hemodynamics. The main variables of this system are Arterial Blood Pressure (ABP) variations and changes in End-tidal pCO2 (EtCO2). In this work we show that models that have ABP and EtCO2 as input, trained with the SVM, are superior to ANN models in terms of the fit of an unknown set, and they are also more adequate for measuring the influence of EtCO2 on Cerebral Blood Flow Velocity.
References
- Acir, N., and Guzelis, C., 2004, Automatic spike detection in EEG by a two-stage procedure based on support vector machines. Comput Biol Med. Vol. 7, 561-75.
- Demuth, H., Beale. M., 2001, Neural network toolbox user's guide, The MathWorks Inc.
- Espinoza, M., Suykens, J.K.A., Belmans, R., and De Moor, B., 2007, Electric load forecasting - using kernel based modeling for nonlinear system identification,” IEEE Control Systems Magazine (Special Issue on Applications of System Identification), 43-57.
- Martínez-Ramón, M., Rojo-Álvarez, JL., Camps-Valls, G. Navia-Vázquez, A., Soria-Olivas, E., and FigueirasVidal, A., 2006, Support vector machines for nonlinear kernel ARMA system identification, IEEE Trans. on Neural Net., Vol. 17, 1617-1622.
- Mitsis, G., Poulin, M., Robbins, P., Marmarelis, V., 2004, Nonlinear modeling of dinamic effects of arterial pressure and CO2 variations on cerebral blood flow in healthy humans, IEEE Trans. Biomed. Eng., Vol. 51, 1932-1943.
- Panerai, R., Simpson, D., Deverson, S., Mahony, P., Hayes, P., Evans, D., 2000, Multivariate Dynamic Analysis of Cerebral Blood Flow Regulation in Humans”, IEEE Trans. Biomed. Eng., Vol 47, 419- 423.
- Rojo-Álvarez, JL, Martínez-Ramón, M. Prado-Cumplido, M Artés-Rodríguez, Figueiras-Vidal, A., 2004, Support Vector Method for Robust ARMA System Identification, IEEE Tran. Signal Process. Vol. 52, 155-164.
- Simpson, D., Panerai, R., Evans, D., Garnham, J., Naylor, A., Bell, P., 2000, Estimating normal and pathological dynamic responses in cerebral blood flow velocity to step changes in end-tidal pCO2, Med. Biol. Eng. Comp., Vol. 38, 535-539.
- Schölkopf, B., Smola, A., Williamson R.C., and Bartlett, P.L., 1998, New support vector algorithms, Neural Computation, Vol. 12, 1083-1121,.
- Suykens, JAK., Vandewalle J., 2000, Recurrent least squares support vector machines, IEEE Trans. on Circuits and Systems I, Vol. 47, 1109-1114.
- Widder, B., Paulat, K., Hackspacher, J. Mayr, E. 1986, Trascranial Doppler CO2 test for the detection of hemodynamically critical carotid artery stenoses and occlusions, Eur. Arch. Psych. Neurol. Sci., Vol 236, 162-168.
Paper Citation
in Harvard Style
Chacón M., Araya C., Muñoz M. and B. Panerai R. (2009). COMPARISON BETWEEN SVM AND ANN FOR MODELING THE CEREBRAL AUTOREGULATION BLOOD FLOW SYSTEM . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 522-525. DOI: 10.5220/0002279205220525
in Bibtex Style
@conference{icnc09,
author={Max Chacón and Claudio Araya and Marcela Muñoz and Ronney B. Panerai},
title={COMPARISON BETWEEN SVM AND ANN FOR MODELING THE CEREBRAL AUTOREGULATION BLOOD FLOW SYSTEM},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={522-525},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002279205220525},
isbn={978-989-674-014-6},
}
in EndNote Style
TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - COMPARISON BETWEEN SVM AND ANN FOR MODELING THE CEREBRAL AUTOREGULATION BLOOD FLOW SYSTEM
SN - 978-989-674-014-6
AU - Chacón M.
AU - Araya C.
AU - Muñoz M.
AU - B. Panerai R.
PY - 2009
SP - 522
EP - 525
DO - 10.5220/0002279205220525