Classification of Time Series Using Singular Values and Wavelet Subband Analysis with ANN and SVM Classifiers
Balázs Benyó*, Péter Somogyi**, and Béla Paláncz***
*Department of Information Technology, Széchenyi István University, Egyetem tér 1., Győr H-9026, Hungary
**Department of Control Engineering and Information Technology, Budapest University of Technology and Economics, Magyar tudósok krt. 2., Budapest H-1117, Hungary
***Department of Photogrammetry and Geoinformatics, Budapest University of Technology and Economics, Műegyetem rakpart 3., Budapest H-1117, Hungary
Oscillation of cerebral blood flow (CBF) in physiological or pathophysiological brain states is common, therefore it is promising to identify cerebral circulation disorders based on CBF signal classification. To characterize temporal blood flow patterns, we applied two feature extractions, spectral matrix and wavelet subband analysis. To distinguish between different physiological states, two different classifications have been developed – the radial basis function-based neural network and a support vector classifier with a Gaussian kernel. Feature extraction and classification are evaluated and their efficiency compared. Calculation was done using Mathematica 5.1 and its Wavelet Application.
-  Aboufadel and Schlicker, “Discovering Wavelets,” Wiley-Interscience, 1999.
-  B. Benyó et al., “Characterization of the Temporal Pattern of Cerebral Blood Flow Oscillations,” Proc. of 2004 International Joint Conference on Neural Networks, pp. 468-471, July, 2004.
-  B. Benyó et al., “Characterization of Cerebral Blood Flow Oscillations Using Different Classification Methods,” Proc. of 2005 IFAC, electronic publication #04987, 2005.
-  B. Benyó et al., “Classification of Cerebral Flood Flow Oscillation using SVM classifiers with different kernels,” Intelligent Systems at the Service of Mankind, Vol.2, pp. 145-151, 2005.
-  B. Diehl et al., “Spontaneous oscillations in cerebral blood flow velocities in middle cerebral arteries in control subjects and patients with epilepsy,” Stroke, Vol.28, pp. 2457-2459, 1997.
-  N. Cristianini, and J. Shawe-Taylor, “An introduction to Support Vector Machines and other kernel-based learning methods,” Cambridge University Press, 2000.
-  G. Lenzsér et al., “Nitric oxide synthase blockade sensitizes the cerebrocortical circulation to thromboxane-induced CBF oscillations,” Journal of Cerebral Blood Flow and Metabolism, Vol.23, p. 88, 2003.
-  J. C. Goswami, and A. K. Chan, “Fundamentals of Wavelets. Theory, Algorithms, and Application,” Wiley, 1999.
-  L. Zhang et al., “Wavelet Support Vector Machine,” IEEE Trans. Systems, Man and Cybernetics – Part B: Cybernetics, 4(1): pp. 34-39, Februray, 2004.
-  H. Nilsson, and C. Aalkjær, “Vasomotion mechanisms and physiological importance,” Molecular Interventions, Vol.7, pp. 59-68, 2003.
-  B. Paláncz, “Support Vector Classifier via Mathematica,” Wolfram Research Mathematica Information Center, 2004.
-  B. Paláncz, “Wavelets and their Application to Digital Image Processing,” Publications in Geomatics, 2004, Győr, ISSN: 1419-6492.
-  W. Shaw, and J. Tigg, “Applied Mathematica,” Addison-Wesley, 1994.
-  Z. Lacza et al., “The cerebrocortical microcirculatory effect of nitric oxide synthase blockade is dependent upon baseline red blood cell flow in the rat,” Neuroscience Letters, Vol.291, pp. 65-68, 2000.
-  Z. Lacza et al., “NO synthase blockade induces chaotic cerebral vasomotion via activation of thromboxane receptors,” Stroke, Vol.32, pp. 2609-2614, 2001.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.