Paper:
Language: English:

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

Received: September 25, 2005

Accepted: December 21, 2005

Keywords: biomedical classification, neural-network model, radial base function network, support vector machine

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.10, No.4 pp. 498-503, 2006

Abstract

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.

[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here: