Publication: Robust g-filter using support vector method
Loading...
Identifiers
Publication date
2004-12
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Abstract
This Letter presents a new approach to time series modelling using the support vector machines (SVM). Although the g filter can provide stability in several time series models, the SVM is proposed here to provide robustness in the estimation of the g filter coefficients. Examples in chaotic time series prediction and channel equalization show the advantages of the joint SVM g filter.
Description
Keywords
Suuport vector machines, Gamma filter, Iterated prediction, Channel equalization
Bibliographic citation
Neurocomputing, vol. 62, Dec. 2004, pp. 493-499