A signal theory approach to support vector classification: the sinc kernel

Nelso, James D.B., Damper, Robert I., Gunn, Steve R. and Guo, Baofeng (2008) A signal theory approach to support vector classification: the sinc kernel Neural Networks, 22, (1), pp. 49-57. (doi:10.1016/j.neunet.2008.09.016). (PMID:19118976).


[img] PDF nnt1906.pdf - Other
Download (201kB)


Fourier-based regularisation is considered for the support vector machine classification problem over absolutely integrable loss functions. By invoking the modest assumption that the decision function belongs to a Paley–Wiener space, it is shown that the classification problem can be developed in the context of signal theory. Furthermore, by employing the Paley–Wiener reproducing kernel, namely the sinc function, it is shown that a principled and finite kernel hyper-parameter search space can be discerned, a priori. Subsequent simulations performed on a commonly-available hyperspectral image data set reveal that the approach yields results that surpass state-of-the-art benchmarks.

Item Type: Article
Digital Object Identifier (DOI): doi:10.1016/j.neunet.2008.09.016
Keywords: hyperspectral imaging, parameter estimation, regularisation, reproducing kernel hilbert spaces, sequency analysis, signal theory, sinc kernel, support vector machines
Organisations: Electronic & Software Systems, Southampton Wireless Group
ePrint ID: 266637
Date :
Date Event
12 November 2008e-pub ahead of print
January 2009Published
Date Deposited: 08 Sep 2008 20:16
Last Modified: 17 Apr 2017 19:01
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/266637

Actions (login required)

View Item View Item