Share Email Print
cover

Proceedings Paper

Performance evaluation of evolutionary computational and conventionally trained support vector machines
Author(s): Walker H. Land; John Heine; George Tomko; Alda Mizaku; Swati Gupta; Robert Thomas
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The main objective of this paper is to validate this newly developed Evolutionary Programming (EP) derived Support Vector Machines (SVMs) paradigm by a performance comparison with the accepted conventional iterative gradient method usually used to train these SVMs. The paper first reviews the background research associated with this research problem and follows with the description of the EP developed family of SVMs. Both the mutation and selection methods used to formulate the family of SVMs are described, which is followed by the more familiar Langrangian formulation of SVMs. Kernel based learning methods are then discussed. The concepts described here are not limited to SVMs, and the general principles also apply to other kernel based classifiers as well. Results are depicted for two EP methods: the first a "crude" earlier method described in reference 7 and the more recently method described here. Iteratively derived SVM results are also developed for comparison with the EP derived SVM approach. These results show that both methods produced essentially perfect classification AZ results, generally ranging from 0.926 to 0.931. Only the hyperbolic tangent kernel yielded the less accurate result of 0.87. These were expected results because all ambiguous findings were "scrubbed" from the features describing the screen film data set.

Paper Details

Date Published: 30 April 2007
PDF: 11 pages
Proc. SPIE 6560, Intelligent Computing: Theory and Applications V, 65600W (30 April 2007); doi: 10.1117/12.716543
Show Author Affiliations
Walker H. Land, Binghamton Univ. (United States)
John Heine, Univ. of Southern Florida (United States)
George Tomko, Binghamton Univ. (United States)
Alda Mizaku, Binghamton Univ. (United States)
Swati Gupta, Binghamton Univ. (United States)
Robert Thomas, Binghamton Univ. (United States)


Published in SPIE Proceedings Vol. 6560:
Intelligent Computing: Theory and Applications V
Kevin L. Priddy; Emre Ertin, Editor(s)

© SPIE. Terms of Use
Back to Top