File(s) not publicly available

Performance analysis of statistical classifier SMO with other data mining classifiers

chapter
posted on 06.12.2017, 00:00 by A B M Shawkat Ali
Seven classifiers are compared on sixteen quite different, standard and extensively used datasets in terms of classification error rates and computational times. It is found that the average error rates for a majority of the classifiers are closes with each other but the computational times of the classifiers differ over a wide range. The statistical classifier Sequential Minimal Optimization (SMO) based on Support Vector Machine has the lowest average error rate and computationally it is faster than four classifiers but slightly expensive than other two classifiers.

History

Parent Title

Advances in soft computing : engineering design and manufacturing

Start Page

205

End Page

211

Number of Pages

7

ISBN-10

1852337559

ISBN-13

9781852337551

Publisher

Springer

Place of Publication

London, UK

Open Access

No

External Author Affiliations

Monash University;

Era Eligible

No

Number of Chapters

36

Exports

CQUniversity

Exports