Mixed-variable ant colony optimisation algorithm for feature subset selection and tuning support vector machine parameter
by Hiba Basim Alwan; Ku Ruhana Ku-Mahamud
International Journal of Bio-Inspired Computation (IJBIC), Vol. 9, No. 1, 2017

Abstract: This paper presents a hybrid classification algorithm, ACOMV-SVM which is based on ant colony and support vector machine. A new direction for ant colony optimisation is to optimise mixed (discrete and continuous) variables. The optimised variables are then feed into selecting feature subset and tuning its parameters are two main problems of SVM. Most approaches related to tuning support vector machine parameters will discretise the continuous value of the parameters which will give a negative effect on the performance. The objective of this paper is to formulate an algorithm for tuning SVM parameters and feature subset selection. This can be achieved by simultaneously performing the selection of feature subset and tuning SVM parameters tasks. ACO_MV-SVM algorithm is able to simultaneously tune SVM parameters and feature subset selection. Experimental results obtained from the proposed algorithm are better compared with other approaches in terms of classification accuracy and feature subset selection. The work in this paper also contributes to a new direction for ACO that can deal with mixed variable ACO.

Online publication date: Sun, 29-Jan-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bio-Inspired Computation (IJBIC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com