Authors: Omar Saber Qasim; Zakariya Yahya Algamal
Addresses: Department of Mathematics, University of Mosul, Mosul, 41002, Iraq ' Department of Statistics and Informatics, University of Mosul, Mosul, 41002, Iraq
Abstract: In classification problems, there are many data that contain a large number of features, some of which are irrelevant and cause confusion for the classifiers. The support vector classification (SVC) method is one of the most common methods used in classification. Feature selection, together with the parameters setting of SVC, such as the kernel parameter and the penalty parameter, significantly affects the classification performance of the SVC. In this study, the gray wolf optimisation (GWO) algorithm is proposed to improve feature selection and determine the optimal parameter values of SVC simultaneously. Based on several benchmark datasets for diseases, the experimental results show that the proposed method, FOGWO-SVC, is capable in selecting the best features with best parameters determination. Further, the comparative results demonstrate that the FOGWO-SVC is better or comparable than other competitor algorithms in terms of classification accuracy and feature reduction.
Keywords: feature selection; GWO; gray wolf optimisation; binary GWO; parameter selection; SVC; support vector classification; metaheuristic algorithms; classification.
International Journal of Computing Science and Mathematics, 2021 Vol.13 No.1, pp.93 - 102
Received: 29 Mar 2019
Accepted: 02 Mar 2020
Published online: 13 Apr 2021 *