Support Vector Machine (SVM) is one of the widely used algorithms for classification and regression problems. In SVM, penalty parameter C and kernel parameters can have a significant impact on the complexity and performance of SVM. In this paper, an Optimal Foraging Algorithm (OFA) is proposed to optimize the main parameters of SVM and reduce the classification error. Six public benchmark datasets were employed for evaluating the proposed (OFA-SVM). Also, five well-known and recently optimization algorithms are used for evaluation. These algorithms are Artificial Bee Colony (ABC), Genetic Algorithm (GA), Chicken Swarm Optimization (CSO), Particle Swarm Optimization (PSO) and Bat Algorithm (BA). The experimental results show that the proposed OFA-SVM obtained superior results. Also, the results demonstrate the capability of the proposed OFA-SVM to find optimal values of SVM parameters.
CITATION STYLE
Sayed, G. I., Soliman, M., & Hassanien, A. E. (2018). Modified Optimal Foraging Algorithm for Parameters Optimization of Support Vector Machine. In Advances in Intelligent Systems and Computing (Vol. 723, pp. 23–32). Springer Verlag. https://doi.org/10.1007/978-3-319-74690-6_3
Mendeley helps you to discover research relevant for your work.