¹ School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China, 221116
² Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, 100190

---

Abstract—How to select the suitable parameters and kernel model is a very important problem for Twin Support Vector Machines (TSVMs). In order to solve this problem, one solving algorithm called Invasive Weed Optimization Algorithm for Optimizating the Parameters of Mixed Kernel Twin Support Vector Machines (IWO-MKTSVMs) is proposed in this paper. Firstly, introducing the mixed kernel, the twin support vector machines based on mixed kernel is constructed. This strategy is a good way to solve the kernel model selection. In order to solve the parameters selection problem which contain TSVMs parameters and mixed kernel model parameters, Invasive Weed Optimization Algorithm (IWO) is introduced. IWO is an optimization algorithm who has strong robustness and good global searching ability. Finally, compared with the classical TSVMs, the experimental results show that IWO-MKTSVMs have higher classification accuracy.

Index Terms—Mixed kernel, Invasive weed optimization algorithm, Parameter optimization, Twin support vector machines

[PDF]

Cite: Huajuan Huang, Shifei Ding, Hong Zhu, and Xinzheng Xu, " Invasive Weed Optimization Algorithm for Optimizating the Parameters of Mixed Kernel Twin Support Vector Machines," Journal of Computers vol. 8, no. 8, pp. 2077-2084, 2013.