An Improved Ant Colony Optimization for Parameter Optimization using Support Vector Machine
Srujana Rongali1, Radhika Yalavarthi2

1Srujana Rongali, Department of Computer Science & Engineering, GIT, GITAM University, Visakhapatnam, India.
2Radhika Yalavarthi, Department of Computer Science & Engineering, GIT, GITAM University, Visakhapatnam, India. 

Manuscript received on 15 February 2017 | Revised Manuscript received on 22 February 2017 | Manuscript Published on 28 February 2017 | PP: 198-204 | Volume-6 Issue-3, February 2017 | Retrieval Number: C4868026317/17©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Support Vector Machine (SVM) is one of the significant classification technique and it can be applied in various areas like meteorology, financial data analysis etc. The performance of SVM is influenced by parameters like C, which is cost constant and kernel parameter. In this paper, an improved Ant Colony Optimization (IACO) technique is proposed to optimize the parameters of SVM. To evaluate the proposed approach, the experiment adopts five benchmark datasets. The developed approach was compared with the ACO-SVM algorithm proposed by Zhang et al. The experimental results of the simulation show that performance of the proposed method is encouraging.
Keywords: Support Vector Machines, Ant Colony Optimization, Parameter Optimization

Scope of the Article: Cross-Layer Optimization