Efficient Parameter Tuning of Support Vector Machine Based on Nesting Particle Swarm Optimization
Authors
Pin Liao, Sensen Wang, Xin Zhang, Kunlun Li, Mingyan Wang
Corresponding Author
Pin Liao
Available Online April 2015.
- DOI
- 10.2991/isrme-15.2015.102How to use a DOI?
- Keywords
- Support Vector Machine; Parameter Optimization; Particle Swarm Optimization; Nested Optimization Method; Gender Classification of Facial Images
- Abstract
Parameter optimization of Support Vector Machine (SVM) is an important research problem, because it is critical for establishing an effective SVM with excellent generalization. This study develops a novel and efficient method to solve this problem by nesting two particle swarm optimization (PSO) algorithms to optimize SVM kernel parameter(s) and penalty parameter separately, in comparison with traditional methods that try to optimize all the parameters concurrently. The experimental results on gender classification of facial images validate the feasibility and quickness of the new method.
- Copyright
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Pin Liao AU - Sensen Wang AU - Xin Zhang AU - Kunlun Li AU - Mingyan Wang PY - 2015/04 DA - 2015/04 TI - Efficient Parameter Tuning of Support Vector Machine Based on Nesting Particle Swarm Optimization BT - Proceedings of the 2015 International Conference on Intelligent Systems Research and Mechatronics Engineering PB - Atlantis Press SP - 478 EP - 481 SN - 1951-6851 UR - https://doi.org/10.2991/isrme-15.2015.102 DO - 10.2991/isrme-15.2015.102 ID - Liao2015/04 ER -