Computer Engineering and Applications ›› 2014, Vol. 50 ›› Issue (15): 30-33.
Previous Articles Next Articles
LIU Jiajia, WANG Kai, YUAN Jianying, JIANG Xiaoliang, LI Bailin
Online:
Published:
刘甲甲,王 凯,袁建英,江晓亮,李柏林
Abstract: In the railway fastener detection system, RBF-SVM is used as image classifier for railway fasteners. The selection of kernel parameters is an important problem in RBF-SVM research. A parameter selection method based on quantum genetic algorithm(QPSO) is presented. Initial population is produced in the adjustable range of parameters c and [γ], and individuals in it are used as the parameters of RBF-SVM to calculation; then by multi-iterations, the parameters[(c,γ)] are obtained which are corresponding to fitness of population, and used as kernel parameters of Radial Basis kernel Function of Support Vector Machine(RBF-SVM) to training model. The experimental results indicate that the QPSO algorithm outperforms PSO algorithm. It has a high convergence and stability, and the detection algorithm of rail fastener based on it is practicable.
Key words: Quantum Particle Swarm Optimization(QPSO), Radial Basis Function(RBF), Support Vector Machine(SVM), model optimization, railway fastener
摘要: 在开发的铁路扣件检测系统中,RBF-SVM被作为扣件图像分类识别的分类器。核参数的选择是RBF-SVM模型优化研究中的重要问题,将量子粒子群算法应用于参数的优化选择,在[(c,γ)]参数可调范围内产生初始种群,将种群中的个体作为RBF-SVM的参数进行学习;经过多次迭代获得最佳参数对[(c,γ)],并将该参数对作为RBF-SVM的核参数训练支持向量机。实验表明,QPSO的性能优于传统的 PSO算法,该方法在解决支持向量机优化方面表现出了高效的收敛性和稳定性,并且在该方法的基础上形成的铁路扣件检测算法是切实可行的。
关键词: 量子粒子群算法, 径向基函数, 支持向量机, 模型优化, 铁路扣件
LIU Jiajia, WANG Kai, YUAN Jianying, JIANG Xiaoliang, LI Bailin. Optimization of RBF-SVM model in railway fastener detection system[J]. Computer Engineering and Applications, 2014, 50(15): 30-33.
刘甲甲,王 凯,袁建英,江晓亮,李柏林. 铁路扣件图像检测中的RBF-SVM模型优化[J]. 计算机工程与应用, 2014, 50(15): 30-33.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://cea.ceaj.org/EN/
http://cea.ceaj.org/EN/Y2014/V50/I15/30