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

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