CAJ | 학술논문

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。
재개발적철로구건검측계통중，RBF-SVM피작위구건도상분류식별적분류기。핵삼수적선택시RBF-SVM모형우화연구중적중요문제，장양자입자군산법응용우삼수적우화선택，재(c，γ)삼수가조범위내산생초시충군，장충군중적개체작위RBF-SVM적삼수진행학습；경과다차질대획득최가삼수대(c，γ)，병장해삼수대작위RBF-SVM적핵삼수훈련지지향량궤。실험표명，QPSO적성능우우전통적 PSO산법，해방법재해결지지향량궤우화방면표현출료고효적수렴성화은정성，병차재해방법적기출상형성적철로구건검측산법시절실가행적。
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 genet-ic 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.