CAJ | 학술논문

建立在统计学习理论和结构风险最小化准则基础上的支持向量回归(SVR)是处理小样本数据回归问题的有利工具,SVR的参数选取直接影响其学习性能和泛化能力.文中将SVR参数选取看作是参数的组合优化问题,确定组合优化问题的目标函数,采用实数量子进化算法(RQEA)求解组合优化问题进而优选SVR参数,形成RQEA-SVR,并应用RQEA-SVR求解交通流预测问题.仿真试验表明RQEA是优选SVR参数的有效方法,解决交通流预测问题具有优良的性能.
건립재통계학습이론화결구풍험최소화준칙기출상적지지향량회귀(SVR)시처리소양본수거회귀문제적유리공구,SVR적삼수선취직접영향기학습성능화범화능력.문중장SVR삼수선취간작시삼수적조합우화문제,학정조합우화문제적목표함수,채용실수양자진화산법(RQEA)구해조합우화문제진이우선SVR삼수,형성RQEA-SVR,병응용RQEA-SVR구해교통류예측문제.방진시험표명RQEA시우선SVR삼수적유효방법,해결교통류예측문제구유우량적성능.
Support Vector Regression(SVR) based on statistical learning theory and structural risk minimization principle is a powerful tool for solving small-sample regression problem,and selecting appropriate parameters is very crucial to learn accuracy and generalization performance of SVR.Firstly,the parameters selection of SVR is considered as a combinatorial optimization problem,and the objective function of optimization problem is set.Then,Real-coded Quantum Evolutionary Algorithm(RQEA) is employed to solve this problem furthermore to select appropriate parameters of SVR,which is called RQEA-SVR,and RQEA-SVR is applied to the problem of traffic flow forecasting.The experiment results show that the proposed method is an effective approach for parameters selection of SVR,and the good performance for traffic flow forecasting is obtained.