基于粒子群优化最小二乘支持向量机的铁路客运量预测

Prediction of Railway Passenger Volume Based on Particle Swarm Optimization Least Square Support Vector Machine

对于铁路客运量预测的准确度问题,本研究提出了基于粒子群(PSO)优化最小二乘支持向量机(LS-SVM)重要参数的方法。以1995—2013年的铁路客运量历史数据作为训练集,2014—2018年的客运量作为测试集,用LS-SVM进行建模和预测。针对模型中参数难以选择问题,采用PSO全局搜索方法,与神经网络和LS-SVM的预测效果作比较,仿真表明,采用PSO优化LS-SVM对铁路客运量建模与预测效果更好,精度更高。

For the accuracy of railway passenger volume prediction,this study proposes a method based on particle swarm optimization(PSO) to optimize the important parameters of least square support vector machine(LS-SVM).The historical data of railway passenger volume from 1995 to 2013 is taken as the training set,and the passenger volume from 2014 to 2018 is taken as the test set.lS-SVM is used for modeling and prediction.In view of the difficulty of selecting parameters in the model,the PSO global search method is used to compare the prediction effect with the neural network and LS-SVM.The simulation results show that the lS-SVM optimized by PSO has better modeling and prediction effect and higher accuracy.