自适应加权最小二乘支持向量机的短时交通流量预测
首发时间:2017-04-27
摘要:针对交通流量数据中可能包含异常数据点以及异常数据点对模型的影响,本文提出一种基于自适应加权最小二乘支持向量机(AWLS-SVM)的短时交通流量预测方法,该方法通过自适应地赋予每个样本合适的权值,以降低异常样本点对模型的影响。由于加权最小二乘支持向量机(WLS-SVM)的正则化参数、核宽参数以及权函数参数对模型的拟合精度和泛化能力有较大的影响,利用PSO算法的全局寻优能力对以上参数进行优化选择,以避免参数选择的盲目性。仿真实验表明AWLS-SVM能有效克服异常样本数据的影响,其模型预测性能优于WLS-SVM和LS-SVM。最后,利用实地调查的交通流量数据,建立AWLS-SVM短时交通流量预测模型,获得满意结果。
关键词: 自适应加权 最小二乘支持向量机 短时交通流量 粒子群优化
For information in English, please click here
Short-term traffic flow forecasting model based on adaptive weighted least squares support vector machine
Abstract:In order to eliminate the influence of unavoidable outliers in training sample on a model's performance, a novel adaptive weighted least squares support vector machine regression method (AWLS-SVM) is proposed. Firstly, least squares support vector machine regression is employed to develop model and obtain the sample data fitting error. Secondly, the initial weighted is calculated according to the fitting error of each sample. Thirdly, the partial swarm optimization algorithm (PSO) is applied to determine the optimal parameters of the AWLS-SVM with the adaptive sample weights. The simulation experiment results show that the outliers influence on the model's performance is eliminated in AWLS-SVM, and that the prediction performance is better than those of WLS-SVM and LS-SVM method. Furthermore, the AWLS-SVM method was applied to build short-term traffic flow forecasting model, and the satisfactory result is obtained.
Keywords: adaptive weighted;least squares support vector machine;short-term traffic flow;PSO
论文图表:
引用
No.4728157119465514****
同行评议
共计0人参与
勘误表
自适应加权最小二乘支持向量机的短时交通流量预测
评论
全部评论