摘要
公交站点客流量情况的及时准确预测对提供更可靠的公交服务和节省公交公司的运营成本是非常重要.首先对标准的LS-SVM算法进行了改进,得到一种新的SOR-LS-SVM学习算法.该算法不仅能减少计算的复杂性,提高学习速度;同时能提高函数估计的精确度.然后利用SOR-LS-SVM算法对公交站点的客流量情况进行预测和模拟.实验结果表明改进的SOR-LS-SVM算法具有较高的预测精度,且实验取得了较好效果.
Timely and accurately forecasting passenger volume in bus stops is important for transit operation and it can provide more reliable bus services and save operating costs. Based on the traditional least squares support vector machine（LS-SVM）, the improved algorithm of successive overrelaxation for Least squares support vector machine（SOR-LS-SVM） is presented. This methods can reduce compute complex and increase learning speed. At the same time, the new algorithm can improve accuracy of estimation. At last, the SOR-LS-SVM algorithm is applied to forecast passenger volume in bus stops. Experiment resut shows better effect and higher precision of forecasting by the SOR-LS-SVM algorithm.
出处
《湖南工程学院学报（自然科学版）》
2009年第4期68-71,共4页
Journal of Hunan Institute of Engineering(Natural Science Edition)
基金
大理学院科研基金资助项目(2005X23)
