【作者】 魏善冠；

【导师】 张绍阳；

【作者基本信息】 长安大学 ， 计算机软件与理论， 2010， 硕士

【摘要】 交通量的预测是提高交通运输管理水平、降低运输成本的重要手段之一,同时也是进行交通状况评价、路网规划、线路改造以及工程建设项目可行性分析的基础。因此,研究高速公路交通量预测具有重要的意义。本文在深入分析比较各种交通量预测方法的基础上,研究了利用支持向量机进行交通量预测方法并进行了实际应用。首先,对收费站出口数据进行了数据预处理,使之转化为预测分析数据集。然后,深入的研究了灰色理论预测方法和神经网络预测方法,并使用这些方法对现有数据集进行对比预测。重点研究了支持向量机预测模型的建模方法,包括数据归一化、核函数选择、模型参数选择等,建立了基于支持向量机的交通量预测模型,对西潼高速公路的渭南西与渭南东两站间的路段进行了交通量预测,平均误差率仅为2.5%。最后对基于支持向量机交通量预测软件进行了详细设计。预测结果表明,支持向量机用于交通量的预测是可行及有效的。所研究的支持向量机预测模型在陕西省公路资源整合项目的“综合分析决策支持系统”中得到了应用。更多还原

【Abstract】 Traffic prediction is one of the important means to improve the transportation management level and reduce the cost of transportation. Simultaneously, it is also the foundation of road network planning, traffic evaluation and feasibility analysis of construction projects.Therefore, the research on highway traffic prediction has important significance.Based on the analysis and comparation of various traffic prediction methods, traffic prediction method using support vector machine (SVM) and conducted practical application are studied in this paper. First, the toll data of export is preprocessed into prediction analysis data sets.Then, the grey prediction methods and neural network prediction methods are researched, and these methods are used to conduct comparison of prediction about existing data sets in the paper. Support vector machine prediction model, including data normalization, selection of kernel function, selection of model parameter etc. are deeply studied. After that, the forecasting model of traffic based on support vector machine is established. The model is used to predict the road traffic between the station of Weinan Xi and Weinan Dong in Xitong highway, the average error is limited 2.5%.Finally, the paper gave the detailed design of support vector machine forecasting method based on support vector machine.The prediction results show that the prediction of traffic using the support vector machine (SVM) is feasible and effective.The support vector machine prediction model has been applied in "comprehensive analysis and decision support system" for road resource integration project of Shaanxi province.更多还原