改进的支持向量机算法在短时交通流预测中的应用

摘要

The paper introduces cross-validation and grid-search method to optimize the prediction accuracy of Support Vector Machine models,the establishment of an improved Support Vector Machine prediction model,and applied to short-term traffic flow forecasting empirical analysis.The paper also uses the real time data of certain urban road to test the efficiency of the proposed model and the result is satisfactory.%把交叉验证和网格搜索算法引入支持向量机预测算法,建立了改进的支持向量机预测模型,并将其应用于短时交通流预测进行实证分析。以某城市道路的实时数据来对模型进行验证,预测结果表明了该模型的有效性。