点击次数：

论文类型：期刊论文

发表时间：2009-06-01

发表刊物：Journal of Information and Computational Science

收录刊物：EI、Scopus

卷号：6

期号：3

页面范围：1287-1294

ISSN号：15487741

摘要：Traffic flow is a fundamental measure in transportation. Accurate traffic flow forecasting also is crucial to the development of intelligent transportation systems and advanced traveler information systems. As one of data mining techniques, forecasting is widely used to predict the unknown future based upon the patterns hidden in the current and past data. This paper employs support vector machine (SVM) combined with data mining technology to forecast traffic flow. With this method it can decrease SVM training data and eliminate redundant information from the huge data set. Compared to single SVM and back-propagation neural networks (BPNN), the proposed method can speed up processing and achieve higher forecasting accuracy in short-term traffic flow forecasting. It demonstrates the feasibility of applying SVM to traffic flow forecasting based on data mining technology. 1548-7741/ Copyright ? 2009 Binary Information Press.