Abstract: In order to develop the Intelligent Transportation System(ITS), combined RBF network with ARIMA forecast, a method of short-term traffic flow prediction is put forward. The hybrid forecasting method combines the two methods to make use of the non-linear RBF neural network which has a structure of three layers. The simulation test of the three forecasting methods is taken placed used field data, and the results show that the non-linear hybrid model, which takes advantage of the unique strength of the two models in linear and nonlinear modeling can produce more accurate predictions than that of single model. The hybrid model can be an efficient method to the short-term traffic flow prediction.

Key words: traffic flow, short-term prediction, RBF neural network, non-linear hybrid prediction

摘要： 为开发智能交通系统，提出一种基于RBF和ARIMA网络非线性组合模型的短时交通流预测方法，采用三层结构的RBF网络将2种单一预测方法——RBF和ARIMA网络进行非线性组合，利用实测数据对3类方法进行仿真实验，结果表明，非线性组合模型的预测准确性高于各自单独使用时的准确性，组合模型发挥了2种单一方法各自的优势，是短时交通流预测的有效方法。

关键词: 交通流, 短时预测, RBF神经网络, 非线性组合预测

CLC Number: 

• U491.14