小波神经网络在短时交通流预测中的应用  

A Forecasting Model for Short-term Traffic Flow Based on Wavelet Neural Networks

作　　者：孟杰[1] 杨保成[1] 

机构地区：[1]常熟理工学院机械工程学院,江苏常熟215500

出　　处：《常熟理工学院学报》2012年第4期83-86,共4页Journal of Changshu Institute of Technology

摘　　要：研究了小波神经网络对于预测短时交通流的适应性,提出了利用小波神经网络的特性建立短时交通流预测模型;并利用苏州市某交叉口实测交通流量,运用小波神经网络建立了非线性回归预测模型,结果证明预测是可靠的,有助于城市交通流动态参数的预测,可为ITS的构建提供数据支持.The research of short-term traffic flow is reviewed first. Based on analyzing the highly non-linear characteristic and researching the advantage of wavelet neural networks in handling non-linear and unsteady signal, the adaptive of wavelet neural networks on forecasting short-term traffic flow is researched and a forecasting model utilizing wavelet neural networks is put forward. Besides, through the practical flow data of a cross in the city of Su- zhou, a nonlinear regressing model is built using wavelet neural networks. The result confirms the reliance and it can help the forecasting of urban dynamic flow, and it can also provide fundamental data for the intelligent traffic systems.

关 键 词：交通流预测 短时交通流 小波神经网络 预测模型 非线性回归 

分 类 号：U491.112[交通运输工程—交通运输规划与管理]