基于混沌理论和神经网络的交通量预测

针对目前交通量预测不能很好地满足智能交通管理需求的现状，分析交通量数据内在混沌特性，主要包括时间延迟、嵌入维数、关联维数及Lyapunov指数的计算，并将此分析耦合人工神经网络模型进行预测，最后给出北京环路上某车道交通量预测的实例，结果显示基于混沌时间序列分析的神经网络交通量预测在数据动力特征刻画及误差控制上有显著优势。

Traffic Volume Forecasting based on Chaos Theory and Neural Network Model

For the developing demand of intelligent transport systems not being satisfied by relatively lower prediction accuracy derived from traditional methods,a new forecasting model based on Chaos theory and Neural Network is developed,this paper has analyzed the Chaos property of traffic volume and calculated time delay,embedding dimension and Lyapunov exponent.Finally,the paper made a traffic prediction of urban highway in Beijing with a competitively better result especially in the aspect of tracing dynamic character and error control.