小波支持向量机在交通流量预测中的应用

摘要

The traffic flow prediction is the basis of intelligent traffic management system, and the traditional forecasting method can not accurately describe the characteristics of time-varying, sudden and nonlinearity of traffic flow,thus traffic flow prediction accuracy is low. In order to improve the prediction accuracy of traffic flow, the paper proposes a prediction model based on the wavelet analysis and support vector machine (SVM). Firstly, the traffic flow is decomposed by the wavelet analysis and traffic flow is smoothed, the high frequency and low frequency part of the traffic signal is obtained, then the flow is predicted by using support vector machine, the high frequency and low frequency part are reconstructed to form the flow predictive value. Simulation results show that the proposed model improves the traffic flow prediction accuracy and speed, and it is a new vigor for the traffic flow prediction research.%交通流量预测是智能交通管理系统的基础,预测某段单位时间内交通流量,难以准确刻画交通流量的时变性、突发性和非线性等变化规律,传统方法使交通流量预测精度低.为了提高交通流量的预测精度,提出小波分析的支持向量机预测模型,并应用于交通流量预测中.模型首先对交通流量进行小波分解,使交通流量平稳化,得到交通流量信号的高频和低频部分,采用支持向量机进行预测,最后将高频和低频部分的预测结果采用小波重构,获得最终预测值.仿真结果表明,小波支持向量机模型提高了交通流量预测精度和预测速度,为交通流量准确预测研究提供了依据.